WO2018141285A1

WO2018141285A1 - Robot-assisted learning for wireless coverage and interference maps

Info

Publication number: WO2018141285A1
Application number: PCT/CN2018/075257
Authority: WO
Inventors: Kin Nang Lau; Ho Man LEE; Liyao Zhao
Original assignee: The Hong Kong University Of Science And Technology
Priority date: 2017-02-06
Filing date: 2018-02-05
Publication date: 2018-08-09

Abstract

Robot-assisted learning for wireless coverage and interference maps is described herein. A method as described herein includes updating, by a device operatively coupled to a processor, a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model; and determining, by the device, a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.

Description

ROBOT-ASSISTED LEARNING FOR WIRELESS COVERAGE AND INTERFERENCE MAPS

CROSS-REFERENCE TO RELATED APPLICATIONS

The present application claims the benefit of priority to U.S. Provisional Patent Application No. 62/499,733, filed February 6, 2017, and entitled “Robot-Assisted Learning of Wireless Coverage and Interference Map, ” the entirety of which application is incorporated herein by reference.

TECHNICAL FIELD

The present disclosure relates to wireless communication networks, and more particularly, to techniques for modeling wireless network coverage.

BACKGROUND

In the course of establishing and/or maintaining a wireless communication network, e.g., a Wi-Fi or LTE (Long Term Evolution) system, the ability to characterize wireless coverage quality throughout the network can be highly useful for operators and/or vendors associated with the system. For instance, an operator can utilize coverage quality information for an indoor wireless network to determine how many access points to install in the network, where to install respective access points, what transmit power levels to use for respective access points, or the like. Similarly, a network operator can utilize network interference information to detect unknown interference sources, which can be useful in the detection and removal of illegal transmitting stations, among other uses.

The above-described background relating to characterization of wireless coverage quality is merely intended to provide a contextual overview of some current issues, and is not intended to be exhaustive. Other contextual information may become further apparent upon review of the following detailed description.

SUMMARY

The following summary is a general overview of various embodiments disclosed herein and is not intended to be exhaustive or limiting upon the disclosed embodiments. Embodiments are better understood upon consideration of the detailed description below in conjunction with the accompanying drawings and claims.

Disclosed herein is an innovative robot-assisted platform that can perform both wireless propagation model estimation and interference source detection. The platform, in various aspects, can operate via a single robot or multi-robot coordination. In multi-robot mode, various embodiments described herein provide algorithms for a centralized mode and a decentralized mode. In an aspect, a propagation model parameter estimation module can be used to recursively update parameters of a propagation model and compute a confidence level for respective updates. Additionally, a measurement driven path planning model as described herein can be used to determine locations for subsequent measurement based on the computed confidence level. By using the robot-assisted platform as described herein, users can be freed from labor-intensive wireless coverage measurement tasks and achieve more accurate model estimation in less time as compared to conventional techniques.

In one embodiment, a system is described herein. The system includes a memory that stores computer executable components and a processor that executes computer executable components stored in the memory. The computer executable components include a parameter estimation component that updates a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model, and a path planning component that determines a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.

In another embodiment, a computer-implemented method is described herein. The computer-implemented method includes updating, by a device operatively coupled to a processor, a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model, and determining, by the device, a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.

In a further embodiment, a non-transitory machine readable medium is described herein. The non-transitory machine readable medium includes executable instructions that, when executed by a processor, facilitate performance of operations that include updating a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model, and computing a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.

DESCRIPTION OF DRAWINGS

Various non-limiting embodiments of the subject disclosure are described with reference to the following figures, wherein like reference numerals refer to like parts throughout unless otherwise specified.

FIG. 1 is a block diagram of a system that facilitates robot-assisted learning for wireless coverage and interference maps in accordance with various aspects described herein.

FIG. 2 is a diagram illustrating example operating modes that can be employed by a robot-assisted wireless coverage modeling platform in accordance with various aspects described herein.

FIGS. 3-5 are block diagrams illustrating respective aspects of a robot-assisted wireless coverage modeling platform in accordance with various aspects described herein.

FIG. 6 is a diagram illustrating an example propagation model parameter estimation module that can be utilized in accordance with various aspects described herein.

FIG. 7 is a diagram illustrating an example measurement driven path planning module that can be utilized in accordance with various aspects described herein.

FIG. 8 is a diagram illustrating an example simultaneous location and mapping (SLAM) module that can be utilized in accordance with various aspects described herein.

FIG. 9 is a diagram illustrating an example SLAM fusion module that can be utilized in accordance with various aspects described herein.

FIG. 10 is a block diagram of an example measurement system that can be utilized in accordance with various aspects described herein.

FIG. 11 is a block diagram of a system that facilitates single-robot assisted learning for wireless coverage and interference maps in accordance with various aspects described herein.

FIG. 12 is a block diagram of an example single-robot architecture that can be utilized in accordance with various aspects described herein.

FIG. 13 is a flow diagram of an initialization procedure for robot-assisted learning for wireless coverage and interference maps in accordance with various aspects described herein.

FIG. 14 is a flow diagram of a process for maintaining a wireless signal propagation model via a single robot agent in accordance with various aspects described herein.

FIG. 15 is a block diagram of a system that facilitates multi-robot assisted learning for wireless coverage and interference maps in accordance with various aspects described herein.

FIG. 16 is a block diagram of an example centralized multi-robot architecture that can be utilized in accordance with various aspects described herein.

FIG. 17 is a flow diagram of a process for maintaining a wireless signal propagation model via a centralized network of robot agents in accordance with various aspects described herein.

FIG. 18 is a block diagram of an example decentralized multi-robot architecture that can be utilized in accordance with various aspects described herein.

FIG. 19 is a flow diagram of a process for maintaining a wireless signal propagation model via a decentralized network of robot agents in accordance with various aspects described herein.

FIG. 20 is a flow diagram of a process that facilitates multi-robot assisted learning for wireless coverage and interference maps in accordance with various aspects described herein.

FIG. 21 is a diagram of an example computing environment in which various embodiments described herein can function.

DETAILED DESCRIPTION

Various specific details of the disclosed embodiments are provided in the description below. One skilled in the art will recognize, however, that the techniques described herein can in some cases be practiced without one or more of the specific details, or with other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring certain aspects. Additionally, it should be appreciated that elements in the drawings provided herein are not necessarily drawn to scale, and that some areas or elements may be expanded to help improve understanding of various embodiments described herein.

Wireless coverage planning and interference source detection are useful tasks in the development and/or maintenance of a wireless communication network. For instance, it can be desirable for an operator and/or vendor associated with a wireless network to characterize wireless coverage quality throughout the network in order to determine how many access points to install, where to install such access points, what transmit power to employ in indoor environments such as a campus, shopping mall or enterprise office, or the like. Additionally, it can be desirable for an operator of an outdoor wireless network to detect unknown interference sources in order to locate and/or remove illegal transmitting stations, among other purposes. Conventionally, however, wireless coverage planning and interference source detection are tedious and labor-intensive tasks. For example, generating wireless coverage planning information for indoor use and detecting unknown interference sources in an outdoor environment both generally involve a significant amount of human labor and/or effort associated with performing these tasks on site and working against complicated indoor environments and/or large-scale outdoor environments.

One existing technique for wireless coverage characterization involves the use of indoor coverage planning tools to simulate wireless coverage in a target indoor environment via ray tracing models and/or other simulation methods. However, these tools require large amounts of input data, such as floor plan dimensions, construction material parameters, locations of windows, partitions, and/or furniture, etc., to be entered manually, and errors in this data entry can adversely impact the quality of the simulated coverage. Another existing technique involves the use of real-time channel measurement to verify coverage in a target service area. This technique, however, is similarly tedious and labor-intensive as it conventionally requires multiple teams of human users with signal collection devices to travel to various locations around an unknown source and record signal strength data for triangulation. Moreover, as measurements performed by different human teams are often difficult to precisely synchronize, relatively large errors in estimating the position of an illegal signal source can result.

In view of at least the above, it is desirable to implement techniques to facilitate wireless network coverage and interference determinations in both indoor and outdoor environments, and various embodiments described herein can provide a universal platform capable of both propagation modeling and interference source detection for both indoor and outdoor environments. Additionally, various embodiments described herein facilitate the entry and/or collection of information in an automated manner, thereby reducing inaccuracy associated with errors in data entry, synchronization, etc., as noted above.

With reference now to the drawings, FIG. 1 is a block diagram of a system 100 that facilitates robot-assisted learning for wireless coverage and interference maps in accordance with various aspects described herein. The system 100 includes a parameter estimation component 110 that updates a signal propagation model for an area associated with a robot agent 102 based on a location of the robot agent 102 and a first signal strength measurement performed by the robot agent 102 and reported to the parameter estimation component 110. The system 100 further includes a path planning component 120 that computes a location of a second, subsequent signal strength measurement to be performed by the robot agent 102 based on the updated signal propagation model generated by the parameter estimation component 110 and a confidence level associated with the updated signal propagation model as computed by the parameter estimation component 110. Various aspects of the operation of the parameter estimation component 110 and the path planning component 120 are described in further detail below.

In an aspect, the robot agent (s) shown in the system 100 include one or more robots (e.g., flying drones, land robots, etc. ) that can have heterogeneous capabilities in terms of range, responsiveness, battery life, speed, and/or other characteristics. Further, the robot agent (s) shown in the system 100 can be equipped to perform simultaneous location and mapping (SLAM) sensor measurements and/or other measurements as appropriate. Further aspects of the robot agent (s) are described in more detail below.

As described above, various embodiments provided herein can operate as a versatile robot-assisted wireless coverage measurement platform that can be employed for a variety of tasks. Diagram 200 in FIG. 2 illustrates respective operating modes that can be utilized by a robot-assisted platform in accordance with various aspects herein. As shown by diagram 200, the platform can provide both wireless signal propagation model estimation and interference wireless signal source detection. As further shown by diagram 200, both of these functions can be utilized in indoor or outdoor use cases. When performing a specific function, diagram 200 further shows that a user can be given an option to select between a single-robot mode and a multi-robot mode. In the multi-robot mode, the user can further select between centralized and decentralized algorithms. In an aspect, the centralized mode focuses on global optimization of model accuracy while the decentralized mode focuses on estimation efficiency.

In an aspect, a robot-assisted wireless coverage measurement platform as described herein can operate to perform various tasks. A non-exhaustive list of such tasks or functions is as follows:

A) Indoor/Outdoor single robot propagation model estimation

B) Indoor/Outdoor centralized multi-robot propagation model estimation

C) Indoor/Outdoor decentralized multi-robot propagation model estimation

D) Indoor/Outdoor single robot interference source detection

E) Indoor/Outdoor centralized multi-robot interference source detection.

F) Indoor/Outdoor decentralized multi-robot interference source detection

Other tasks or functions are also possible. Respective ones of the functions listed above, and/or other functions, are described in further detail below.

With reference next to FIGS. 3-5, respective operating modes that can be employed by various embodiments described herein are provided. It should be appreciated, however that the operating modes shown in FIGS. 3-5 are merely examples of operating modes that can be used and that other modes are also possible. Referring first to FIG. 3, diagram 300 illustrates an example centralized operating mode that can be utilized by a single robot agent 102 or multiple robot agents 102 configured to operate in the centralized mode. As shown by diagram 300, respective robot agents 102 can communicate with a cloud server 310 through a communication interface, e.g., a Wi-Fi or other wireless communication connection facilitated by a communication module 320.

As further shown by diagram 300, respective robot agents 102 can utilize a SLAM module 332 and a measurement module 334. In an aspect, the SLAM module 332 can perform mapping and localization for an associated robot agent 102, and the measurement module 334 can be utilized by an associated robot agent 102 to collect signal strength data (e.g., Received Signal Strength Index or RSSI) . In an aspect, the measurement module 334 can be operable to capture instantaneous channel fading and/or RSSI from respective wireless access points, e.g., via multi-channel or multi-radio capability. Operation of the SLAM module 332 and the measurement module 334 are described in further detail below with regard to FIGS. 8 and 11, respectively.

As additionally shown by diagram 300, the cloud server 310 can utilize a SLAM fusion module 312, a (propagation model parameter) estimation module 314, and a (measurement-driven) path planning module 316. In an aspect, the SLAM fusion module 312 can integrate local maps received from respective robot agents 102 into a global map and transform respective local coordinates provided by the robot agents 102 into corresponding global coordinates. Operation of the SLAM fusion module is described in further detail below with respect to FIG. 9. In another aspect, the estimation module 314 can recursively estimate the parameters of a given propagation model, and the path planning module 316 can guide the navigation of the robot agents 102 based on the localization results from the SLAM fusion module 312 and/or the estimation results from the estimation module 314. For instance, the path planning module 316 can provide directions to respective robot agents 102 regarding their next destinations for data measurement. Operation of the estimation module 314 and the path planning module 316 are described in further detail below with respect to FIGS. 6-7.

In the centralized mode shown by FIG. 3, the robot agents 102 can submit measurement reports (e.g., value + reliability, location + reliability, timestamps, etc. ) to a centralized controller at the cloud server 310 via a wireless connection to the cloud server 310. Here, the estimation module 314 and the path planning module 316 for the robot agents 102 reside in the cloud and can compute desired destinations and/or paths for each robot agent 102 and communicate these destinations to the local controllers of the respective robot agents 102. The local controllers (not shown) of the respective robot agents 102 can then compute controlling commands (e.g., translational and/or rotational control) to actuators (e.g., wheels, propellers, etc. ) .

In contrast to the centralized mode shown by diagram 300, diagram 400 in FIG. 4 illustrates a decentralized mode that can be utilized by multiple robot agents 102 in the absence of a cloud server 310. As shown by diagram 400, respective robot agents 102 operating in a decentralized mode include a SLAM module 332 and a measurement module 334 as described above with respect to diagram 300. Additionally, the respective robot agents 102 are include computational modules, such as an estimation module 314 and a path planning module 316, that are similar to those described above with respect to the cloud server 310. In an aspect, the robot agents 102 operating in a decentralized mode can share data collection and computation results by communicating with each other in substantially real-time via their respective communication modules 320.

In the decentralized mode shown by FIG. 4, respective robot agents 102 can broadcast measurement reports (e.g., measurements + reliability, time, location, etc. ) to their neighbors using local wireless connections in an ad hoc mode. Here, the estimation module 314 and path planning module 316 can reside in each robot agent 102 locally and operate by incorporating measurement reports from neighboring robot agents 102 and determining the appropriate control command (s) to navigate through priority areas in a decentralized manner.

As described above with respect to FIG. 2, a robot-assisted wireless coverage measurement platform as described herein can operate in both a centralized mode and a decentralized mode. Accordingly, diagram 500 in FIG. 5 illustrates a platform transformation switch 510 that can be utilized (e.g., via a user operating a user interface, etc. ) to switch operation of the platform between the centralized mode shown by diagram 300 and the decentralized mode shown by diagram 400.

Referring next to FIG. 6, an example propagation model parameter estimation module 600 that can be utilized in accordance with various aspects described herein is illustrated. In an aspect, the propagation model parameter estimation module 600 can be utilized to implement the estimation module 314 described above with respect to FIGS. 3-4 either wholly or in part. As shown in FIG. 6, the propagation model parameter estimation module 600 can take as input a [Coordinates, Signal Strength Indicator] input pair from one or more robot agents 102 as well as a set of prior estimated parameters and a confidence level associated with the prior estimated parameters. In an aspect, the coordinates in the received input pair can correspond to respective positions of robot agents 102 in the global map. As further shown by FIG. 6, the outputs of the propagation model parameter estimation module 600 can include current estimated parameters and a new confidence level associated with the current estimated parameters.

In an aspect, the [Coordinates, Signal Strength Indicator] input pair shown in FIG. 6 can represent historical signal strength measurement data for one or multiple locations. The prior estimated parameters can include a last updated propagation model, e.g., with the latest updated model parameters. Based on these and/or other inputs, the propagation model parameter estimation module 600 can calculate the reliability of the propagation model, which can then be represented as a confidence level. In an aspect, the confidence level can account for confidence in the estimation accuracy of the model at respective physical regions of the investigation site.

Turning to FIG. 7, an example measurement driven path planning module 700 that can be utilized in accordance with various aspects described herein is illustrated. In an aspect, the measurement driven path planning module 700 can be utilized to implement the path planning module 316 described above with respect to FIGS. 3-4 either wholly or in part. In another aspect, the measurement driven path planning module 700 can be utilized to navigate robot agent (s) 102 through an area based on model estimation results (e.g., as determined by the propagation model parameter estimation module 600) and/or a confidence level associated with those results. Also or alternatively, the measurement driven path planning module 700 can be used to enable robot agents 102 to collaboratively identify an area with weak wireless coverage and/or strong interference in a target indoor service area.

As shown by FIG. 7, inputs to the measurement driven path planning module 700 can include current location coordinates of respective robot agents 102, a latest fused map (e.g., as constructed using a SLAM fusion module 312) , and a confidence level of the present estimated model parameters, e.g., as determined by the propagation model parameter estimation module 600. The outputs of the measurement driven path planning module 700 can include a list of desired destinations for subsequent measurements to be performed by the respective robot agents 102.

In an aspect, a low confidence level in the present model parameters as provided to the measurement driven path planning module 700 can indicate that collected measurement data may be of low reliability, e.g., the data may be noisy or contain severe interference. In response to receiving a low confidence level, the measurement driven path planning module 700 can guide the robot agents 102 to investigate neighboring regions of already investigated locations. Conversely, in response to receiving a high confidence level, the measurement driven path planning module 700 can direct the robot agents 102 to investigate regions that have not yet been reached.

In an aspect, the measurement driven path planning module 700 can determine (e.g., on the fly) one or more locations where reliability of signal strength measurements and/or location measurements is below a threshold. In response to this determination, the measurement driven path planning module 700 can direct one or more robot agents 102 to move to the corresponding areas and/or regions neighboring the corresponding areas for further measurement. In an aspect, the output of the measurement driven path planning module 700 can include a priority list of areas associated with measurements of low reliability, which can be provided to the controllers of respective robot agents 102 to generate control commands (e.g., translational/rotational control signals, timestamps, etc. ) to traverse the priority areas with reduced time or cost. Stated another way, the measurement driven path planning module 700 can distribute a priority list of locations to the local controllers of respective robot agents 102 to coordinate the paths of multiple robot agents 102 such that multiple robot agents 102 can visit the areas on the priority list in a complementary manner to reduce the time and cost associated with traversing those areas.

Turning to FIG. 8, an example SLAM module 800 that can be utilized in accordance with various aspects described herein is illustrated. In an aspect, the SLAM module 800 can be utilized to implement the SLAM module 332 described above with respect to FIGS. 3-4 either wholly or in part. As shown by FIG. 8, the SLAM module 800 can take as input raw sensor data, e.g., associated with a robot agent 102. Based on the sensor data, the SLAM module 800 can build a local map corresponding to the area in which the corresponding robot agent 102 is located and estimate the location of the robot agent 102 with respect to the local map. As further shown by FIG. 8, the SLAM module 800 can store the local map to aid in subsequent location and/or mapping operations.

With reference next to FIG. 9, an example SLAM fusion module 900 that can be utilized in accordance with various aspects described herein is illustrated. In an aspect, the SLAM fusion module 900 can be utilized to implement the SLAM fusion module 312 described above with respect to FIG. 3 either wholly or in part. As shown by FIG. 9, the SLAM fusion module 900 can accept as input respective local maps and positions generated by respectively corresponding robot agents 102, e.g., via respective SLAM modules 800 at the robot agents 102. In an aspect, the SLAM fusion module 900 can build a global map from the local maps provided by the robot agents 102 and translate the local positions provided by the robot agents 102 into global positions with respect to the global map.

Referring next to FIG. 10, an example measurement system 1000 that can be utilized in accordance with various aspects described herein is illustrated. In an aspect, the measurement system 1000 can be utilized to implement the measurement module 334 described above with respect to FIGS. 3-4 either wholly or in part. As shown by FIG. 10, the measurement system 1000 can perform one or more measurements corresponding to respective routers 1010 and/or other signal sources via an antenna/receiver 1020. For instance, the antenna/receiver 1020 can detect data packets and/or other transmissions from the respective routers 1010 and provide the detected transmissions to a data processor 1030. The data processor 1030, in turn, can perform one or more measurements with respect to the transmissions which can include, but are not limited to, RSSI, router identification, network identification, channel information, timestamp information, or the like.

Referring next to FIG. 11, a block diagram of a system 1100 that facilitates single-robot assisted learning for wireless coverage and interference maps in accordance with various aspects described herein is illustrated. The system 1100 can be implemented by, e.g., a single robot agent 102 operating in a single robot mode. The system 1100 includes a measurement component 1110 that can perform a signal strength measurement, e.g., the first signal strength measurement as described above with respect to FIG. 1. The system 1100 further includes a SLAM component 1120 that can determine the location of a corresponding robot agent 102 and builds a map corresponding to the area associated with the robot agent 102, e.g., as described above with respect to FIG. 8. In an aspect, the signal strength measurement performed by the measurement component 1110 and the location and map information generated by the SLAM component 1120 can be provided to a parameter estimation component 110, which can update a signal propagation model based on the provided information in accordance with various aspects described herein. The parameter estimation component 110 can, in turn, provide suitable information to a path planning component 120 for directing the robot agent 102 to subsequent measurements as generally described above with respect to FIG. 7.

Turning next to FIG. 12, an example architecture that can be employed for a single-robot task is illustrated by diagram 1200. In an aspect, the architecture shown by diagram 1200 can be utilized for either model estimation or interference source detection since the two tasks can share a common data path with differences in the model parameters, as will be described below.

As diagram 1200 illustrates a single-robot architecture, the components and/or functionality described below is localized within a single robot agent 102. As shown in diagram 1200, the robot agent 102 can interact with its environment, which can include physical characteristics of the surrounding area, signatures of nearby radio frequency (RF) signals, etc. In an aspect, physical characteristics of the environment can be sensed by one or more sensors 1210 on the robot agent 102. For instance, a visual sensor 1210A and/or laser scanner 1210B can be employed to find ranges to surroundings, while an inertia momentum unit (IMU) 1210C can be employed to measure linear acceleration, angular velocity, orientation, or the like. As additionally shown by diagram 1200, RF signal strength can be continuously or near-continuously collected by the measurement module 334, e.g., as RSSI and/or other suitable measures, in parallel with the sensor operation. Processed sensor data can subsequently be passed to a SLAM module 332 for map generation and localization. The resulting map can then be registered at a map server 1220 while the localization results and/or coordinates can be passed to a logger 1230 in combination with wireless signal strength data obtained by the measurement module 334 to produce a [coordinates, signal strength] data pair for storage at a position and signal strength database 1240.

In an aspect, a model register 1250 at the robot agent 102 can control switching between tasks, e.g., a model estimation task and an interference source detection task. The model register 1250 can include different mathematical models for respective ones of the switched tasks. Also or alternatively, the model register 1250 can store the latest updated model as estimated by an estimation module 314.

The estimation module 314 can take as input the [coordinates, signal strength] data pair from the position and signal strength database 1240, the previous confidence level, and the latest model as provided by the model register 1250. In response, the estimation module 314 can output the current confidence level and a newly updated model. The latter can be stored back to the model register 1250.

Additionally, a path planning module 316 can take the confidence level determined by the estimation module 314, the current position of the robot agent 102 as stored by the position and signal strength database 1240, and the map stored at the map server 1220 as input. In response, the path planning module 316 can generate a priority list of destinations, which can be fed into a controller 1260 to generate a series of controlling commands, e.g., velocities, according to the priority list.

In an aspect, operation of the robot agent 102 can proceed as described above in a recursive manner, such that the operational flow described with respect to diagram 1200 can be performed multiple times until the confidence level of the estimated model reaches a threshold, e.g., a user-configured threshold and/or other suitable value.

FIG. 13 illustrates a process 1300 for initializing robot-assisted learning for wireless coverage and interference maps in accordance with various aspects described herein. At 1302, a model can be selected, e.g., a wireless coverage model or an interference model. At 1304, sensors associated with one or more robot agents 102 can be configured.

At 1306, a decision strategy can be set for the position estimator and/or path planning algorithm. In an aspect, the decision strategy can be set at least in party by an aggressiveness level for the path planning algorithm, e.g., as set by a user. The aggressiveness level can affect a tradeoff between energy use and efficiency. For instance, a more aggressive setting can result in the path planning module assigning destinations with less consideration to energy use, while a less aggressive setting can result in the path planning module electing not to assign far away destinations in order to save energy.

At 1308, a criterion can be set, e.g., by a user, for a desired model estimation confidence level, such that ongoing tasks are completed upon satisfaction of the criterion. At 1310, associated robot agent (s) 102 can be placed at their corresponding starting point (s) .

Turning next to FIG. 14, a process 1400 for maintaining a wireless signal propagation model via a single robot agent 102 in accordance with various aspects described herein is illustrated. As shown by FIG. 14, process 1400 can begin following completion of the initialization process 1300 described above with respect to FIG. 13.

At 1402, the robot agent 102 can move to a position for which measurements are to be performed. At 1404, the robot agent can perform the desired measurements, such as signal strength and/or sensor measurements. At 1406, the robot agent 102 can estimate updated model parameters, e.g., via an estimation module 314. At 1408, the robot agent 102 can utilize the updated model parameters obtained at 1406 to calculate, via a path planning module 316, a subsequent position for further measurement.

At 1410, the robot agent 102 can generate control commands via a controller 1260 based on the position calculated at 1408. In response, the robot agent 102 can move to the next position at 1412 using the control commands generated at 1410. As shown at 1414, the operations performed at 1410 and 1412 can be repeated until the robot agent 102 arrives at its designated destination.

At 1416, the robot agent 102 can determine whether a criterion (e.g., the criterion set at 1308 in the initialization process) has been met. If the criterion has not been met, the process 1400 can return to 1404 for further measurement. Otherwise, the process 1400 concludes.

Turning next to FIG. 15, a block diagram of a system 1500 that facilitates multi-robot assisted learning for wireless coverage and interference maps in accordance with various aspects described herein is illustrated. The system 1500 includes one or more robot agents 102 which can communicate information with a cloud server 310 and/or other entity that includes a parameter estimation component 110 and/or a path planning component 120 as described above via a communication component 1510. In an aspect, the communication component 1510 can receive a location of a robot agent 102, signal strength measurements performed by the robot agent 102, and/or other suitable information. In response to obtaining local area map information from multiple robot agents 102 via the communication component 1510, a SLAM fusion component 1520 can construct a fused (global) map based on the received map information. The parameter estimation component 110 can then update a signal propagation model based on the fused map, in accordance with various aspects described herein. In another aspect, the path planning module can generate a direction to a location of a subsequent signal strength measurement to be performed by a robot agent 102, which can be relayed to the robot agent 102 via the communication component 1510.

With reference next to FIG. 16, an example centralized architecture that can be employed for a multi-robot task is illustrated by diagram 1600. Repetitive description of like elements employed in other embodiments described herein is omitted for sake of brevity. In the centralized multi-robot mode illustrated by diagram 1600, respective robot agents 102 can sense their respective local environments and regional signal strengths. In an aspect, a robot agent 102 can pack its associated measurement data and upload the packed data along with a locally generated map to a cloud server 310 via a wireless communication module 1630. Also or alternatively, the robot agent 102 can locally store some or all data sent to the cloud server 310 via a local map server 1622 and/or a local database 1624. In response to receiving new target positions from the cloud server 310, respective robot agents 102 can move to their directed positions via controllers 1642 and actuators 1644 as described above with respect to the single-robot mode shown by diagram 1200.

At the cloud server 310, a wireless communication module 1630 can pass local maps from the robot agents 102 to a SLAM fusion module 312 to fuse a global map. In addition, the cloud server 310 can pass local position and signal strength data to a global database 1660, which can transform respective local positions to global positions via transform information obtained from the SLAM fusion module 312. In an aspect, the SLAM fusion module 312 and global database 1660 can collectively utilize a centralized cloud-based SLAM fusion algorithm that fuses the partial maps and location information from individual robot agents 102 of the platform to generate enhanced global mapping and location information about the environment.

In a similar manner to the single-robot mode shown by diagram 1200, the estimation module 314 at the cloud server 310 can update a propagation model and compute an associated confidence level, and a path planning module 316 at the cloud server 310 can compute a series of destinations. Here, unlike the single-robot mode which utilizes a single destination at a time, the centralized multi-robot mode utilizes a list of prioritized destinations.

In an aspect, the estimation module 314 shown in diagram 1600 can utilize a centralized cloud-based propagation model estimation algorithm which recursively updates the parameters of the model based on prior estimation results, fused wireless signal strength information from respective robot agents 102, and the global position states of the respective robot agents 102. In another aspect, the path planning module 316 shown in diagram 1600 can utilize a centralized cloud-based global navigation planning algorithm that directs the global path plans of individual robot agents 102 incrementally based on recent fusion measurements, recent fused RF coverage and interference map information, and/or quality (reliability) of the fused RF coverage and interference map information.

Turning next to FIG. 17, a process 1700 for maintaining a wireless signal propagation model via a centralized network of robot agents 102 in accordance with various aspects described herein is illustrated. As shown by FIG. 17, process 1700 can begin following completion of the initialization process 1300 described above with respect to FIG. 13.

Process 1700 begins at 1702 by checking whether the criterion associated with the procedure, e.g., the criterion set at 1308 in the initialization process, has been met. If the criterion has been met, process 1700 concludes. Otherwise, process 1700 proceeds to 1704.

At 1704, the respective robot agents 102 of the platform can move to their next positions. At 1706, the robot agents 102 can send their local maps, positions, and/or signal strength measurements to the cloud server 310 via a wireless connection.

At 1708, the cloud server 310 can perform global map fusion, global position calculation, and global signal strength/position pairing based on the information received from the robot agents 102 at 1706. At 1710, the cloud server 310 can update its propagation model, e.g., via an estimation module 314. At 1712, the cloud server 310 can generate a prioritized destination list, e.g., via a path planning module 316.

At 1714, the cloud server 310 can send the global map and data obtained at 1708, 1710, and/or 1712 to respective robot agents 102. In response, the robot agents 102 can generate controlling commands via respective local controllers at 1716. At 1718, the robot agents 102 move to their next positions based on the commands generated at 1716. At 1720, if at least a threshold number of the robot agents 102 have arrived at their destinations, process 1700 can return to 1702 for subsequent measurement. Otherwise, process 1700 can return to 1716 to generate further controlling commands at the robot agents 102 that have not arrived at their destinations.

With reference next to FIG. 18, an example decentralized architecture that can be employed for a multi-robot task is illustrated by diagram 1800. Repetitive description of like elements employed in other embodiments described herein is omitted for sake of brevity. In an aspect, the decentralized multi-robot mode can utilize multiple robot agents 102 that are organized in a similar manner to the single robot mode shown by diagram 1200 with the addition of a communication module 1810 utilized for inter-robot communication. While only one robot agent 102A is fully illustrated in diagram 1800 for brevity, it should be appreciated that each robot agent 102 in diagram 1800 can be configured in a similar manner to the illustrated robot agent 102A.

In an aspect, respective robot agents 102 shown in diagram 1800 can operate similarly to that described above with respect to the single-robot mode shown by diagram 1200. In addition, the communication module 1810 can broadcast the position of each robot agent 102, signal strength measurement data, and recent estimated model parameters, as well as listen for similar information from respective neighboring robot agents 102.

In another aspect, the estimation module 314 at respective robot agents 102 can utilize a decentralized propagation model estimation algorithm that recursively updates model parameters based on locally determined estimated model parameters and [coordinates, signal strength] data pairs in addition to similar information obtained from neighboring robot agents 102. In this way, the propagation model estimation algorithm can utilize local and neighbor wireless signal strength data, as well as local and neighbor position states, in computing updated model parameters. The resulting output of the estimation module 314 can be given as a fused result that includes a fused propagation model and a corresponding confidence level.

Respective robot agents 102 as illustrated by diagram 1800 can further utilize a decentralized SLAM algorithm that can build a partial indoor/outdoor map and local position information simultaneously based on local sensor measurements. In response to operation of the SLAM algorithm, a decentralized/local path determination algorithm at the respective robot agents 102 can further locally determine robot controls based on the SLAM sensor measurements, the estimated indoor/outdoor map, and associated wireless channel measurements.

In an aspect, when the path planning module 316 shown in diagram 1800 finds a new destination, it can take into account the positions of neighboring robot agents 102 to avoid overlapping destinations. In this way, the robot agents 102 of the platform can operate as a group to search regions in a time-and energy-efficient manner. In another aspect, the path planning module 316 can utilize a decentralized/local path planning algorithm that guides the path planning of an associated robot agent 102 incrementally based on recent local measurements, recent local RF coverage and/or interference map determinations and/or quality of such determinations, and/or other criteria.

Referring now to FIG. 19, a process 1900 for maintaining a wireless signal propagation model via a decentralized network of robot agents 102 in accordance with various aspects described herein is illustrated. As shown by FIG. 19, process 1900 can begin following completion of the initialization process 1300 described above with respect to FIG. 13.

Process 1900 begins at 1902 by checking whether the criterion associated with the procedure, e.g., the criterion set at 1308 in the initialization process, has been met. In an aspect, the criterion checked at 1902 can include whether a certain number of robot agents 102 have achieved an estimated propagation model with a confidence level of at least a threshold value. The threshold confidence level, and/or the number of agents that are to achieve the threshold confidence level, can be set (e.g., by a user) in the course of setting the criterion at 1308. If it is determined at 1902 that the criterion has been met, process 1900 concludes. Otherwise, process 1900 proceeds to 1904.

At 1904, the respective robot agents 102 of the platform can move to their next positions. At 1906, the robot agents 102 can broadcast their local maps, positions, and/or signal strength measurements to neighboring robot agents 102 via a wireless connection and listen for similar broadcasts from the neighboring robot agents 102.

At 1908, the robot agents 102 can integrate the neighbor agent data received at 1906 into a local database. At 1910, the robot agents 102 can update their respective propagation models, e.g., via estimation modules 314. At 1912, the robot agents 102 can generate respective destinations, e.g., via path planning modules 316.

At 1914, the robot agents can generate controlling commands, e.g., via local controllers, corresponding to the destinations obtained at 1912. At 1916, the robot agents 102 move to their next positions based on the commands generated at 1914. At 1918, if at least a threshold number of the robot agents 102 have arrived at their destinations, process 1900 can return to 1902 for subsequent measurement. Otherwise, process 1900 can return to 1914 to generate further controlling commands at the robot agents 102 that have not arrived at their destinations.

Turning next to FIG. 20, illustrated is a flow diagram of a process 2000 that facilitates multi-robot assisted learning for wireless coverage and interference maps in accordance with various aspects described herein. At 2002, a device operatively coupled to a processor (e.g., a robot agent 102 and/or a cloud server 310) can update (e.g., by a parameter estimation component 110) a signal propagation model for an area associated with a robot agent 102 based on a location of the robot agent 102 and a first signal strength measurement performed by the robot agent 102, resulting in an updated signal propagation model.

At 2004, the device can determine (e.g., via a path planning component 120) a location of a second signal strength measurement to be performed by the robot agent 102 based on the updated signal propagation model obtained at 2002 and a confidence level associated with the updated signal propagation model.

FIGS. 13, 14, 17, 19, and 20 as described above illustrate respective methods in accordance with certain aspects of this disclosure. While, for purposes of simplicity of explanation, the methods are shown and described as a series of acts, it is to be understood and appreciated that this disclosure is not limited by the order of acts, as some acts may occur in different orders and/or concurrently with other acts from that shown and described herein. For example, those skilled in the art will understand and appreciate that methods can alternatively be represented as a series of interrelated states or events, such as in a state diagram. Moreover, not all illustrated acts may be required to implement methods in accordance with certain aspects of this disclosure.

In order to provide additional context for various embodiments described herein, FIG. 21 and the following discussion are intended to provide a brief, general description of a suitable computing environment 2100 in which the various embodiments of the embodiment described herein can be implemented. While the embodiments have been described above in the general context of computer-executable instructions that can run on one or more computers, those skilled in the art will recognize that the embodiments can be also implemented in combination with other program modules and/or as a combination of hardware and software.

Generally, program modules include routines, programs, components, data structures, etc., that perform particular tasks or implement particular abstract data types. Moreover, those skilled in the art will appreciate that the inventive methods can be practiced with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, hand-held computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which can be operatively coupled to one or more associated devices.

The illustrated embodiments of the embodiments herein can be also practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote memory storage devices.

Computing devices typically include a variety of media, which can include computer-readable storage media and/or communications media, which two terms are used herein differently from one another as follows. Computer-readable storage media can be any available storage media that can be accessed by the computer and includes both volatile and nonvolatile media, removable and non-removable media. By way of example, and not limitation, computer-readable storage media can be implemented in connection with any method or technology for storage of information such as computer-readable instructions, program modules, structured data or unstructured data.

Computer-readable storage media can include, but are not limited to, random access memory (RAM) , read only memory (ROM) , electrically erasable programmable read only memory (EEPROM) , flash memory or other memory technology, solid state drive (SSD) or other solid-state storage technology, compact disk read only memory (CD-ROM) , digital versatile disk (DVD) , Blu-ray disc or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or other tangible and/or non-transitory media which can be used to store desired information. In this regard, the terms “tangible” or “non-transitory” herein as applied to storage, memory or computer-readable media, are to be understood to exclude only propagating transitory signals per se as modifiers and do not relinquish rights to all standard storage, memory or computer-readable media that are not only propagating transitory signals per se.

Computer-readable storage media can be accessed by one or more local or remote computing devices, e.g., via access requests, queries or other data retrieval protocols, for a variety of operations with respect to the information stored by the medium.

Communications media typically embody computer-readable instructions, data structures, program modules or other structured or unstructured data in a data signal such as a modulated data signal, e.g., a carrier wave or other transport mechanism, and includes any information delivery or transport media. The term “modulated data signal” or signals refers to a signal that has one or more of its characteristics set or changed in such a manner as to encode information in one or more signals. By way of example, and not limitation, communication media include wired media, such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media.

With reference again to FIG. 21, the example environment 2100 for implementing various embodiments of the aspects described herein includes a computer 2102, the computer 2102 including a processing unit 2104, a system memory 2106 and a system bus 2108. The system bus 2108 couples system components including, but not limited to, the system memory 2106 to the processing unit 2104. The processing unit 2104 can be any of various commercially available processors. Dual microprocessors and other multi-processor architectures can also be employed as the processing unit 2104.

The system bus 2108 can be any of several types of bus structure that can further interconnect to a memory bus (with or without a memory controller) , a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. The system memory 2106 includes ROM 2110 and RAM 2112. A basic input/output system (BIOS) can be stored in a non-volatile memory such as ROM, erasable programmable read only memory (EPROM) , EEPROM, which BIOS contains the basic routines that help to transfer information between elements within the computer 2102, such as during startup. The RAM 2112 can also include a high-speed RAM such as static RAM for caching data.

The computer 2102 further includes an internal hard disk drive (HDD) 2114 (e.g., EIDE, SATA) , a magnetic floppy disk drive (FDD) 2116, (e.g., to read from or write to a removable diskette 2118) and an optical disk drive 2120, (e.g., reading a CD-ROM disk 2122 or, to read from or write to other high capacity optical media such as the DVD) . While the internal HDD 2114 is illustrated as located within the computer 2102, the internal HDD 2114 can also be configured for external use in a suitable chassis (not shown) . The HDD 2114, magnetic FDD 2116 and optical disk drive 2120 can be connected to the system bus 2108 by an HDD interface 2124, a magnetic disk drive interface 2126 and an optical drive interface 2128, respectively. The interface 2124 for external drive implementations includes at least one or both of Universal Serial Bus (USB) and Institute of Electrical and Electronics Engineers (IEEE) 1394 interface technologies. Other external drive connection technologies are within contemplation of the embodiments described herein.

The drives and their associated computer-readable storage media provide nonvolatile storage of data, data structures, computer-executable instructions, and so forth. For the computer 2102, the drives and storage media accommodate the storage of any data in a suitable digital format. Although the description of computer-readable storage media above refers to an HDD, a removable magnetic diskette, and a removable optical media such as a CD or DVD, it should be appreciated by those skilled in the art that other types of storage media which are readable by a computer, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, can also be used in the example operating environment, and further, that any such storage media can contain computer-executable instructions for performing the methods described herein.

A number of program modules can be stored in the drives and RAM 2112, including an operating system 2130, one or more application programs 2132, other program modules 2134 and program data 2136. All or portions of the operating system, applications, modules, and/or data can also be cached in the RAM 2112. The systems and methods described herein can be implemented utilizing various commercially available operating systems or combinations of operating systems.

A user can enter commands and information into the computer 2102 through one or more wired/wireless input devices, e.g., a keyboard 2138 and a pointing device, such as a mouse 2140. Other input devices (not shown) can include a microphone, an infrared (IR) remote control, a joystick, a game pad, a stylus pen, touch screen or the like. These and other input devices are often connected to the processing unit 2104 through an input device interface 2142 that can be coupled to the system bus 2108, but can be connected by other interfaces, such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, etc.

A monitor 2144 or other type of display device can be also connected to the system bus 2108 via an interface, such as a video adapter 2146. In addition to the monitor 2144, a computer typically includes other peripheral output devices (not shown) , such as speakers, printers, etc.

The computer 2102 can operate in a networked environment using logical connections via wired and/or wireless communications to one or more remote computers, such as a remote computer (s) 2148. The remote computer (s) 2148 can be a workstation, a server computer, a router, a personal computer, portable computer, microprocessor-based entertainment appliance, a peer device or other common network node, and typically includes many or all of the elements described relative to the computer 2102, although, for purposes of brevity, only a memory/storage device 2150 is illustrated. The logical connections depicted include wired/wireless connectivity to a local area network (LAN) 2152 and/or larger networks, e.g., a wide area network (WAN) 2154. Such LAN and WAN networking environments are commonplace in offices and companies, and facilitate enterprise-wide computer networks, such as intranets, all of which can connect to a global communications network, e.g., the Internet.

When used in a LAN networking environment, the computer 2102 can be connected to the local network 2152 through a wired and/or wireless communication network interface or adapter 2156. The adapter 2156 can facilitate wired or wireless communication to the LAN 2152, which can also include a wireless access point (AP) disposed thereon for communicating with the wireless adapter 2156.

When used in a WAN networking environment, the computer 2102 can include a modem 2158 or can be connected to a communications server on the WAN 2154 or has other means for establishing communications over the WAN 2154, such as by way of the Internet. The modem 2158, which can be internal or external and a wired or wireless device, can be connected to the system bus 2108 via the input device interface 2142. In a networked environment, program modules depicted relative to the computer 2102 or portions thereof, can be stored in the remote memory/storage device 2150. It will be appreciated that the network connections shown are example and other means of establishing a communications link between the computers can be used.

The computer 2102 can be operable to communicate with any wireless devices or entities operatively disposed in wireless communication, e.g., a printer, scanner, desktop and/or portable computer, portable data assistant, communications satellite, any piece of equipment or location associated with a wirelessly detectable tag (e.g., a kiosk, news stand, restroom) , and telephone. This can include Wireless Fidelity (Wi-Fi) and

wireless technologies. Thus, the communication can be a predefined structure as with a conventional network or simply an ad hoc communication between at least two devices.

The above description includes non-limiting examples of the various embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the disclosed subject matter, and one skilled in the art may recognize that further combinations and permutations of the various embodiments are possible. The disclosed subject matter is intended to embrace all such alterations, modifications, and variations that fall within the spirit and scope of the appended claims.

With regard to the various functions performed by the above described components, devices, circuits, systems, etc., the terms (including a reference to a “means” ) used to describe such components are intended to also include, unless otherwise indicated, any structure (s) which performs the specified function of the described component (e.g., a functional equivalent) , even if not structurally equivalent to the disclosed structure. In addition, while a particular feature of the disclosed subject matter may have been disclosed with respect to only one of several implementations, such feature may be combined with one or more other features of the other implementations as may be desired and advantageous for any given or particular application.

The terms “exemplary” and/or “demonstrative” as used herein are intended to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent structures and techniques known to one skilled in the art. Furthermore, to the extent that the terms “includes, ” “has, ” “contains, ” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive -in a manner similar to the term “comprising” as an open transition word -without precluding any additional or other elements.

The term “or” as used herein is intended to mean an inclusive “or” rather than an exclusive “or. ” For example, the phrase “A or B” is intended to include instances of A, B, and both A and B. Additionally, the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless either otherwise specified or clear from the context to be directed to a singular form.

The term “set” as employed herein excludes the empty set, i.e., the set with no elements therein. Thus, a “set” in the subject disclosure includes one or more elements or entities. Likewise, the term “group” as utilized herein refers to a collection of one or more entities.

The description of illustrated embodiments of the subject disclosure as provided herein, including what is described in the Abstract, is not intended to be exhaustive or to limit the disclosed embodiments to the precise forms disclosed. While specific embodiments and examples are described herein for illustrative purposes, various modifications are possible that are considered within the scope of such embodiments and examples, as one skilled in the art can recognize. In this regard, while the subject matter has been described herein in connection with various embodiments and corresponding drawings, where applicable, it is to be understood that other similar embodiments can be used or modifications and additions can be made to the described embodiments for performing the same, similar, alternative, or substitute function of the disclosed subject matter without deviating therefrom. Therefore, the disclosed subject matter should not be limited to any single embodiment described herein, but rather should be construed in breadth and scope in accordance with the appended claims below.

Claims

A system, comprising:

a memory that stores computer executable components; and

a processor that executes computer executable components stored in the memory, wherein the computer executable components comprise:

a parameter estimation component that updates a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model; and

a path planning component that determines a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.
The system of claim 1, wherein the computer executable components further comprise:

a measurement component that performs the first signal strength measurement at the robot agent.
The system of claim 2, wherein the computer executable components further comprise:

a simultaneous location and mapping component that determines the location of the robot agent and builds a map corresponding to the area associated with the robot agent, wherein the parameter estimation module further updates the signal propagation model based on the map.
The system of claim 1, wherein the computer executable components further comprise:

a communication component that receives the location of the robot agent and the first signal strength measurement from the robot agent.
The system of claim 4, wherein the robot agent is a first robot agent, and wherein the computer executable components further comprise:

a simultaneous location and mapping fusion module that obtains area map information from the first robot agent and at least one second robot agent in the area associated with the first robot agent and constructs a fused map based on the area map information, wherein the parameter estimation module further updates the signal propagation model based on the fused map.
The system of claim 4, wherein the communication component transmits a direction to the location of the second signal strength measurement to the robot agent.
The system of claim 1, wherein the robot agent is a first robot agent, and wherein the parameter estimation component updates the signal propagation model based on respective locations of the first robot agent and at least one second robot agent and respective first signal strength measurements performed by the first robot agent and the at least one second robot agent.
The system of claim 1, wherein the signal propagation model comprises a wireless signal coverage map.
The system of claim 1, wherein the signal propagation model comprises a wireless signal interference model.
A computer-implemented method, comprising:

updating, by a device operatively coupled to a processor, a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model; and

determining, by the device, a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.
The computer-implemented method of claim 10, further comprising:

building, by the device, a map corresponding to the area associated with the robot agent,

wherein the updating comprises updating the signal propagation model based on the map.
The computer-implemented method of claim 10, further comprising:

receiving, by the device, the location of the robot agent and the first signal strength measurement from the robot agent.
The computer-implemented method of claim 12, wherein the robot agent is a first robot agent, and further comprising:

obtaining, by the device, area map information from the first robot agent and at least one second robot agent in the area associated with the first robot agent; and

generating, by the device, a fused map based on the area map information.
The computer-implemented method of claim 13, wherein the updating comprises updating the signal propagation model based on the fused map.
The computer-implemented method of claim 10, wherein the robot agent is a first robot agent, and wherein the updating comprises updating the signal propagation model based on respective locations of the first robot agent and at least one second robot agent and respective first signal strength measurements performed by the first robot agent and the at least one second robot agent.
A non-transitory machine-readable medium comprising executable instructions that, when executed by a processor, facilitate performance of operations, the operations comprising:

updating a signal propagation model for an area associated with a robot agent based on a location of the robot agent and a first signal strength measurement performed by the robot agent, resulting in an updated signal propagation model; and

computing a location of a second signal strength measurement to be performed by the robot agent based on the updated signal propagation model and a confidence level associated with the updated signal propagation model.
The non-transitory machine-readable medium of claim 16, wherein the operations further comprise:

building a map corresponding to the area associated with the robot agent; and

updating the signal propagation model based on the map.
The non-transitory machine-readable medium of claim 16, wherein the operations further comprise:

receiving the location of the robot agent and the first signal strength measurement from the robot agent.
The non-transitory machine-readable medium of claim 18, wherein the robot agent is a first robot agent, and wherein the operations further comprise:

obtaining area map information from the first robot agent and a second robot agent in the area associated with the first robot agent;

constructing a fused map based on the area map information; and

updating the signal propagation model based on the fused map.
The non-transitory machine-readable medium of claim 16, wherein the robot agent is a first robot agent, and wherein the operations further comprise:

updating the signal propagation model based on respective locations of the first robot agent and a second robot agent and respective first signal strength measurements performed by the first robot agent and the second robot agent.