CN109389838A - Unmanned crossing paths planning method, system, equipment and storage medium - Google Patents
Unmanned crossing paths planning method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN109389838A CN109389838A CN201811417693.9A CN201811417693A CN109389838A CN 109389838 A CN109389838 A CN 109389838A CN 201811417693 A CN201811417693 A CN 201811417693A CN 109389838 A CN109389838 A CN 109389838A
- Authority
- CN
- China
- Prior art keywords
- crossing
- traffic police
- instruction
- traffic
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Atmospheric Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of unmanned crossing paths planning method, system, equipment and storage medium, this method includes the image for acquiring vehicle front, and the running environment of vehicle front is judged according to image；If it is crossing environment, detect in described image with the presence or absence of traffic lights and traffic police；If detecting traffic police in the picture, determine that traffic police instructs according to the gesture of traffic police；If detecting traffic lights in described image, determine that signal lamp instructs according to the image of traffic lights；The path planning for determining that vehicle travels at crossing is instructed according to traffic police's instruction and/or signal lamp, path planning decision may further be carried out by trained Controlling model.By using the solution of the present invention, when there is crossroad traffic signal lamp failure or congestion needs traffic police to direct traffic, it can accurately identify and combine traffic lights and traffic police's gesture to plan suitable path for traffic police's gesture in real time, automatic driving vehicle is helped to pass through crossroad.
Description
Technical field
The present invention relates to unmanned technical field more particularly to a kind of unmanned crossing paths planning method, system,
Equipment and storage medium.
Background technique
Unmanned Systems are divided into sensory perceptual system, decision rule system and executing agency；Wherein perception and decision rule system
The core system united as unmanned algorithm, plays a crucial role.Currently, for nobody in crossroad environment
The identification that sensing module is based primarily upon traffic lights and traffic sign is driven, and unmanned garage is calculated based on traffic rules
Path is sailed, and for there is traffic police to command the crossroad path planning under intervening less, when crossroad access signal lamp failure
Or congestion is when needing traffic police to direct traffic, and will be unable to command in accordance with traffic police and passes through crossroad.
Summary of the invention
For the problems of the prior art, the purpose of the present invention is to provide a kind of unmanned crossing path planning sides
Method, system, equipment and storage medium overcome when crossroad traffic signal lamp failure or congestion need traffic police to direct traffic, by nothing
The problem of method passes through crossing in accordance with traffic police commander, accurately identifies for traffic police's gesture and combines traffic lights and traffic police's hand
Gesture plans suitable path.
The embodiment of the present invention provides a kind of unmanned crossing paths planning method, and described method includes following steps:
The image for acquiring vehicle front, the running environment of vehicle front is judged according to described image；
If the running environment of vehicle front is crossing environment, detect in described image with the presence or absence of traffic lights and
Traffic police；
If detecting traffic police in described image, determine that traffic police instructs according to the gesture of traffic police；
If detecting traffic lights in described image, determine that signal lamp instructs according to the image of traffic lights；
The path planning for determining that vehicle travels at crossing is instructed according to traffic police's instruction and/or signal lamp.
Optionally, the method also includes following steps:
The image of multiple crossing environment and multiple non-crossing environment is acquired as training set, training environment identification model,
The input of the Context awareness model is image, is exported as running environment type；
The running environment that vehicle front is judged according to described image, includes the following steps:
Described image is inputted into the Context awareness module, judges the running environment type of output for crossing environment also right and wrong
Crossing environment.
Optionally, the method also includes following steps:
Image that multiple traffic police shoot in different angle is acquired as training set, training traffic police's identification model is described
The input of traffic police's identification model is image, is exported whether to detect the result of traffic police；
It whether there is traffic lights in the detection described image, include the following steps:
Described image is inputted into traffic police's identification model, whether friendship is detected according to the output result judgement of model
It is alert.
Optionally, the method also includes following steps:
Acquisition indicates that traffic police's gesture of each different instruction is used as training set, trained traffic police in the image of multiple and different angles
Gesture identification model, the input of traffic police's gesture identification model are image, are exported as traffic police's instruction；
The gesture according to traffic police determines that traffic police instructs, and includes the following steps:
The image that the arm segment of traffic police is intercepted from described image, inputs traffic police's gesture identification for truncated picture
Model determines that traffic police instructs according to the output result of model.
Optionally, described that the path planning for determining that vehicle travels at crossing, packet are instructed according to traffic police's instruction and/or signal lamp
Include following steps:
Current crossing operating condition is determined according to detecting that traffic police's instruction or signal lamp instruct in image；
Current crossing operating condition, the traffic police detected instruction and/or signal lamp instruction are inputted as Controlling model, are input to
Trained crossing path planning Controlling model, obtains the vehicle control instruction that vehicle travels at crossing, and the vehicle control refers to
Enable includes at least one of steering wheel angle signal, throttle signal, brake pedal signal and steering modulating signal of vehicle.
Optionally, described according to traffic police's instruction or the determining current crossing operating condition of signal lamp instruction is detected in image, it wraps
Include following steps:
If currently only detecting that traffic police instructs, current crossing operating condition is that traffic signal light fault traffic police commands operating condition；
If currently only detecting that signal lamp instructs, current crossing operating condition is traffic lights normally without traffic police's operating condition；
If being currently detected simultaneously by traffic police's instruction and signal lamp instruction, current crossing operating condition is that traffic lights are normal
There is traffic police's operating condition.
Optionally, described that the path planning for determining that vehicle travels at crossing is instructed according to traffic police's instruction and/or signal lamp, also
Include the following steps:
Obtain the survey of the measurement data, the measurement data of Inertial Measurement Unit, laser radar of the GPS positioning instrument of vehicle setting
The measurement data of amount data and millimetre-wave radar refers to as the input of Controlling model with current crossing operating condition, the traffic police detected
It enables and/or signal lamp instruction inputs trained crossing path planning Controlling model together.
Optionally, the method also includes following steps:
Driver is acquired in the intersection data at each crossing, the intersection data includes the crossing operating condition at corresponding crossing, hands over
Measurement data, the measurement data of Inertial Measurement Unit, laser thunder of the GPS positioning instrument of alert instruction, signal lamp instruction, vehicle setting
The measurement data of the measurement data and millimetre-wave radar that reach；
Driver is acquired in the driving data at each crossing, the driving data includes the steering wheel of the vehicle at corresponding crossing
Angular signal, throttle signal, brake pedal signal and steering modulating signal；
The intersection data of driver and driving data are matched according to crossing position and time, Controlling model is added
Training set, training crossing path planning Controlling model, the input of the crossing path planning Controlling model are intersection data, output
For driving data.
Optionally, described that the path planning for determining that vehicle travels at crossing, packet are instructed according to traffic police's instruction and/or signal lamp
Include following steps:
Judge whether to be detected simultaneously by traffic police's instruction and signal lamp instruction；
If only detecting that traffic police instructs, the path planning for determining that vehicle travels at crossing is instructed according to traffic police；
If only detecting that signal lamp instructs, the path planning for determining that vehicle travels at crossing is instructed according to signal lamp；
If being detected simultaneously by traffic police's instruction and signal lamp instruction, further judges traffic police's instruction and signal lamp instruction is
It is no to exist unanimously；
If there is path planning that is consistent, then being travelled according to the determining vehicle of consistent instruction at crossing；
If it is inconsistent, processing request is sent to cloud server, determined according to the instruction that cloud server returns
The path planning that vehicle travels at crossing.
Optionally, the method also includes following steps:
The cloud server stores the position data at each crossing；
The current position of vehicle, the image that vehicle acquires and the traffic police detected are instructed and/or are believed by Vehicle Controller
Signal lamp instruction is sent to the cloud server；
The cloud server determines the position at vehicle front crossing according to the image that the current position of vehicle and vehicle acquire
Range is set, the director data that vehicle detection corresponding to the crossing arrives is stored.
Optionally, the traffic police that the processing request is arrived including the current position of vehicle, the image of vehicle acquisition, vehicle identification
Instruction and signal lamp instruction；
It is described to request processing after being sent to cloud server, further include following steps:
After the cloud server receives the processing request, according to the image of the current position of vehicle and vehicle acquisition
Determine the position range at the crossing of vehicle front；
The cloud server judges that other vehicles for whether having quantity to be greater than preset threshold in present period upload the road
Traffic police's instruction that mouth detects；
If it is, the cloud server integrates traffic police's instruction that all vehicles upload in present period, according to ballot
Decision-making mechanism determines the instruction of the crossing present period；
The instruction of the crossing present period is back to the vehicle for sending processing request by the cloud server.
Optionally, the method also includes following steps:
The cloud server receives the traffic signal light condition Notification of Changes at each crossing, according to Notification of Changes change pair
Answer the traffic signal light condition at crossing；
The cloud server receives the traffic police commander that traffic police reports and starts notice and position data, more according to position data
The traffic police at new corresponding crossing commands state；
The cloud server judges whether have other vehicles to upload the director data that the crossing detects in present period
Later, further include following steps:
If uploading traffic police's instruction that the crossing detects without other vehicles in present period, the cloud server is sentenced
Break the corresponding traffic signal light condition in the crossing；
If the corresponding traffic signal light condition in the crossing is failure, the friendship that the cloud server arrives vehicle detection
Alert instruction is back to the vehicle for sending processing request as the instruction at the crossing；
If the corresponding traffic signal light condition in the crossing be it is normal, when the cloud server judges that the crossing is current
The traffic police commander that traffic police reports whether is received quarter before to start to notify and do not receive the traffic police that traffic police reports and command to terminate to lead to
Know, if it is, the cloud server by vehicle detection to traffic police's instruction be back at transmission as the instruction at the crossing
Manage the vehicle of request.
Optionally, the method also includes following steps:
Obtain the programme path between the departure place and destination of vehicle driving；
Extract the position data at each crossing in programme path；
It is inquired according to the position data at each crossing in the cloud server, judges each crossing in present period
Instruction type；
If instruction type of the crossing in present period is traffic police's instruction, further judge that the traffic police at the crossing refers to
Enabling, which whether there is with the driving direction at the crossing in programme path, conflicts；
If there is conflict, then the Some routes for passing through the crossing in the programme path are changed to other optional routes.
The embodiment of the present invention also provides a kind of unmanned crossing path planning system, applied to the unmanned road
Mouth paths planning method, the system comprises:
Image capture module, for acquiring the image of vehicle front；
Running environment judgment module, for judging the running environment of vehicle front according to described image；
Instruction detection module whether there is traffic lights and traffic police in the image for detecting crossing environment；If
Traffic police is detected in described image, determines that traffic police instructs according to the gesture of traffic police；If detecting that traffic is believed in described image
Signal lamp determines that signal lamp instructs according to the image of traffic lights；
Path planning module, for instructing the path for determining that vehicle travels at crossing according to traffic police's instruction and/or signal lamp
Planning.
The embodiment of the present invention also provides a kind of unmanned crossing route design device, comprising:
Processor；
Memory, wherein being stored with the executable instruction of the processor；
Wherein, the processor is configured to execute the unmanned crossing road via the executable instruction is executed
The step of diameter planing method.
The embodiment of the present invention also provides a kind of computer readable storage medium, and for storing program, described program is performed
Described in Shi Shixian the step of unmanned crossing paths planning method.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Unmanned crossing paths planning method, system, equipment and storage medium provided by the present invention have following excellent
Point:
The present invention solves the problems of the prior art, needs traffic police to command when there is crossroad traffic signal lamp failure or congestion
When traffic, it can accurately identify and combine traffic lights and traffic police's gesture to plan suitable road for traffic police's gesture in real time
Diameter helps automatic driving vehicle to pass through crossroad.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon.
Fig. 1 is the flow chart of the unmanned crossing paths planning method of one embodiment of the invention；
Fig. 2 is the schematic diagram of the Controlling model of one embodiment of the invention；
Fig. 3 is the stream of the right instructions that determining crossing is instructed according to traffic police's instruction and signal lamp of another embodiment of the present invention
Cheng Tu；
Fig. 4 is that the cloud server of another embodiment of the present invention requests to determine the flow chart of the instruction at crossing according to processing；
Fig. 5 is the flow chart of the fullpath planning of another embodiment of the present invention；
Fig. 6 is the structural schematic diagram of the unmanned crossing path planning system of one embodiment of the invention；
Fig. 7 is the schematic diagram of the unmanned crossing route design device of one embodiment of the invention；
Fig. 8 is the signal of the external equipment being connected with unmanned crossing route design device of one embodiment of the invention
Figure；
Fig. 9 is the schematic diagram of the computer readable storage medium of one embodiment of the invention.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
As shown in Figure 1, in order to solve the above-mentioned technical problem, the embodiment of the present invention provides a kind of unmanned crossing path rule
The method of drawing, described method includes following steps:
S100: Vehicle Controller acquires the image of vehicle front by camera, judges vehicle front according to described image
Running environment, specially judge that the running environment of vehicle front for crossing environment is also non-crossing environment；
S200: if the running environment of vehicle front be crossing environment, Vehicle Controller detect described image in whether
There are traffic lights and traffic police；
S300: if detecting traffic police in described image, Vehicle Controller determines that traffic police refers to according to the gesture of traffic police
Enable, the instruction of traffic police mainly include stop, allowing to keep straight on, allow to turn left, allowing to turn right, turn left wait turn, lane change, slow down,
One of pulling over observing etc. or a variety of combinations；
S400: if detecting traffic lights in described image, Vehicle Controller is according to the figures of traffic lights
As determining signal lamp instruction；Signal lamp instruction includes but is not limited to allow to keep straight on, forbid keeping straight on, allow left-hand rotation, no left turn, permit
Perhaps right-hand rotation, no right turn, allow to turn around, one of no turns etc. or a variety of combinations.
S500: Vehicle Controller is instructed according to traffic police and/or signal lamp instructs and determines that vehicle is advised in the path that crossing travels
It draws.
In this embodiment, the unmanned crossing paths planning method is mainly executed by Vehicle Controller, specifically
Ground can also use other executing subjects, for example, using unmanned crossing road described in the mobile terminal execution bound with vehicle
Diameter planing method, or described unmanned crossing paths planning method etc. is executed using cloud server, belong to the present invention
Protection scope within.
The number of step is only to distinguish each step herein, without indicating that the sequence between step, above-mentioned steps can also be with
Reversed order, as long as being able to achieve technical solution of the present invention.
In this embodiment it is possible to realize the identification of running environment by creation Context awareness model.The method is also
Include the following steps:
The image of multiple crossing environment and multiple non-crossing environment is acquired as training set, training environment identification model,
The input of the Context awareness model is image, is exported as running environment type, and existing support vector machines can be used in training
Training method or convolutional neural networks training method etc.；
The running environment that vehicle front is judged according to described image, includes the following steps:
Described image is inputted into the Context awareness module, judges the running environment type of output for crossing environment also right and wrong
Crossing environment.
However, the present invention is not limited thereto, can also be using other Context awareness algorithms, for example, the spy in label crossing environment
It levies and records, the image of acquisition is compared with the feature in the environment of crossing, judge whether unanimously, to be judged according to comparison result
The type of running environment.
It in this embodiment, can also be specifically, described using the method for training identification model to the identification of traffic police's identity
Method further includes following steps:
Image that multiple traffic police shoot in different angle is acquired as training set, training traffic police's identification model is described
The input of traffic police's identification model is image, is exported whether to detect the result of traffic police；
It whether there is traffic lights in the detection described image, include the following steps:
Described image is inputted into traffic police's identification model, whether friendship is detected according to the output result judgement of model
It is alert.
The feature of traffic police can be grabbed from positions such as the fluorescence clothes of traffic police, police uniform, cap, police emblems, and training traffic police's identity is known
The method of other model can also be using the training of the modes such as existing support vector machines or convolutional neural networks.Alternatively, it is also possible to adopt
With other traffic police's recognizers, all belong to the scope of protection of the present invention within.
When detecting traffic lights, identification traffic lights can be passed through to the identification of the instruction of traffic lights
Color, position, shape identify.
When detecting traffic police, further the gesture of traffic police is identified, it similarly, in this embodiment, can also be with
It is realized by establishing traffic police's gesture identification model, specifically, the method also includes following steps:
Acquisition indicates that traffic police's gesture of each different instruction is used as training set, trained traffic police in the image of multiple and different angles
Gesture identification model, the input of traffic police's gesture identification model are image, are exported as traffic police's instruction；Trained mode can also be with
Using existing training method of support vector machine or convolutional neural networks training method etc.；
The gesture according to traffic police determines that traffic police instructs, and includes the following steps:
The image that the arm segment of traffic police is intercepted from described image, inputs traffic police's gesture identification for truncated picture
Model determines that traffic police instructs according to the output result of model.
In addition, identify to traffic police's gesture using other traffic police's gesture algorithms also possible, the present invention is belonged to
Protection scope within.For example, identifying the hand motion of traffic police in the picture, the image of hand motion is handled, according to
Gesture graphing, using matrix form to graphical configuration mode, mode corresponding to the image by acquisition with it is preset several
Mode corresponding to gesture-type is compared, and can determine gesture-type corresponding to acquisition image.
In an embodiment of the present invention, the path planning of crossing traveling can be realized using Controlling model end to end.
Specifically, in this embodiment, described instructed according to traffic police's instruction and/or signal lamp determines that vehicle is advised in the path that crossing travels
It draws, includes the following steps:
Current crossing operating condition is determined according to detecting that traffic police's instruction or signal lamp instruct in image；
Current crossing operating condition, the traffic police detected instruction and/or signal lamp instruction are inputted as Controlling model, are input to
Trained crossing path planning Controlling model, obtains the vehicle control instruction that vehicle travels at crossing, and the vehicle control refers to
Enable includes at least one of steering wheel angle signal, throttle signal, brake pedal signal and steering modulating signal of vehicle.
It is described according to detecting that traffic police's instruction or signal lamp instruction determine current crossing operating condition in image, including walk as follows
It is rapid:
If currently only detecting that traffic police instructs, current crossing operating condition is that traffic signal light fault traffic police commands operating condition；
If currently only detecting that signal lamp instructs, current crossing operating condition is traffic lights normally without traffic police's operating condition；
If being currently detected simultaneously by traffic police's instruction and signal lamp instruction, current crossing operating condition is that traffic lights are normal
There is traffic police's operating condition.
As shown in Fig. 2, the schematic diagram of the crossing path planning Controlling model for one embodiment of the invention.Wherein, it inputs and is
Intersection data exports as driving data.Input can be a Multidimensional numerical for including multiple parameters, for example, numerically
The type of crossing operating condition, 1 indicates that traffic signal light fault traffic police commands operating condition, 2 indicate traffic lights normally without traffic police's operating condition,
3 expression traffic lights normally have traffic police's operating condition；The type instructed using digital representation traffic police, for example, 1 indicates to move ahead, 2 are indicated
Turn left etc., it is instructed using digital representation signal lamp, for example, 1 indicates to move ahead, and 2 expressions are turned left etc., if not detecting that traffic police refers to
It enables, then it is 0 that traffic police, which instructs corresponding dimension, if not detecting that signal lamp instructs, the corresponding dimension of signal lamp instruction is
0.Output is also possible to a Multidimensional numerical, including four dimensions: steering wheel angle signal, throttle signal, brake pedal signal
With steering modulating signal, the different value of each dimension can indicate different control instructions.
Further, in this embodiment, described instructed according to traffic police's instruction and/or signal lamp determines vehicle in crossing row
The path planning sailed can also include the following steps:
Obtain the survey of the measurement data, the measurement data of Inertial Measurement Unit, laser radar of the GPS positioning instrument of vehicle setting
The measurement data of amount data and millimetre-wave radar refers to as the input of Controlling model with current crossing operating condition, the traffic police detected
It enables and/or signal lamp instruction inputs trained crossing path planning Controlling model together.
Specifically, outputting and inputting for Controlling model can be adjusted with needs according to the actual situation end to end, and
Not to be limited list and figure herein shown in.
The crossing path planning Controlling model of the embodiment, can by acquire in advance the driving habit data of driver into
Row study, using neural network or other machines learning model, and can continue to optimize Controlling model, optimal model ginseng
Number.
In this embodiment, it before training pattern, needs to acquire the data of training set first, specifically, acquires driver
Intersection data at each crossing, the intersection data include the crossing operating condition at corresponding crossing, traffic police instruction, signal lamp instruction,
Measurement data, the measurement data of Inertial Measurement Unit, the measurement data of laser radar and the millimeter of the GPS positioning instrument of vehicle setting
The measurement data of wave radar；
Driver is acquired in the driving data at each crossing, the driving data includes the steering wheel of the vehicle at corresponding crossing
Angular signal, throttle signal, brake pedal signal and steering modulating signal；
The intersection data of driver and driving data are matched according to crossing position and time, Controlling model is added
Training set, i.e., in training set include each intersection data group and with each one-to-one driving data of intersection data group, training
The input of crossing path planning Controlling model, the crossing path planning Controlling model is intersection data, is exported as driving data.
As shown in figure 3, the present invention also provides the paths planning methods in another embodiment, it is in this embodiment, described
The path planning for determining that vehicle travels at crossing is instructed according to traffic police's instruction and/or signal lamp, is included the following steps:
Judge whether to be detected simultaneously by traffic police's instruction and signal lamp instruction；
If only detecting that traffic police instructs, the path planning for determining that vehicle travels at crossing is instructed according to traffic police, at this time
Illustrate that current crossing does not have traffic lights or traffic signal light fault, then traffic police of being subject to indicates；
If only detecting that signal lamp instructs, the path planning for determining that vehicle travels at crossing is instructed according to signal lamp,
Illustrate to command currently without traffic police at the crossing at this time, it is only necessary to carry out path planning according to the instruction of traffic lights；
If being detected simultaneously by traffic police's instruction and signal lamp instruction, further judges traffic police's instruction and signal lamp instruction is
It is no to exist unanimously；
If there is path planning that is consistent, then being travelled according to the determining vehicle of consistent instruction at crossing；Traffic police refers to herein
Order is consistent with signal lamp instruction, it is identical to can be the two, such as traffic police's instruction is to allow to keep straight on, and signal lamp instruction is also
Allow to keep straight on, then determines that vehicle, to keep straight on, it is consistent to be also possible to part, such as traffic police's instruction is that permission is straight at the crossing at this time
Row, and signal lamp instruction includes allowing to keep straight on and allow to turn right, then the part being overlapped according to the two allows determining vehicle of keeping straight on
It is straight trip at the crossing；
If inconsistent, in order to avoid identification error, then processing request is sent to cloud server, by cloud server
Judgement processing is carried out, the path planning that vehicle travels at crossing is determined according to the instruction that cloud server returns.Cloud server
The upload data that multiple vehicles can be integrated integrated and can in conjunction with the feedback of traffic police department, traffic lights it is anti-
Information, the comprehensive descision crossing such as feedback and road conditions report, weather forecast correctly instruct.
The embodiment furthermore presents a kind of cloud server and judges the scheme that crossing correctly instructs, but intelligible
It is that this scheme is merely illustrative, not as the limitation of the scope of the present invention.
In this embodiment, the unmanned crossing paths planning method further includes following steps:
The cloud server stores the position data at each crossing；
The current position of vehicle, the image that vehicle acquires and the traffic police detected are instructed and/or are believed by Vehicle Controller
Signal lamp instruction is sent to the cloud server；Vehicle Controller herein is not limited to the Vehicle Controller of automatic driving vehicle,
In the vehicle for thering is driver to operate, if Vehicle Controller joined car networking, the information of acquisition can also be uploaded into cloud
Server is held, more data is provided for cloud server judgement and supports；
The cloud server determines the position at vehicle front crossing according to the image that the current position of vehicle and vehicle acquire
Range is set, the director data that vehicle detection corresponding to the crossing arrives is stored.
In this embodiment, the processing request is arrived including the current position of vehicle, the image of vehicle acquisition, vehicle identification
Traffic police instruction and signal lamp instruction；
As shown in figure 4, described request processing after being sent to cloud server, further include following steps:
After the cloud server receives the processing request, according to the image of the current position of vehicle and vehicle acquisition
It is right can to navigate to the vehicle institute for sending and handling and requesting according to the position range for the position range for determining the crossing of vehicle front
The crossing answered；
The cloud server judges that other vehicles for whether having quantity to be greater than preset threshold in present period upload the road
Traffic police's instruction that mouth detects；For example, setting preset threshold as 2, i.e., other than the vehicle, it is also necessary at least two vehicles
Upload traffic police's instruction that the crossing detects；
If it is, the cloud server integrates traffic police's instruction that all vehicles upload in present period, according to ballot
Decision-making mechanism determines the instruction of the crossing present period；The judgement of traffic police's gesture can be further improved using ballot decision-making mechanism
Accuracy rate；
The instruction of the crossing present period is back to the vehicle for sending processing request by the cloud server.
Due to relying solely on the acquisition information of vehicle upload, the data volume of cloud server can be smaller, in the short time
It is interior to form effective judgment basis, therefore.Cloud server can be combined with the traffic lights at each crossing itself
Feedback and the feedback of traffic police department, traffic intersection information etc. carry out comprehensive descision.Specifically, the method also includes walking as follows
It is rapid:
The cloud server receives the traffic signal light condition Notification of Changes at each crossing, according to Notification of Changes change pair
Answer the traffic signal light condition at crossing；
The cloud server receives the traffic police commander that traffic police reports and starts notice and position data, more according to position data
The traffic police at new corresponding crossing commands state；
The cloud server judges whether have other vehicles to upload the director data that the crossing detects in present period
Later, further include following steps:
If uploading traffic police's instruction that the crossing detects without other vehicles in present period, the cloud server is sentenced
Break the corresponding traffic signal light condition in the crossing；
If the corresponding traffic signal light condition in the crossing is failure, the friendship that the cloud server arrives vehicle detection
Alert instruction is back to the vehicle for sending processing request as the instruction at the crossing；
If the corresponding traffic signal light condition in the crossing be it is normal, when the cloud server judges that the crossing is current
The traffic police commander that traffic police reports whether is received quarter before to start to notify and do not receive the traffic police that traffic police reports and command to terminate to lead to
Know, if it is, the cloud server by vehicle detection to traffic police's instruction be back at transmission as the instruction at the crossing
The vehicle of request is managed, otherwise, cloud server can further request traffic control department, and traffic control department is asked to assist to determine that the crossing is worked as
Preceding right instructions.
As shown in figure 5, being based on above scheme, the correct of each crossing current time is stored in the cloud server
Instruction, then can be according to the method also includes following steps:
Vehicle Controller obtains the programme path between the departure place and destination of vehicle driving；Since programme path is general
It is to be planned according to the instruction of traffic lights and existing traffic sign, without in view of may currently there is friendship
It alert the case where directing traffic, may be deviated；
Vehicle Controller extracts the position data at each crossing in programme path；
Vehicle Controller is inquired according to the position data at each crossing in the cloud server, judges that each crossing is being worked as
Instruction type in the preceding period；
If instruction type of the crossing in present period is traffic police's instruction, Vehicle Controller further judges the road
Traffic police's instruction of mouth whether there is with the driving direction at the crossing in programme path to conflict；
If there is conflict, in that case, it is possible that after vehicle comes this crossing, it can not be according to set rule
The case where drawing route walking, therefore the Some routes for passing through the crossing in the programme path are changed to it in advance by Vehicle Controller
His optional route.
The distance between departure place and destination can have certain limit value, and destination is also not necessarily referring to finally herein
Destination, the distance between departure place and final destination can be segmented, when each section of progress path planning, be taken from cloud
Business device gets the information whether each crossing of current road segment has traffic police to direct traffic, and adjusts current road segment according to the information
Path planning, when driving to current road segment, then traffic police's command information at each crossing in next section is obtained, under adjustment
The path planning in one section, to guarantee the timeliness that traffic police's command information obtains.
Using this kind of mode, it not only can utmostly optimize the unmanned path planning at crossing, it can be with excellent
Change the unmanned path planning in whole section of distance.
As shown in fig. 6, the embodiment of the present invention also provides a kind of unmanned crossing path planning system, applied to described
Unmanned crossing paths planning method, the system comprises:
Image capture module 100, for acquiring the image of vehicle front；
Running environment judgment module 200, for judging the running environment of vehicle front according to described image；
Instruction detection module 300 whether there is traffic lights and traffic police in the image for detecting crossing environment；If
Traffic police is detected in described image, determines that traffic police instructs according to the gesture of traffic police；If detecting traffic in described image
Signal lamp determines that signal lamp instructs according to the image of traffic lights；
Path planning module 400, for instructing the road for determining that vehicle travels at crossing according to traffic police's instruction and/or signal lamp
Diameter planning.
The embodiment of the present invention also provides a kind of unmanned crossing route design device, including processor；Memory, wherein
It is stored with the executable instruction of the processor；Wherein, the processor is configured to hold via the executable instruction is executed
The step of unmanned crossing paths planning method described in row.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as " circuit ", " module " or " platform ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 7.The electronics that Fig. 7 is shown
Equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 7, electronic equipment 600 is showed in the form of universal computing device.The combination of electronic equipment 600 can wrap
Include but be not limited to: at least one processing unit 610, at least one storage unit 620, connection different platform combination (including storage
Unit 620 and processing unit 610) bus 630, display unit 640 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that the processing unit 610 executes described in this specification above-mentioned electronic prescription circulation processing method part according to this
The step of inventing various illustrative embodiments.For example, the processing unit 610 can execute step as shown in fig. 1.
The storage unit 620 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 6201 and/or cache memory unit 6202 can further include read-only memory unit (ROM) 6203.
The storage unit 620 can also include program/practical work with one group of (at least one) program module 6205
Tool 6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 660 can be communicated by bus 630 with other modules of electronic equipment 600.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 600, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage platform etc..
As shown in figure 8, in this embodiment, the external equipment 700 communicated with electronic equipment 600 can also include camera shooting
Head, laser radar, millimetre-wave radar, GPS, V2X (Vehicle toeverything, vehicle are exchanged with external information) equipment,
Domain controller/industrial personal computer etc. obtains the data of detection, the input as unmanned crossing path planning from external equipment 700.
External equipment 700 is only for example herein, and the communication modes of each equipment and route design device are also only example, and the present invention is unlimited
In this.
The embodiment of the present invention also provides a kind of computer readable storage medium, and for storing program, described program is performed
Described in Shi Shixian the step of unmanned crossing paths planning method.In some possible embodiments, of the invention each
A aspect is also implemented as a kind of form of program product comprising program code, when described program product is in terminal device
When upper operation, said program code is for making the terminal device execute this specification above-mentioned electronic prescription circulation processing method portion
Point described according to the present invention various illustrative embodiments the step of.
Refering to what is shown in Fig. 9, describing the program product for realizing the above method of embodiment according to the present invention
800, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In conclusion compared with prior art, unmanned crossing paths planning method provided by the present invention, system,
Equipment and storage medium have the advantage that
The present invention solves the problems of the prior art, needs traffic police to command when there is crossroad traffic signal lamp failure or congestion
When traffic, it can accurately identify and combine traffic lights and traffic police's gesture to plan suitable road for traffic police's gesture in real time
Diameter helps automatic driving vehicle to pass through crossroad.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (16)
1. a kind of unmanned crossing paths planning method, which comprises the steps of:
The image for acquiring vehicle front, the running environment of vehicle front is judged according to described image；
If the running environment of vehicle front is crossing environment, detect in described image with the presence or absence of traffic lights and friendship
It is alert；
If detecting traffic police in described image, determine that traffic police instructs according to the gesture of traffic police；
If detecting traffic lights in described image, determine that signal lamp instructs according to the image of traffic lights；
The path planning for determining that vehicle travels at crossing is instructed according to traffic police's instruction and/or signal lamp.
2. unmanned crossing paths planning method according to claim 1, which is characterized in that further include following steps:
The image of multiple crossing environment and multiple non-crossing environment is acquired as training set, training environment identification model is described
The input of Context awareness model is image, is exported as running environment type；
The running environment that vehicle front is judged according to described image, includes the following steps:
Described image is inputted into the Context awareness module, judges that the running environment type of output for crossing environment is also non-crossing
Environment.
3. unmanned crossing paths planning method according to claim 1, which is characterized in that further include following steps:
Image that multiple traffic police shoot in different angle is acquired as training set, training traffic police's identification model, the traffic police
The input of identification model is image, is exported whether to detect the result of traffic police；
It whether there is traffic police in the detection described image, include the following steps:
Described image is inputted into traffic police's identification model, whether traffic police is detected according to the output result judgement of model.
4. unmanned crossing paths planning method according to claim 1, which is characterized in that further include following steps:
Acquisition indicates that traffic police's gesture of each different instruction is used as training set, trained traffic police's gesture in the image of multiple and different angles
Identification model, the input of traffic police's gesture identification model are image, are exported as traffic police's instruction；
The gesture according to traffic police determines that traffic police instructs, and includes the following steps:
The image that the arm segment of traffic police is intercepted from described image, inputs traffic police's gesture identification mould for truncated picture
Type determines that traffic police instructs according to the output result of model.
5. unmanned crossing paths planning method according to claim 1, which is characterized in that described to be instructed according to traffic police
And/or signal lamp instructs the path planning for determining that vehicle travels at crossing, includes the following steps:
Current crossing operating condition is determined according to detecting that traffic police's instruction or signal lamp instruct in image；
Current crossing operating condition, the traffic police detected instruction and/or signal lamp instruction are inputted as Controlling model, are input to training
Good crossing path planning Controlling model obtains the vehicle control instruction that vehicle travels at crossing, the vehicle control instruction packet
Include at least one of steering wheel angle signal, throttle signal, brake pedal signal and the steering modulating signal of vehicle.
6. unmanned crossing paths planning method according to claim 5, which is characterized in that described to be examined according in image
It measures traffic police's instruction or signal lamp instruction determines current crossing operating condition, include the following steps:
If currently only detecting that traffic police instructs, current crossing operating condition is that traffic signal light fault traffic police commands operating condition；
If currently only detecting that signal lamp instructs, current crossing operating condition is traffic lights normally without traffic police's operating condition；
If being currently detected simultaneously by traffic police's instruction and signal lamp instruction, current crossing operating condition is that traffic lights normally have friendship
Alert operating condition.
7. unmanned crossing paths planning method according to claim 5, which is characterized in that described to be instructed according to traffic police
And/or signal lamp instructs the path planning for determining that vehicle travels at crossing, further includes following steps:
Obtain the measurement data of GPS positioning instrument of vehicle setting, the measurement data of Inertial Measurement Unit, laser radar measurement number
It is instructed as the input of Controlling model with current crossing operating condition, the traffic police detected according to the measurement data with millimetre-wave radar
And/or signal lamp instruction inputs trained crossing path planning Controlling model together.
8. unmanned crossing paths planning method according to claim 7, which is characterized in that the method also includes such as
Lower step:
Driver is acquired in the intersection data at each crossing, the intersection data includes that the crossing operating condition at corresponding crossing, traffic police refer to
It enables, signal lamp instruction, the measurement data of GPS positioning instrument of vehicle setting, the measurement data of Inertial Measurement Unit, laser radar
The measurement data of measurement data and millimetre-wave radar；
Driver is acquired in the driving data at each crossing, the driving data includes the steering wheel angle of the vehicle at corresponding crossing
Signal, throttle signal, brake pedal signal and steering modulating signal；
The intersection data of driver and driving data are matched according to crossing position and time, the training of Controlling model is added
The input of collection, training crossing path planning Controlling model, the crossing path planning Controlling model is intersection data, is exported to drive
Sail data.
9. unmanned crossing paths planning method according to claim 1, which is characterized in that described to be instructed according to traffic police
And/or signal lamp instructs the path planning for determining that vehicle travels at crossing, includes the following steps:
Judge whether to be detected simultaneously by traffic police's instruction and signal lamp instruction；
If only detecting that traffic police instructs, the path planning for determining that vehicle travels at crossing is instructed according to traffic police；
If only detecting that signal lamp instructs, the path planning for determining that vehicle travels at crossing is instructed according to signal lamp；
If being detected simultaneously by traffic police's instruction and signal lamp instruction, further judge whether traffic police's instruction and signal lamp instruction deposit
Consistent；
If there is path planning that is consistent, then being travelled according to the determining vehicle of consistent instruction at crossing；
If it is inconsistent, processing request is sent to cloud server, vehicle is determined according to the instruction that cloud server returns
In the path planning of crossing traveling.
10. unmanned crossing paths planning method according to claim 9, which is characterized in that the method also includes
Following steps:
The cloud server stores the position data at each crossing；
Vehicle Controller is by the current position of vehicle, the image that vehicle acquires and the traffic police detected instructs and/or signal lamp
Instruction is sent to the cloud server；
The cloud server determines the position model at vehicle front crossing according to the image that the current position of vehicle and vehicle acquire
It encloses, stores the director data that vehicle detection corresponding to the crossing arrives.
11. unmanned crossing paths planning method according to claim 10, which is characterized in that the processing request packet
Include the current position of vehicle, vehicle acquisition image, vehicle identification arrive traffic police instruction and signal lamp instruction；
It is described to request processing after being sent to cloud server, further include following steps:
After the cloud server receives the processing request, determined according to the image that the current position of vehicle and vehicle acquire
The position range at the crossing of vehicle front；
The cloud server judges that other vehicles for whether having quantity to be greater than preset threshold in present period upload crossing inspection
The traffic police's instruction measured；
If it is, the cloud server integrates traffic police's instruction that all vehicles upload in present period, according to ballot decision
Mechanism determines the instruction of the crossing present period；
The instruction of the crossing present period is back to the vehicle for sending processing request by the cloud server.
12. unmanned crossing paths planning method according to claim 11, which is characterized in that further include walking as follows
It is rapid:
The cloud server receives the traffic signal light condition Notification of Changes at each crossing, changes corresponding road according to Notification of Changes
The traffic signal light condition of mouth；
The cloud server receives the traffic police commander that traffic police reports and starts notice and position data, according to position data update pair
The traffic police at crossing is answered to command state；
After the cloud server judges whether have other vehicles to upload the director data that the crossing detects in present period,
Further include following steps:
If uploading traffic police's instruction that the crossing detects without other vehicles in present period, the cloud server judgement should
The corresponding traffic signal light condition in crossing；
If the corresponding traffic signal light condition in the crossing be failure, the cloud server by vehicle detection to traffic police refer to
The instruction as the crossing is enabled to be back to the vehicle for sending processing request；
If the corresponding traffic signal light condition in the crossing be it is normal, the cloud server judge crossing current time it
It is preceding whether receive the traffic police commander that traffic police reports and start to notify and do not receive the traffic police that traffic police reports command end notification, such as
Fruit is, then the cloud server by vehicle detection to traffic police's instruction be back to transmission processing as the instruction at the crossing and request
Vehicle.
13. unmanned crossing paths planning method according to claim 12, which is characterized in that further include walking as follows
It is rapid:
Obtain the programme path between the departure place and destination of vehicle driving；
Extract the position data at each crossing in programme path；
It is inquired according to the position data at each crossing in the cloud server, judges instruction of each crossing in present period
Type；
If instruction type of the crossing in present period be traffic police instruction, further judge the crossing traffic police instruction with
The driving direction at the crossing is with the presence or absence of conflict in programme path；
If there is conflict, then the Some routes for passing through the crossing in the programme path are changed to other optional routes.
14. a kind of unmanned crossing path planning system, which is characterized in that be applied to any one of claims 1 to 13 institute
The unmanned crossing paths planning method stated, the system comprises:
Image capture module, for acquiring the image of vehicle front；
Running environment judgment module, for judging the running environment of vehicle front according to described image；
Instruction detection module whether there is traffic lights and traffic police in the image for detecting crossing environment；If described
Traffic police is detected in image, determines that traffic police instructs according to the gesture of traffic police；If detecting traffic lights in described image,
Determine that signal lamp instructs according to the image of traffic lights；
Path planning module, for instructing the path planning for determining that vehicle travels at crossing according to traffic police's instruction and/or signal lamp.
15. a kind of unmanned crossing route design device characterized by comprising
Processor；
Memory, wherein being stored with the executable instruction of the processor；
Wherein, the processor is configured to come any one of perform claim requirement 1 to 13 institute via the execution executable instruction
The step of unmanned crossing paths planning method stated.
16. a kind of computer readable storage medium, for storing program, which is characterized in that described program is performed realization power
Benefit require any one of 1 to 13 described in unmanned crossing paths planning method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811417693.9A CN109389838A (en) | 2018-11-26 | 2018-11-26 | Unmanned crossing paths planning method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811417693.9A CN109389838A (en) | 2018-11-26 | 2018-11-26 | Unmanned crossing paths planning method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109389838A true CN109389838A (en) | 2019-02-26 |
Family
ID=65429826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811417693.9A Pending CN109389838A (en) | 2018-11-26 | 2018-11-26 | Unmanned crossing paths planning method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109389838A (en) |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109903576A (en) * | 2019-04-22 | 2019-06-18 | 爱驰汽车有限公司 | Vehicle lane change based reminding method, system, equipment and storage medium based on navigation |
| CN110347043A (en) * | 2019-07-15 | 2019-10-18 | 武汉天喻信息产业股份有限公司 | A kind of intelligent driving control method and device |
| CN110598563A (en) * | 2019-08-15 | 2019-12-20 | 北京致行慕远科技有限公司 | Method and device for processing travelling of movable equipment and storage medium |
| CN110658820A (en) * | 2019-10-10 | 2020-01-07 | 北京京东乾石科技有限公司 | Control method and device for unmanned vehicle, electronic device, and storage medium |
| CN110689747A (en) * | 2019-10-12 | 2020-01-14 | 北京百度网讯科技有限公司 | Control method and device of automatic driving vehicle and automatic driving vehicle |
| CN111047871A (en) * | 2019-11-19 | 2020-04-21 | 北京航空航天大学 | Man-machine driving hybrid traffic cooperative control system and method based on Internet of vehicles |
| CN111081045A (en) * | 2019-12-31 | 2020-04-28 | 智车优行科技（上海）有限公司 | Attitude trajectory prediction method and electronic equipment |
| CN111289003A (en) * | 2020-02-06 | 2020-06-16 | 广州小马智行科技有限公司 | Path planning method, apparatus, system, storage medium and processor |
| CN111599179A (en) * | 2020-05-21 | 2020-08-28 | 北京航空航天大学 | A motion planning method for autonomous driving at unsignaled intersections based on risk dynamic balance |
| CN111666906A (en) * | 2020-06-10 | 2020-09-15 | 上海商汤智能科技有限公司 | Prompt message generation method and device, electronic equipment and storage medium |
| CN111806357A (en) * | 2020-07-31 | 2020-10-23 | 北京小马慧行科技有限公司 | Signal collection method and collection device for traffic signal lights |
| CN111814657A (en) * | 2020-07-06 | 2020-10-23 | 南京工业大学 | A method, system and storage medium for unmanned vehicle parking based on image recognition |
| CN111824003A (en) * | 2019-04-23 | 2020-10-27 | 上海汽车集团股份有限公司 | A kind of control method and control system of vehicle lamp |
| CN111931726A (en) * | 2020-09-23 | 2020-11-13 | 北京百度网讯科技有限公司 | Traffic light detection method and device, computer storage medium and road side equipment |
| CN111985373A (en) * | 2020-08-12 | 2020-11-24 | 杭州鸿泉物联网技术股份有限公司 | Safety warning method, device and electronic device based on traffic intersection recognition |
| WO2020238699A1 (en) * | 2019-05-28 | 2020-12-03 | 深圳市商汤科技有限公司 | State detection method and device for signal indicator, driving control method and device |
| CN112208539A (en) * | 2019-07-09 | 2021-01-12 | 奥迪股份公司 | Systems, vehicles, methods and media for autonomous vehicles |
| CN112487869A (en) * | 2020-11-06 | 2021-03-12 | 深圳优地科技有限公司 | Robot intersection passing method and device and intelligent equipment |
| CN112765823A (en) * | 2021-01-26 | 2021-05-07 | 陈佳伟 | Remote desktop control system and method based on big data |
| CN112991799A (en) * | 2019-12-17 | 2021-06-18 | 现代自动车株式会社 | Vehicle autopilot system and method using V2X communication |
| CN113033464A (en) * | 2021-04-10 | 2021-06-25 | 阿波罗智联(北京)科技有限公司 | Signal lamp detection method, device, equipment and storage medium |
| CN113140120A (en) * | 2020-01-16 | 2021-07-20 | 华为技术有限公司 | Method and device for determining traffic indication information |
| CN113160547A (en) * | 2020-01-22 | 2021-07-23 | 华为技术有限公司 | Automatic driving method and related equipment |
| CN113192352A (en) * | 2021-06-03 | 2021-07-30 | 山东交通学院 | Automatic driving method and system for receiving instructions of traffic management personnel |
| CN113295181A (en) * | 2021-07-28 | 2021-08-24 | 国汽智控(北京)科技有限公司 | Vehicle path planning method, device and system |
| CN113514074A (en) * | 2021-07-09 | 2021-10-19 | 北京航空航天大学 | Intersection path planning method and device and storage medium |
| CN113954835A (en) * | 2020-07-15 | 2022-01-21 | 广州汽车集团股份有限公司 | A vehicle driving control method, system and computer-readable storage medium at intersection |
| CN114202942A (en) * | 2022-01-12 | 2022-03-18 | 北京京东乾石科技有限公司 | Traffic light related module control method and device |
| CN114283497A (en) * | 2021-12-27 | 2022-04-05 | 吉林大学 | A traffic police gesture recognition method in a congested intersection scene |
| US11422559B2 (en) | 2020-02-18 | 2022-08-23 | Wipro Limited | Method and system of navigating an autonomous vehicle at an intersection of roads |
| CN115334109A (en) * | 2022-08-08 | 2022-11-11 | 小米汽车科技有限公司 | System architecture, transmission method, vehicle, medium and chip for traffic signal identification |
| CN119516832A (en) * | 2025-01-20 | 2025-02-25 | 厦门理工学院 | Vehicle lane change command and control method, medium and device based on virtual traffic signal |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013207223A1 (en) * | 2013-04-22 | 2014-10-23 | Ford Global Technologies, Llc | Method for detecting non-motorized road users |
| CN104943684A (en) * | 2014-03-31 | 2015-09-30 | 比亚迪股份有限公司 | Pilotless automobile control system and automobile with same |
| CN107084733A (en) * | 2017-04-10 | 2017-08-22 | 广东数相智能科技有限公司 | A kind of method based on unpiloted path planning, apparatus and system |
| CN107490382A (en) * | 2017-07-31 | 2017-12-19 | 中北智杰科技（北京）有限公司 | A kind of pilotless automobile path planning system and control method |
| CN107813817A (en) * | 2016-08-25 | 2018-03-20 | 大连楼兰科技股份有限公司 | Unmanned driving system, unmanned driving method and vehicle |
| CN107813830A (en) * | 2016-08-31 | 2018-03-20 | 法乐第(北京)网络科技有限公司 | A kind of method and device for aiding in vehicle drive |
| CN107944624A (en) * | 2017-11-17 | 2018-04-20 | 南京大学 | A kind of unmanned vehicle crossing Driving Decision-making method based on Hidden Markov Model |
-
2018
- 2018-11-26 CN CN201811417693.9A patent/CN109389838A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013207223A1 (en) * | 2013-04-22 | 2014-10-23 | Ford Global Technologies, Llc | Method for detecting non-motorized road users |
| CN104943684A (en) * | 2014-03-31 | 2015-09-30 | 比亚迪股份有限公司 | Pilotless automobile control system and automobile with same |
| CN107813817A (en) * | 2016-08-25 | 2018-03-20 | 大连楼兰科技股份有限公司 | Unmanned driving system, unmanned driving method and vehicle |
| CN107813830A (en) * | 2016-08-31 | 2018-03-20 | 法乐第(北京)网络科技有限公司 | A kind of method and device for aiding in vehicle drive |
| CN107084733A (en) * | 2017-04-10 | 2017-08-22 | 广东数相智能科技有限公司 | A kind of method based on unpiloted path planning, apparatus and system |
| CN107490382A (en) * | 2017-07-31 | 2017-12-19 | 中北智杰科技（北京）有限公司 | A kind of pilotless automobile path planning system and control method |
| CN107944624A (en) * | 2017-11-17 | 2018-04-20 | 南京大学 | A kind of unmanned vehicle crossing Driving Decision-making method based on Hidden Markov Model |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109903576A (en) * | 2019-04-22 | 2019-06-18 | 爱驰汽车有限公司 | Vehicle lane change based reminding method, system, equipment and storage medium based on navigation |
| CN111824003A (en) * | 2019-04-23 | 2020-10-27 | 上海汽车集团股份有限公司 | A kind of control method and control system of vehicle lamp |
| WO2020238699A1 (en) * | 2019-05-28 | 2020-12-03 | 深圳市商汤科技有限公司 | State detection method and device for signal indicator, driving control method and device |
| CN112208539A (en) * | 2019-07-09 | 2021-01-12 | 奥迪股份公司 | Systems, vehicles, methods and media for autonomous vehicles |
| CN110347043B (en) * | 2019-07-15 | 2023-03-10 | 武汉天喻信息产业股份有限公司 | Intelligent driving control method and device |
| CN110347043A (en) * | 2019-07-15 | 2019-10-18 | 武汉天喻信息产业股份有限公司 | A kind of intelligent driving control method and device |
| CN110598563A (en) * | 2019-08-15 | 2019-12-20 | 北京致行慕远科技有限公司 | Method and device for processing travelling of movable equipment and storage medium |
| CN110658820A (en) * | 2019-10-10 | 2020-01-07 | 北京京东乾石科技有限公司 | Control method and device for unmanned vehicle, electronic device, and storage medium |
| CN110689747A (en) * | 2019-10-12 | 2020-01-14 | 北京百度网讯科技有限公司 | Control method and device of automatic driving vehicle and automatic driving vehicle |
| CN111047871B (en) * | 2019-11-19 | 2021-08-06 | 北京航空航天大学 | A human-machine driving hybrid traffic collaborative control system and method based on the Internet of Vehicles |
| CN111047871A (en) * | 2019-11-19 | 2020-04-21 | 北京航空航天大学 | Man-machine driving hybrid traffic cooperative control system and method based on Internet of vehicles |
| CN112991799A (en) * | 2019-12-17 | 2021-06-18 | 现代自动车株式会社 | Vehicle autopilot system and method using V2X communication |
| CN111081045A (en) * | 2019-12-31 | 2020-04-28 | 智车优行科技（上海）有限公司 | Attitude trajectory prediction method and electronic equipment |
| US12307889B2 (en) | 2020-01-16 | 2025-05-20 | Shenzhen Yinwang Intelligent Technologies Co., Ltd. | Traffic indication information determining method and apparatus |
| CN113140120A (en) * | 2020-01-16 | 2021-07-20 | 华为技术有限公司 | Method and device for determining traffic indication information |
| CN113160547B (en) * | 2020-01-22 | 2023-02-03 | 华为技术有限公司 | A kind of automatic driving method and related equipment |
| CN113160547A (en) * | 2020-01-22 | 2021-07-23 | 华为技术有限公司 | Automatic driving method and related equipment |
| CN111289003A (en) * | 2020-02-06 | 2020-06-16 | 广州小马智行科技有限公司 | Path planning method, apparatus, system, storage medium and processor |
| US11422559B2 (en) | 2020-02-18 | 2022-08-23 | Wipro Limited | Method and system of navigating an autonomous vehicle at an intersection of roads |
| CN111599179A (en) * | 2020-05-21 | 2020-08-28 | 北京航空航天大学 | A motion planning method for autonomous driving at unsignaled intersections based on risk dynamic balance |
| CN111666906A (en) * | 2020-06-10 | 2020-09-15 | 上海商汤智能科技有限公司 | Prompt message generation method and device, electronic equipment and storage medium |
| CN111814657A (en) * | 2020-07-06 | 2020-10-23 | 南京工业大学 | A method, system and storage medium for unmanned vehicle parking based on image recognition |
| CN113954835A (en) * | 2020-07-15 | 2022-01-21 | 广州汽车集团股份有限公司 | A vehicle driving control method, system and computer-readable storage medium at intersection |
| CN111806357A (en) * | 2020-07-31 | 2020-10-23 | 北京小马慧行科技有限公司 | Signal collection method and collection device for traffic signal lights |
| CN111985373A (en) * | 2020-08-12 | 2020-11-24 | 杭州鸿泉物联网技术股份有限公司 | Safety warning method, device and electronic device based on traffic intersection recognition |
| CN111931726A (en) * | 2020-09-23 | 2020-11-13 | 北京百度网讯科技有限公司 | Traffic light detection method and device, computer storage medium and road side equipment |
| CN111931726B (en) * | 2020-09-23 | 2024-06-11 | 阿波罗智联(北京)科技有限公司 | Traffic light detection method, device, computer storage medium and road side equipment |
| CN112487869B (en) * | 2020-11-06 | 2024-08-23 | 深圳优地科技有限公司 | Robot intersection passing method and device and intelligent equipment |
| CN112487869A (en) * | 2020-11-06 | 2021-03-12 | 深圳优地科技有限公司 | Robot intersection passing method and device and intelligent equipment |
| CN112765823B (en) * | 2021-01-26 | 2022-11-18 | 北京城建智控科技股份有限公司 | Remote desktop control system and method based on big data |
| CN112765823A (en) * | 2021-01-26 | 2021-05-07 | 陈佳伟 | Remote desktop control system and method based on big data |
| CN113033464B (en) * | 2021-04-10 | 2023-11-21 | 阿波罗智联(北京)科技有限公司 | Signal lamp detection method, device, equipment and storage medium |
| CN113033464A (en) * | 2021-04-10 | 2021-06-25 | 阿波罗智联(北京)科技有限公司 | Signal lamp detection method, device, equipment and storage medium |
| CN113192352A (en) * | 2021-06-03 | 2021-07-30 | 山东交通学院 | Automatic driving method and system for receiving instructions of traffic management personnel |
| CN113514074B (en) * | 2021-07-09 | 2023-11-17 | 北京航空航天大学 | Intersection path planning method, intersection path planning device and storage medium |
| CN113514074A (en) * | 2021-07-09 | 2021-10-19 | 北京航空航天大学 | Intersection path planning method and device and storage medium |
| CN113295181A (en) * | 2021-07-28 | 2021-08-24 | 国汽智控(北京)科技有限公司 | Vehicle path planning method, device and system |
| CN114283497A (en) * | 2021-12-27 | 2022-04-05 | 吉林大学 | A traffic police gesture recognition method in a congested intersection scene |
| CN114283497B (en) * | 2021-12-27 | 2025-04-15 | 吉林大学 | Traffic police gesture recognition method in congestion crossroad scene |
| CN114202942A (en) * | 2022-01-12 | 2022-03-18 | 北京京东乾石科技有限公司 | Traffic light related module control method and device |
| CN114202942B (en) * | 2022-01-12 | 2023-09-01 | 北京京东乾石科技有限公司 | Traffic light related module control method and device |
| CN115334109A (en) * | 2022-08-08 | 2022-11-11 | 小米汽车科技有限公司 | System architecture, transmission method, vehicle, medium and chip for traffic signal identification |
| CN115334109B (en) * | 2022-08-08 | 2025-01-21 | 小米汽车科技有限公司 | System architecture, transmission method, vehicle, medium and chip for traffic signal recognition |
| CN119516832A (en) * | 2025-01-20 | 2025-02-25 | 厦门理工学院 | Vehicle lane change command and control method, medium and device based on virtual traffic signal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389838A (en) | Unmanned crossing paths planning method, system, equipment and storage medium | |
| US11644319B2 (en) | Destination changes in autonomous vehicles | |
| JP7150846B2 (en) | Object interaction prediction system and method for autonomous vehicles | |
| US20210397185A1 (en) | Object Motion Prediction and Autonomous Vehicle Control | |
| CN109466543B (en) | Planning autonomous movement | |
| US11022974B2 (en) | Sensor-based object-detection optimization for autonomous vehicles | |
| US11507090B2 (en) | Systems and methods for vehicle motion control with interactive object annotation | |
| KR102470186B1 (en) | Intervention in operation of a vehicle having autonomous driving capabilities | |
| US20200134494A1 (en) | Systems and Methods for Generating Artificial Scenarios for an Autonomous Vehicle | |
| US20190101924A1 (en) | Anomaly Detection Systems and Methods for Autonomous Vehicles | |
| BR112019016268B1 (en) | METHOD FOR USE IN CROSSING A VEHICLE AND AUTONOMOUS VEHICLE TRANSPORTATION NETWORK | |
| CN110533900A (en) | Method, assistance system and motor vehicle for assisting driving of at least one motor vehicle | |
| CN109213134A (en) | The method and apparatus for generating automatic Pilot strategy | |
| CN108646752A (en) | The control method and device of automated driving system | |
| CN106541947A (en) | Vehicle active Ride Control System and control method and vehicle, intelligent vehicle machine | |
| US11755008B2 (en) | Using plays for human-AI decision-making in remote autonomous vehicle support | |
| JP7462837B2 (en) | Annotation and Mapping for Vehicle Operation in Low-Confidence Object Detection Conditions | |
| WO2024184918A1 (en) | Method and system for determining sub-path in a navigational path for a vehicle | |
| CN115659701B (en) | Verification method, device and storage medium for vehicle-road cooperative V2X application scene | |
| US11899446B2 (en) | Verifying authorized personnel for interaction with autonomous vehicles | |
| CN118339069A (en) | Autonomous vehicle maneuvers in response to hand signals in construction zones | |
| CN118354952A (en) | Gesture signal detection system using supervision | |
| CN119739805A (en) | Method, vehicle and cloud server for constructing waiting area roads in map | |
| CN119085678A (en) | Dynamic navigation method, electronic device and storage medium for roadblocks | |
| CN120141526A (en) | Vehicle navigation control method, vehicle and cloud server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200923 Address after: 201821 J871 room 6, 1288 Yecheng Road, Jiading District, Shanghai. Applicant after: AIWAYS AUTO (SHANGHAI) Co.,Ltd. Address before: 334000 Jiangxi Province, Shangrao city Shangrao Economic & Technological Development Zone West Park Avenue Applicant before: AIWAYS AUTOMOBILE (SHANGHAI) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190226 |
|
| RJ01 | Rejection of invention patent application after publication |