CN115953911A - Global automatic driving control system based on centralized calculation - Google Patents

Abstract

The invention relates to the technical field of automatic driving control, in particular to a global automatic driving control system based on centralized calculation. The area covered by the system is divided into a plurality of grids, and the system comprises a root server and a plurality of computing centers; each grid comprises at least one computing center; the root server is configured to receive a travel demand sent by a vehicle terminal and plan a global path according to the travel demand; dividing the global path into a plurality of subtasks according to the grids covered by the global path, and respectively sending the subtasks to the computing center of each grid; and the computing center is configured to plan a local path and control the vehicle terminal to run according to the local path to complete the distributed subtasks in the running process of the vehicle terminal in the grid where the computing center is located. The invention ensures the real-time performance of control information issuing and vehicle information feedback, and provides guarantee for the comprehensive popularization of the automatic driving vehicle.

Description

A global autonomous driving control system based on centralized computing

technical field

The invention belongs to the technical field of automatic driving control, and in particular relates to a global automatic driving control system based on centralized calculation.

Background technique

The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

The computing power of mobile processors has advanced by leaps and bounds in recent years, enabling the large-scale application of sensor technology and artificial intelligence in the field of advanced driver assistance. Today, almost all automakers' autonomous driving implementation paths are based on the three-step rule of "perception-decision-execution". In order to enhance product competitiveness, manufacturers are competing to stack expensive sensors such as lidar, vehicle-mounted MCU chips with computing power comparable to workstations, etc. The disadvantages of this model are not only a substantial increase in the cost of a single vehicle, but also repeated development costs and In addition to wasting resources, there are also technical limitations.

The popularity of cars with independent autonomous driving capabilities is not the optimal solution to various travel problems. With the continuous advancement of technology, the form of traffic participants will also undergo tremendous changes, gradually changing from a single vehicle driven by a human. Connected self-driving vehicles. With the continuous increase and even popularization of networked self-driving vehicles, it will bring huge pressure on network transmission and computing resources.

Contents of the invention

In order to overcome the above-mentioned deficiencies in the prior art, the present invention provides a global automatic driving control system based on centralized computing, which realizes the regional division of computing resources through a grid-based system architecture, and ensures that control information distribution and vehicle information The real-time nature of the feedback provides a guarantee for the comprehensive popularization of self-driving vehicles.

In order to achieve the above purpose, one or more embodiments of the present invention provide the following technical solutions:

A global autonomous driving control system based on centralized computing, the area covered by the system is divided into multiple grids, the system includes a root server and multiple computing centers; each grid includes at least one computing center; among them,

The root server is configured to receive the travel demand sent by the vehicle terminal, plan a global path according to the travel demand; divide the global path into multiple subtasks according to the grid covered by the global path, and send them to each grid respectively computing center;

The computing center is configured to plan a partial route when the vehicle terminal is traveling in the grid where the computing center is located, and control the vehicle terminal to travel along the partial route to complete assigned subtasks.

Further, the system further includes a plurality of computing center intermediate layers corresponding to the plurality of grids; each of the computing center intermediate layers is connected to one or more computing centers in the grid, and, Each of the middle layers of the computing center is connected to the root server.

Further, the system further includes a plurality of wireless communication base stations, each grid includes at least one wireless communication base station, and each wireless communication base station is connected to the middle layer of the computing center in the grid.

Further, the travel demand includes destination information; the root server planning a global path according to the travel demand includes:

Planning a global path according to the current location and destination information of the vehicle terminal to obtain multiple driving paths;

According to the current traffic conditions, the performance parameters of the vehicle terminal and the number of occupants, calculate the time consumption and energy consumption of the various driving routes, and send them to the vehicle terminal;

The selection of the driving route by the occupant is received and used for the division of subtasks.

Further, the planning of the local path by the computing center includes:

Obtain the global path, current location, and current driving state of all current vehicle terminals in the grid; segment the global path of these vehicles with the intersection position, the position where the vehicle enters and exits the grid as nodes;

Taking the current location of the target vehicle terminal to the next node as a calculation cycle, perform the following steps:

(1) According to the current location and current driving state of each vehicle terminal in the current calculation cycle, calculate the theoretical arrival time of these vehicle terminals to the next node, arrange the sequence of these vehicle terminals according to the theoretical arrival time, and update the time of these vehicle terminals theoretical arrival time;

(2) Obtain the position of the target vehicle terminal in real time, calculate the actuator input parameters of the vehicle terminal according to the theoretical arrival time, control the target vehicle terminal to arrive at the next node within the theoretical time, and update the current location of the target vehicle terminal;

Repeat steps (1)-(2) until the last node is reached.

Further, after the computing center completes the assigned subtask, it transfers the vehicle control right to the computing center of the grid where the next subtask is located. The handover process is as follows:

In a certain transition area where the vehicle terminal travels to the next grid, both the current computing center and the next computing center plan a local path for the vehicle terminal, and send actuator input parameters to the vehicle terminal;

When the vehicle terminal just enters the transition area, it still keeps executing the actuator input parameters issued by the calculation center of the current grid, and after driving the set distance, it gives priority to executing the actuator input parameters that arrive first;

The vehicle terminal monitors the message delays sent by the two computing centers, and when the packet loss rate and network delay from the next computing center are both less than or equal to the current computing center message, and remain within a period of time When stable, send feedback information to the current computing center, and the current computing center no longer controls the vehicle terminal.

One or more embodiments provide a root server for global autonomous driving control, where the control area is divided into multiple grids, each of which includes at least one computing center; the root server communicates with each The computing centers all maintain communication connections through the middle layer of the computing centers, and the root server is configured to perform the following steps:

Receive the travel demand sent by the vehicle terminal, and plan the global route according to the travel demand;

According to the grid covered by the global path, the global path is divided into a plurality of subtasks, which are respectively sent to the computing centers of each grid.

Further, the travel demand includes destination information; the root server planning a global path according to the travel demand includes:

Planning a global path according to the current location and destination information of the vehicle terminal to obtain multiple driving paths;

According to the current traffic conditions, the performance parameters of the vehicle terminal and the number of occupants, calculate the time consumption and energy consumption of the various driving routes, and send them to the vehicle terminal;

The selection of the driving route by the occupant is received and used for the division of subtasks.

Further, the root server also obtains the data request sent by the computing center when executing the subtask, and uses the global paths, current locations and current driving states of all current vehicle terminals in the grid where the computing center is located for the current subtask The corresponding vehicle terminal executes local path planning.

One or more embodiments provide a computing center communicatively connected to the root server, the computing center is configured to perform the following steps:

When the vehicle terminal is driving in the grid where the computing center is located, plan a partial route, and control the vehicle terminal to travel along the partial route to complete assigned subtasks.

Further, planning a local path includes:

Obtain the global path, current location, and current driving state of all current vehicle terminals in the grid; segment the global path of these vehicles with the intersection position, the position where the vehicle enters and exits the grid as nodes;

Taking the current location of the target vehicle terminal to the next node as a calculation cycle, perform the following steps:

(1) According to the current location and current driving state of each vehicle terminal in the current calculation cycle, calculate the theoretical arrival time of these vehicle terminals to the next node, arrange the sequence of these vehicle terminals according to the theoretical arrival time, and update the time of these vehicle terminals theoretical arrival time;

(2) Obtain the position of the target vehicle terminal in real time, calculate the actuator input parameters of the vehicle terminal according to the theoretical arrival time, control the target vehicle terminal to arrive at the next node within the theoretical time, and update the current location of the target vehicle terminal;

Repeat steps (1)-(2) until the last node is reached.

Further, after the computing center completes the assigned subtask, it transfers the control right of the vehicle to the computing center of the grid where the next subtask is located, and the handover process is as follows:

In a certain transition area where the vehicle terminal travels to the next grid, both the current computing center and the next computing center plan a local path for the vehicle terminal, and send actuator input parameters to the vehicle terminal;

When the vehicle terminal just enters the transition area, it still keeps executing the actuator input parameters issued by the calculation center of the current grid, and after driving the set distance, it gives priority to executing the actuator input parameters that arrive first;

The vehicle terminal monitors the message delays sent by the two computing centers, and when the packet loss rate and network delay from the next computing center are both less than or equal to the current computing center message, and remain within a period of time When stable, send feedback information to the current computing center, and the current computing center no longer controls the vehicle terminal.

The above one or more technical solutions have the following beneficial effects:

By dividing the global autonomous driving road into a geographic grid, setting up one or more computing centers in the grid, and setting up a centralized root server, the distributed computing power layout is realized, which ensures the distribution of control information and the control of vehicles. The real-time nature of information feedback provides a guarantee for the comprehensive popularization of autonomous vehicles.

By dividing the global path of the vehicle into subtasks, the computing centers in different grids perform local path optimization, which is beneficial to achieve the optimal scheduling of computing power and improve the efficiency of information transmission; in addition, each grid performs local During path planning, the path of the vehicle terminal in the grid is also segmented based on nodes, and the scheduling optimization of the vehicle terminals in each segment is carried out in turn to achieve a more refined path optimization.

At the same time, after the locally optimized path is obtained, the driving state of the vehicle is also monitored in real time, and real-time corrections are made according to the deviation from the theoretical driving state to ensure that it travels according to the planned path and the theoretical time to reach each node.

In order to overcome the problem of handover of vehicle controllers in computing centers in adjacent grids, this application also provides a strategy for handing over control rights. In the transition section, both computing centers in two adjacent grids perform analysis and send control parameters to To the vehicle, drive based on the control parameters of priority arrival, and completely hand over the control right when the data sent by a certain computing center is stable, so as to prevent signal interruption or delay when the vehicle terminal crosses the grid boundary.

Description of drawings

The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations to the present invention.

Fig. 1 is an architecture diagram of the global automatic driving control system based on centralized computing described in the embodiment of the present invention;

Fig. 2 is a functional framework diagram of a root server, a computing center and a vehicle terminal in an embodiment of the present invention.

Detailed ways

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

It should be noted that the terminology used here is only for describing specific embodiments, and is not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and/or combinations thereof.

In the case of no conflict, the embodiments and the features in the embodiments of the present invention can be combined with each other.

The purpose of this embodiment is to provide a global autonomous driving control system based on centralized computing, provided that only autonomous vehicles are the traffic participants in the environment where the system is built. In order to meet this premise, this embodiment sets a closed road, and no conventional road access is allowed on any node of the closed road, and physical barriers are set on the edge of the road to avoid any vehicle that is out of the control of the system from entering the road environment. Pedestrians are required to move within the designated area demarcated by road marking lines.

The self-driving car mentioned in this embodiment refers to a car that is controlled by the entire self-driving system network without the need for humans to take over. By uploading the vehicle status (vehicle speed, yaw angle, steering angle, acceleration, centimeter-level positioning coordinates, etc.) in real time, and receiving the takeover command from the computing center to complete the driving operation performed by the controller. Vehicles need to provide necessary controllers and sensors, such as ultrasonic probes, cameras, millimeter-wave radars, etc., to collect information about the environment, vehicles, and pedestrians. On the one hand, it provides real-world Perception data optimizes system decision-making; on the other hand, it can be used as a safety redundancy backup, and the vehicle can also be downgraded to the local limited automatic driving function in the worst case.

The system specifically includes: a root server and multiple computing centers, wherein the root server communicates with the multiple computing centers via the middle layer of the computing centers.

The area in which the system operates is divided into multiple sub-areas. For ease of operation, this embodiment divides the area into grids, and each grid is provided with a computing center intermediate layer, and each computing center intermediate layer is connected with All computing centers in the grid are connected, and the middle layer of each computing center is connected to the root server. In order to meet the real-time and reliability of vehicle-cloud communication, a wireless communication base station is deployed in the middle of the road (such as a street lamp). Layers are directly connected to reduce the communication delay between the self-driving car and the computing center. The deployment density of communication base stations is determined by communication standards and media, not limited to 5G, 6G or quantum communication. Communication speed and stability directly determine the upper limit of the overall performance of the system.

The root server is composed of a computer group with super large computing power, and is responsible for vehicle path planning, road data analysis, regional flow control, and abnormal event handling in the closed road environment of the entire region. Coordinate and dispatch traffic resources at the macro level, transfer and process traffic flow information across grid computing centers. High-precision map databases, vehicle databases and road infrastructure databases are also established on this server.

The computing center is essentially a cloud server unit. The automatic driving system operated by the computing center performs modeling and motion analysis on the vehicles in the area under its jurisdiction, and calculates the driving trajectories of all vehicles and the vehicle chassis in each time period when it reaches the target state. The input parameters of the actuator; on the other hand, the calculation results are synchronized to the root server of the autonomous driving network in real time through the middle layer, and the traffic flow control strategy of the root server is received and executed. The computing center also monitors and reports the operating status of base stations and roadside infrastructure.

In order to ensure information security, the computing center is a computing cluster isolated from the outside world. The computing center can only establish communication with other devices through the middle layer. The middle layer of the computing center does not participate in the computing process, and is responsible for monitoring the working status and scheduling of the computing center internally. The computing resources of each computing center in the grid are also used as the external interface of the grid computing center to communicate with the root server and computing centers of other grids.

The root servers are configured to include:

Basic data management module for managing map data and road infrastructure in the region;

The vehicle management module is used to manage the terminal information of the self-driving vehicle in the area and the corresponding occupant identity information, and is used for identity authentication when driving;

The driving authorization module is used to receive the identity authentication request sent by the occupant when starting the vehicle terminal, and perform authentication. If the authentication is passed, enter the global path planning module;

The global route planning module is used to receive the travel demand sent by the vehicle terminal, and plan the global route according to the travel demand. Specifically, the travel demand includes destination information; planning a global path according to the travel demand includes:

Planning a global path according to the current location and destination information of the vehicle terminal to obtain multiple driving paths;

According to the current traffic conditions, the performance parameters of the vehicle terminal and the number of occupants, calculate the time consumption and energy consumption of the various driving routes, and send them to the vehicle terminal;

The selection of the driving route by the occupant is received and used for the division of subtasks.

The subtask allocation module is used to divide the global path into a plurality of subtasks according to the grid covered by the global path, and send them to the middle layer of the computing center of each grid respectively, and then the middle layer of the computing center distributes them to the network where they are located. Grid computing center.

The subtask tracking module is used to track the actual completion of all subtasks, and evaluate the impact on the global plan according to the results and deviations of task completion, and request subtask reassignment when necessary.

The vehicle state management module is used to obtain information such as the current position, current driving state, and grid of all vehicle terminals, and the computing center currently controlling the vehicle; Computing the global path, current location and current driving state of all current vehicle terminals in the grid where the center is located is used to perform local path planning for the corresponding vehicle terminals of the current subtask.

The computing center is configured to include:

A local path planning module, used to plan a local path when the vehicle terminal is driving in the grid where the computing center is located; specifically includes:

Send a data request to the root server, and obtain the global path, current location, and current driving status of all current vehicle terminals in the grid from the root server; take the intersection location, the location where the vehicle enters and exits the grid as nodes, and The global path of these vehicles is segmented;

Taking the current location of the target vehicle terminal to the next node as a calculation cycle, perform the following steps:

(1) According to the current location and current driving state of each vehicle terminal in the current calculation cycle, calculate the theoretical arrival time of these vehicle terminals to the next node, arrange the sequence of these vehicle terminals according to the theoretical arrival time, and update the time of these vehicle terminals theoretical arrival time;

(2) Obtain the position of the target vehicle terminal in real time, calculate the actuator input parameters of the vehicle terminal according to the theoretical arrival time, control the target vehicle terminal to arrive at the next node within the theoretical time, and update the current location of the target vehicle terminal;

Repeat steps (1)-(2) until the last node is reached.

A vehicle travel control module, configured to control the vehicle terminal to travel along the partial route to complete assigned subtasks.

The vehicle control right handover module is used to hand over the vehicle control right to the computing center of the grid where the next subtask is located after the computing center completes the assigned subtask. The handover process is as follows:

In a certain transition area where the vehicle terminal travels to the next grid, both the current computing center and the next computing center plan a local path for the vehicle terminal, and send actuator input parameters to the vehicle terminal;

When the vehicle terminal just enters the transition area, it still keeps executing the actuator input parameters issued by the calculation center of the current grid, and after driving the set distance, it gives priority to executing the actuator input parameters that arrive first;

The vehicle terminal monitors the message delay sent by the two computing centers, and when the packet loss rate and network delay from the computing center of the next grid are both less than or equal to the message of the computing center of the current grid, And when it remains stable for a period of time, feedback information is sent to the current computing center, and the current computing center no longer controls the vehicle terminal.

a vehicle terminal configured to include:

The current state acquisition module is used to obtain its own current position and driving state in real time, and send them to the root server;

The control system login module is used to obtain the identity information of the occupant and send it to the root server;

The execution control module is used to obtain the actuator input parameters sent by the computing center, and control the driving of the vehicle terminal.

In addition, the system also has a handling strategy for emergencies:

(1) Lost communication with the base station

If the vehicle is not started and the attempt to reconnect fails, exit the autopilot network;

If the vehicle is already started and the attempt to reconnect fails, it will downgrade from automatic driving to limited automatic driving. The vehicle's external sensors will perceive the environment, calculate the driving path locally, and automatically drive into the temporary lane to wait for rescue.

(2) The current computing center response timeout

The middle layer allocates other computing center resources in the region;

If there are no computing resources available in the grid, other computing centers in the grid will provide resources;

When all computing centers have no available resources, the root server takes over.

(3) The middle layer is down

Enable the backup middle layer;

The base station cannot establish communication with the middle layer of the grid where it is located, and the root server takes over the entire grid where it is located.

(4) The vehicle is in danger of collision

When the hazards perceived by the sensors outside the vehicle must be avoided, the locally calculated hazard avoidance strategies are given priority, including but not limited to: automatic emergency braking, automatic emergency steering, emergency lane keeping, automatic lane change, and emergency driving. Driveway awaits rescue.

Upload the results of the vehicle's autonomous risk avoidance measures to the computing center;

The computing center re-plans the node target and arrival time, and updates the order;

After the danger is cleared, the vehicle resumes remote takeover of the autonomous driving network.

The control method executed by the above-mentioned automatic driving control system includes the following steps:

Automatic driving vehicle login step: when the automatic driving vehicle is activated in the parking space, obtain the identity information of the occupant and send it to the root server, the root server authenticates the identity information, and after the authentication is passed, the automatic driving vehicle logs in to the automatic driving Control System.

Among them, logging into the automatic driving control system specifically includes:

(1) The vehicle is unlocked and powered on;

(2) The owner's biometric authentication;

(3) Vehicle self-inspection, diagnosing the status of all controllers, recording the diagnosis results, and uploading the detection data to the root server database;

(4) The root server checks the data uploaded by the vehicle for faults. If there is no problem, the login is allowed. If there is a low-risk fault, it is allowed to log in conditionally. If there is a serious fault, it is not allowed to log in.

After the vehicle self-inspection is successful, log in to the automatic driving network, obtain driving authorization and enter the remote takeover mode.

Travel request acquisition step: After logging into the automatic driving network, the self-driving vehicle obtains the travel request input by the occupant and sends it to the root server. The travel request includes destination information, and more specifically, the final parking area.

Global path planning step: the root server performs global path planning according to the current location and destination information, and decomposes the global path into multiple subtasks according to the grid covered by the global path, and divides the multiple subtasks They are respectively sent to the middle layer of the computing center corresponding to the grid.

Among them, the root server's global path planning includes:

(1) The root server receives the travel request from the vehicle terminal;

(2) Carry out global path planning according to the current location and destination information, and obtain various driving paths;

(3) Calculate the time-consuming and energy consumption of each driving route according to the current traffic flow situation, vehicle performance parameters, and the number of passengers, and send it to the vehicle terminal for display;

(4) receiving the occupant's selection of the driving path, dividing the driving path into a plurality of subtasks according to the grids covered by it, each subtask corresponding to a grid;

(5) sending the plurality of subtasks to the middle layer of the computing center corresponding to the grid;

(6) After the middle layer of the computing center receives the subtask, it sends it to one of the computing centers connected to it.

After the root server obtains the travel request, it also sends an inquiry message to the vehicle terminal. The inquiry information includes whether there is a need for halfway parking. Information for global path planning.

Local area driving control step: the root server assigns the vehicle control right to the computing center of the grid where the current position of the target vehicle terminal is located, and the computing center brings the vehicle driving data into the entire traffic flow model. Carry out local path planning in the grid, and calculate in real time the actuator input parameters that reach the vehicle's target driving state, control the target vehicle terminal to complete the subtasks in the current grid; assign the vehicle control right to the computing center that executes the next subtask .

The computing center is configured to perform the following steps:

(1) Obtain the global path, current location information and current driving status information of all current vehicle terminals in the grid;

(2) Segment the global paths of these vehicle terminals, for example, take the intersection position, the position where the vehicle enters and exits the grid as segmentation nodes;

(3) Taking the current location of the target vehicle terminal to the next node as a calculation period, according to the current position and current driving state of each vehicle terminal in the current calculation period, calculate the theoretical arrival time of these vehicle terminals to the next node;

(4) According to the driving direction of these vehicle terminals at the next node (going straight, turning left or turning right), group these vehicle terminals, and for each group of vehicle terminals, arrange them in order according to the theoretical arrival time; update the theoretical arrival of the vehicle terminals Time, and synchronized to the root server;

(5) Obtain the position of the target vehicle terminal in real time, calculate the input parameters of the actuator of the vehicle terminal according to the theoretical arrival time, and ensure that the vehicle arrives at the next node within the theoretical time; during the driving process, the input parameters of the target vehicle terminal actuator are sent to The calculation center feeds back the offset from the target state. According to the offset, the calculation center brings the vehicle data into the model for recalculation, and continuously corrects the actuator parameters until it reaches the next node.

Among them, the vehicle terminal combines GNSS, IMU dead reckoning, wheel encoder, etc. to obtain its own real-time position and feed it back to the computing center.

(6) Steps (3)-(5) are repeatedly executed until the last node is reached, that is, the position where the vehicle leaves the current grid, and the subtask of the target vehicle terminal in the current grid is completed.

If there is a subtask change (the occupant changes the destination) or a new subtask is added (there is a new vehicle driving in the current grid), re-execute the sorting.

(7) The computing center assigns the control right of the vehicle to the computing center of the grid where the next subtask is located, and repeats steps (1)-(6) until all subtasks are completed.

Wherein, the computing center in the step (7) distributes the vehicle control right to the computing center of the grid where the next subtask is located as follows:

(7-1) In a certain transition area where the vehicle terminal travels to the next grid, both the current computing center and the next computing center plan a local path for the vehicle terminal, and send actuator input parameters to the vehicle terminal. Specifically, when driving into the transition section, the two adjacent base stations both receive the data packets transmitted by the vehicle, send them to the middle layer of their respective grid computing centers, and then send them to the computing center; both computing centers are based on the next grid The vehicle flow and the real-time information of the target vehicle terminal, calculate the control parameters, and send the control parameters and request takeover instruction to the vehicle terminal.

The vehicle information is received through the base station, which ensures the real-time performance of data transmission.

(7-2) The vehicle terminal receives the calculation results and takeover instructions sent by the two computing centers, and when it just enters the transition area, it still keeps executing the calculation results and takeover instructions sent by the computing center of the current grid, and travels for a certain distance After that, the actuator input parameters that arrive first are executed first.

(7-3) The vehicle terminal monitors the message delay sent by the two computing centers, when the packet loss rate and network delay from the next grid computing center are less than or equal to the current grid When the message from the computing center remains stable for a period of time, feedback information is sent to the current computing center, and the current computing center no longer controls the vehicle terminal, and the handover ends.

After the handover period, the vehicle is taken over by a computing center in the new grid. The computing center executes the subtasks assigned by the root server, repeats the above process, and finally reaches the destination, the vehicle enters the parking space, and the automatic driving process ends.

If the final parking area is not obtained in the above-mentioned travel request obtaining step, for example, if the occupant does not have a fixed parking space, after obtaining the travel request, an inquiry message is sent to the vehicle terminal, and the inquiry information includes whether there is a parking location preference. After the global path planning, for each driving path, multiple recommended parking spaces are also calculated according to the expected arrival time and parking location preference. The time consumption, energy consumption and recommended parking space of each driving route are sent to the vehicle terminal. During the execution of the local driving control step, by continuously correcting the expected arrival time, the target parking space is gradually locked from the plurality of recommended parking spaces, and finally the vehicle terminal is controlled to enter the target parking space. It should be noted here that if there are multiple vehicle terminals locking the same target parking space, the root server estimates the arrival time of the multiple vehicle terminals, sorts them, and assigns the parking space to the first arrival first.

Although the specific implementation of the present invention has been described above in conjunction with the accompanying drawings, it does not limit the protection scope of the present invention. Those skilled in the art should understand that on the basis of the technical solution of the present invention, those skilled in the art do not need to pay creative work Various modifications or variations that can be made are still within the protection scope of the present invention.

Claims (12)

1. A global automatic driving control system based on centralized computation is characterized in that the area covered by the system is divided into a plurality of grids, and the system comprises a root server and a plurality of computation centers; each grid comprises at least one computing center; wherein,

the root server is configured to receive a travel demand sent by a vehicle terminal and plan a global path according to the travel demand; dividing the global path into a plurality of subtasks according to the grids covered by the global path, and respectively sending the subtasks to the computing center of each grid;

and the computing center is configured to plan a local path and control the vehicle terminal to run according to the local path to complete the distributed subtasks in the running process of the vehicle terminal in the grid where the computing center is located.

2. The centralized computing-based global automatic driving control system according to claim 1, further comprising a plurality of computing center intermediate layers in one-to-one correspondence with the plurality of grids; each computing center intermediate layer is connected with one or more computing centers in the grid, and each computing center intermediate layer is connected to the root server.

3. The centralized-computing-based global automatic driving control system according to claim 1 or 2, further comprising a plurality of wireless communication base stations, wherein each grid comprises at least one wireless communication base station, and each wireless communication base station is connected with a computing center middle layer in the grid.

4. The centralized computing-based global automatic driving control system according to claim 1 or 2, wherein the travel demand includes destination information; the root server planning a global path according to the travel demand includes:

planning a global path according to the current position and destination information of the vehicle terminal to obtain various driving paths;

calculating the consumed time and energy of the multiple driving paths according to the current traffic condition, the performance parameters of the vehicle terminal and the number of passengers, and sending the consumed time and energy to the vehicle terminal;

and receiving the selection of the driving path by the passenger for dividing the subtasks.

5. The centralized-computing-based global autopilot control system of claim 4 wherein the computing center planning the local path comprises:

acquiring global paths, current positions and current driving states of all current vehicle terminals in a grid; taking the positions of the intersections and the positions of the vehicles entering and exiting the grids as nodes, and segmenting global paths of the vehicles;

taking the current position of the target vehicle terminal to the next node as a calculation cycle, executing the following steps:

(1) Calculating theoretical arrival time of the vehicle terminals reaching the next node according to the current position and the current driving state of each vehicle terminal in the current calculation period, sequencing the vehicle terminals according to the theoretical arrival time, and updating the theoretical arrival time of the vehicle terminals;

(2) Acquiring the position of a target vehicle terminal in real time, calculating actuator input parameters of the vehicle terminal according to theoretical arrival time, controlling the target vehicle terminal to arrive at the next node within the theoretical time, and updating the current position of the target vehicle terminal;

and (3) repeatedly executing the steps (1) to (2) until the last node is reached.

6. The global automatic driving control system based on centralized computation of claim 3, wherein after the computation center completes the assigned subtasks, the computation center hands over the vehicle control right to the grid where the next subtask is located, and the hand-over process is as follows:

in a certain transition area where a vehicle terminal drives to a next grid, a current calculation center and a next calculation center plan local paths for the vehicle terminal, and send actuator input parameters to the vehicle terminal;

the vehicle terminal still keeps executing the actuator input parameters issued by the calculation center of the current grid when just entering the transition area, and preferentially executes the actuator input parameters which arrive first after the vehicle terminal runs for a set distance;

the vehicle terminal monitors the message delay sent by the two computing centers, when the packet loss rate and the network delay from the next computing center are both less than or equal to the current computing center message and are kept stable within a period of time, the vehicle terminal sends feedback information to the current computing center, and the current computing center does not control the vehicle terminal any more.

7. A root server for global automatic driving control is characterized in that a control area is divided into a plurality of grids, and each grid comprises at least one computing center; the root server is in communication connection with each computing center through a computing center middle layer, and the root server is configured to execute the following steps:

the method comprises the steps of receiving a travel demand sent by a vehicle terminal, and planning a global path according to the travel demand;

and dividing the global path into a plurality of subtasks according to the grids covered by the global path, and respectively sending the subtasks to the computing center of each grid.

8. The root server of claim 7, wherein the travel demand comprises destination information; the root server planning a global path according to the travel demand includes:

planning a global path according to the current position of the vehicle terminal and the destination information to obtain various driving paths;

calculating the consumed time and energy of the multiple driving paths according to the current traffic condition, the performance parameters of the vehicle terminal and the number of passengers, and sending the consumed time and energy to the vehicle terminal;

and receiving the selection of the driving path by the passenger for dividing the subtasks.

9. The root server according to claim 7, wherein the root server further obtains a data request sent by the computing center when executing the subtask, and uses the global path, the current position, and the current driving state of all current vehicle terminals in the grid where the computing center is located, to execute local path planning on the vehicle terminal corresponding to the current subtask.

10. A computing center communicatively connected to the root server of any one of claims 7-9, wherein the computing center is configured to perform the steps of:

and when the vehicle terminal runs in the grid where the computing center is positioned, planning a local path, and controlling the vehicle terminal to run according to the local path to complete the distributed subtasks.

11. The computing center of claim 9, wherein planning a local path comprises:

acquiring global paths, current positions and current driving states of all current vehicle terminals in a grid; taking the positions of the intersections and the positions of the vehicles entering and exiting the grids as nodes, and segmenting global paths of the vehicles;

taking the current position of the target vehicle terminal to the next node as a calculation period, executing the following steps:

(1) Calculating theoretical arrival time of the vehicle terminals reaching the next node according to the current position and the current driving state of each vehicle terminal in the current calculation period, sequencing the vehicle terminals according to the theoretical arrival time, and updating the theoretical arrival time of the vehicle terminals;

(2) Acquiring the position of a target vehicle terminal in real time, calculating an actuator input parameter of the vehicle terminal according to theoretical arrival time, controlling the target vehicle terminal to arrive at the next node within the theoretical time, and updating the current position of the target vehicle terminal;

and (3) repeatedly executing the steps (1) to (2) until the last node is reached.

12. The computing center according to claim 9, wherein after the computing center completes the assigned subtasks, the computing center hands over the vehicle control right to the computing center of the grid where the next subtask is located, and the hand-over process is as follows:

in a certain transition region where a vehicle terminal drives to a next grid, a current calculation center and a next calculation center plan a local path for the vehicle terminal, and send actuator input parameters to the vehicle terminal;

the vehicle terminal still keeps executing the actuator input parameters issued by the calculation center of the current grid when just entering the transition area, and preferentially executes the actuator input parameters which arrive first after the vehicle terminal runs for a set distance;

the vehicle terminal monitors the message delay sent by the two computing centers, when the packet loss rate and the network delay from the next computing center are both less than or equal to the current computing center message and are kept stable within a period of time, the vehicle terminal sends feedback information to the current computing center, and the current computing center does not control the vehicle terminal any more.

Images