System and method for providing guidance instructions to operable charging devices

Abstract

A charging device guidance system includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to perform the following operations: receive a sequence of user states associated with a user of a first autonomous vehicle, each user state being one of a walking state and a charging device state, and the sequence of user states being based on a sequence of observed user velocities associated with detected user position data associated with movement of the user from the first autonomous vehicle to a charging device and at the charging device; determine a charging device location of the charging device based on a correlation of the charging device state in the sequence of user states to the user position data; and upload the charging device location associated with the charging device to an edge computing system configured to provide charging device guidance instructions to a second autonomous vehicle based at least in part on the charging device location.

Description

Technical Field

[0001] This technical field generally relates to autonomous vehicles, and more specifically to systems and methods for providing guidance instructions to an operable charging device. Background Technology

[0002] Electric vehicle charging stations typically include multiple parking spaces. An example of an electric vehicle is an autonomous vehicle. A vehicle parked in one of the parking spaces at a charging station can use multiple charging devices.

[0003] One or more charging units at a charging station may be inoperable. Different charging units at a charging station may have different charging rates. A low charging rate may indicate an operational problem associated with a charging unit. A user may not be aware of an operational problem with a charging unit until they attempt to charge their autonomous vehicle using it. A user may try using multiple charging units at a charging station before finding an operational one. In some cases, a user may visit multiple charging stations before finding an operational one.

[0004] Public content

[0005] In one embodiment, the charging device guidance system includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to perform the following operations: receive a sequence of user states associated with a user of a first autonomous vehicle, each user state being either a walking state or a charging device state, and the user state sequence being based on an observed sequence of user speeds associated with detected user location data, which is related to the user's movement from the first autonomous vehicle to and from the charging device; determine the charging device location of the charging device based on the correlation between the charging device state in the user state sequence and the user location data; and upload the charging device location associated with the charging device to an edge computing system configured to provide charging device guidance instructions to a second autonomous vehicle, at least in part, based on the charging device location.

[0006] In one embodiment, the detected user location data is detected by at least one of the surround-view camera system and the wireless positioning sensor system of the first autonomous vehicle's vehicle sensor system.

[0007] In one embodiment, the memory includes further instructions that, when executed by the processor, cause the processor to determine the location of the parking space associated with the charging device based in part on vehicle location data received from the vehicle sensor system of the first autonomous vehicle.

[0008] In one embodiment, the memory includes further instructions that, when executed by the processor, cause the processor to use the Viterbi algorithm in conjunction with a hidden Markov model of user states to generate a sequence of user states associated with the observed sequence of user velocities, wherein the user states are hidden states.

[0009] In an embodiment, the memory includes further instructions that, when executed by the processor, cause the processor to generate at least two intermediate charging device locations based on user location data corresponding to at least two charging device states in a user state sequence, and to determine the charging device location of the charging device based on the average of the at least two intermediate charging device locations.

[0010] In an embodiment, the memory includes further instructions that, when executed by a processor, cause the processor to perform the following operations: receive a sequence of charging device states associated with the charging device, each of the charging device states being either a used state or a disabled state, and the sequence of charging device states being based on an observed charging rate sequence associated with the charging device; and determine the charging device state of the charging device based on the sequence of charging device states.

[0011] In one embodiment, the memory includes further instructions that, when executed by the processor, cause the processor to upload the charging device status associated with the charging device to an edge computing system configured to provide guidance instructions to the charging device to a second autonomous vehicle in part based on the charging device status.

[0012] In an embodiment, the memory includes further instructions that, when executed by the processor, cause the processor to use the Viterbi algorithm in conjunction with a hidden Markov model of the charging device states to generate a sequence of charging device states associated with the observed charging rate sequence, wherein the charging device states are hidden states.

[0013] In one embodiment, a computer-readable medium includes instructions stored thereon for providing guidance instructions to a charging device. When executed by a processor, the instructions cause the processor to perform the following operations: receive a sequence of user states associated with a user of a first autonomous vehicle, each user state being either a walking state or a charging device state, and the user state sequence being based on an observed sequence of user speeds associated with detected user location data, which is related to the user's movement from the first autonomous vehicle to and from the charging device; determine the charging device location of the charging device based on the correlation between the charging device state in the user state sequence and the user location data; and upload the charging device location associated with the charging device to an edge computing system configured to provide charging device guidance instructions to a second autonomous vehicle, at least in part, based on the charging device location.

[0014] In an embodiment, the computer-readable medium further includes instructions that cause the processor to receive detected user location data from at least one of the vehicle sensor system of the first autonomous vehicle, a surround-view camera system, and a wireless positioning sensor system.

[0015] In an embodiment, the computer-readable medium further includes instructions that cause the processor to determine the location of the parking space associated with the charging device based in part on vehicle location data received from the vehicle sensor system of the first autonomous vehicle.

[0016] In an embodiment, the computer-readable medium further includes instructions that cause a processor to use the Viterbi algorithm in conjunction with a hidden Markov model of user states to generate a sequence of user states associated with an observed sequence of user velocities, wherein the user states are hidden states.

[0017] In an embodiment, the computer-readable medium further includes instructions that cause a processor to perform the following operations: generate at least two intermediate charging device locations based on user location data corresponding to at least two charging device states in a user state sequence; and determine the charging device location of the charging device based on the average of the at least two intermediate charging device locations.

[0018] In an embodiment, the computer-readable medium further includes instructions that cause a processor to perform the following operations: receiving a sequence of charging device states associated with a charging device, each of the charging device states being either an in-use state or a deactivated state, and the sequence of charging device states being based on an observed charging rate sequence associated with the charging device; and determining the charging device state of the charging device based on the sequence of charging device states.

[0019] In an embodiment, the computer-readable medium further includes instructions that cause the processor to upload the charging device status associated with the charging device to an edge computing system configured to provide guidance instructions for the charging device to a second autonomous vehicle in part based on the charging device status.

[0020] In an embodiment, the computer-readable medium further includes instructions that cause a processor to use the Viterbi algorithm in conjunction with a hidden Markov model of the charging device state to generate a sequence of charging device states associated with an observed sequence of charging rates, wherein the charging device states are hidden states.

[0021] In one embodiment, a method for providing guidance instructions to a charging device includes: receiving at a charging device guidance system a sequence of user states associated with a user of a first autonomous vehicle, each user state being either a walking state or a charging device state, and the user state sequence being based on an observed user speed sequence associated with detected user location data, the user location data being associated with the user's movement from the first autonomous vehicle to the charging device and at the charging device; determining the charging device location of the charging device based on the correlation between the charging device state in the user state sequence and the user location data; and uploading the charging device location associated with the charging device from the charging device guidance system to an edge computing system configured to provide guidance instructions for the charging device to a second autonomous vehicle at least in part based on the charging device location.

[0022] In an embodiment, the method further includes using the Viterbi algorithm combined with a hidden Markov model of user state to generate a sequence of user state states associated with the observed user velocity sequence, wherein the user state is the hidden state at the charging device guidance system.

[0023] In an embodiment, the method further includes: receiving a sequence of charging device states associated with a charging device, each charging device state being either a used state or a disabled state, and the sequence of charging device states being based on an observed charging rate sequence associated with the charging device; and determining the charging device state of the charging device based on the sequence of charging device states at a charging device guidance system.

[0024] In one embodiment, the method further includes uploading the charging device status associated with the charging device to an edge computing system configured to provide guidance instructions for the charging device to a second autonomous vehicle in part based on the charging device status. Attached Figure Description

[0025] Exemplary embodiments will be described below with reference to the accompanying drawings, wherein the same numbers denote the same elements.

[0026] Figure 1 This is a functional block diagram representation of an autonomous vehicle including an embodiment of a charging device guidance system;

[0027] Figure 2 This is a functional block diagram representation of an autonomous vehicle including a charging device guidance system parked in a parking space at a charging station;

[0028] Figure 3 This is a functional block diagram representation of multiple autonomous vehicles, including an embodiment of a charging device guidance system communicatively coupled to an edge computing system;

[0029] Figure 4This is a functional block diagram representation of an embodiment of the charging device guidance system;

[0030] Figure 5 This is a flowchart representation of an example of a method for determining the location of a charging device using an embodiment of a charging device guidance system;

[0031] Figure 6 This is an example of a state graph associated with a hidden Markov model of user state used in an embodiment of a charging device guidance system.

[0032] Figure 7 This is a block diagram representation of an embodiment of the user state sequence module;

[0033] Figure 8 This is a flowchart representation of an example of a method for predicting the charging device state using an embodiment of a charging device guidance system;

[0034] Figure 9 Here is an example of a state graph associated with a hidden Markov model of charging states; and

[0035] Figure 10 This is an example of a method for providing boot instructions to an operable charging device using an embodiment of a charging device boot system. Detailed Implementation

[0036] The following detailed embodiments are merely exemplary in nature and are not intended to limit the scope of this application and its uses. Furthermore, they are not intended to be construed as being bound by any express or implied theories presented in the foregoing background, disclosure, or the following detailed embodiments. As used herein, the term "module" refers to any hardware, software, firmware, electronic control components, processing logic, and / or processor device, individually or in any combination, including but not limited to: application-specific integrated circuits (ASICs), electronic circuits, processors (shared, dedicated, or grouped), and memory, combinational logic circuitry, and / or other suitable components that execute one or more software or firmware programs to provide the described functionality.

[0037] Embodiments of this disclosure can be described herein in terms of functional and / or logical block components and various processing steps. It should be understood that such block components can be implemented by any number of hardware, software, and / or firmware components configured to perform specified functions. For example, embodiments of this disclosure can employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, lookup tables, etc., which can perform various functions under the control of one or more microprocessors or other control devices. Furthermore, those skilled in the art will understand that embodiments of this disclosure can be practiced in combination with any number of systems, and the systems described herein are merely exemplary embodiments of this disclosure.

[0038] For the sake of brevity, conventional techniques related to signal processing, data transmission, signaling, control, and other functional aspects of the system (and its various operating components) are not described in detail herein. Furthermore, the connecting lines shown in the various figures included herein are intended to represent exemplary functional relationships and / or physical couplings between various elements. It should be noted that many alternative or additional functional relationships or physical connections may exist in the embodiments of this disclosure.

[0039] refer to Figure 1 This diagram illustrates a functional block diagram of an autonomous vehicle 100 including one embodiment of a charging device guidance system 110. The autonomous vehicle 100 typically includes a chassis 112, a body 114, front wheels 116, and rear wheels 118. The body 114 is mounted on the chassis 112 and substantially surrounds the components of the autonomous vehicle 100. The body 114 and chassis 112 may collectively form a frame. The front wheels 116 and rear wheels 118 are each rotatably connected to the chassis 112 near a respective corner of the body 114.

[0040] For example, autonomous vehicle 100 is an automatically controlled vehicle that can transport passengers from one location to another. While autonomous vehicle 100 is described as a passenger car in the illustrated embodiment, other examples of autonomous vehicles include, but are not limited to, motorcycles, trucks, sports utility vehicles (SUVs), recreational vehicles (RVs), boats, and aircraft. In the embodiment, autonomous vehicle 100 is a so-called Level 4 or Level 5 automation system. A Level 4 system signifies “high automation,” referring to the driving mode-specific performance of the automated driving system (ADS) in all aspects of a dynamic driving task, even if the human driver does not respond appropriately to intervention requests. A Level 5 system signifies “full automation,” referring to the comprehensive performance of the ADS in all aspects of a dynamic driving task under all road and environmental conditions that a human driver can manage.

[0041] As shown in the figure, an autonomous vehicle 100 typically includes a propulsion system 120, a transmission system 122, a steering system 124, a braking system 126, a vehicle sensor system 128, an actuator system 130, at least one data storage device 132, at least one controller 134, and a vehicle communication system 136. In various embodiments, the propulsion system 120 may include an internal combustion engine, an electric motor such as a traction motor, and / or a fuel cell propulsion system. The transmission system 122 is configured to transmit power from the propulsion system 120 to the front wheels 116 and the rear wheels 118 according to a selectable speed ratio. According to various embodiments, the transmission system 122 may include a graded automatic transmission, a continuously variable transmission (CVT), or other suitable transmissions. The braking system 126 is configured to provide braking torque to the front wheels 116 and the rear wheels 118. In various embodiments, the braking system 126 may include friction brakes, brake-by-wire brakes, regenerative braking systems such as electric motors, and / or other suitable braking systems. The braking system 124 affects the position of the front wheels 116 and the rear wheels 118. Although described for illustrative purposes as including a steering wheel, in some embodiments contemplated within the scope of this disclosure, the steering system 124 may not include a steering wheel.

[0042] Vehicle sensor system 128 includes one or more vehicle sensing devices 140a-140n that sense observable conditions of the external and / or internal environments of the autonomous vehicle 100. Examples of vehicle sensing devices 140a-140n include, but are not limited to, radar, lidar, GPS, optical cameras, thermal imagers, ultrasonic sensors, and / or other sensors. In one embodiment, vehicle sensor system 128 includes a surround-view camera system. In another embodiment, vehicle sensor system 128 includes a wireless positioning sensor system. In yet another embodiment, vehicle sensor system 128 includes both a surround-view camera system and a wireless positioning sensor system. Actuator system 130 includes one or more actuator devices 142a-142n that control one or more vehicle features, such as, but not limited to, propulsion system 120, drivetrain 122, steering system 124, and braking system 126. In various embodiments, vehicle features may also include internal and / or external vehicle features, such as, but not limited to, doors, trunk, and cabin features, such as air, music, and lighting.

[0043] Vehicle communication system 136 is configured to wirelessly transmit information to and from other entities (“V2X” communication). For example, vehicle communication system 136 is configured to wirelessly transmit information to and from other vehicles 148 (“V2V” communication), to and from drive system infrastructure (“V2I” communication), remote systems, to and from edge computing system 150, and / or personal devices. In embodiments, vehicle communication system 136 is a wireless communication system configured to communicate via a wireless local area network (WLAN) using the IEEE 802.11 standard or by using cellular data communication. However, additional or alternative communication methods, such as Dedicated Short Range Communication (DSRC) channels, are also considered within the scope of this disclosure. DSRC channels refer to one-way or two-way short-to-medium range wireless communication channels designed specifically for automotive use, along with a set of corresponding protocols and standards.

[0044] Data storage device 132 stores data used for automatically controlling the autonomous vehicle 100. Data storage device 132 may be part of controller 134, separate from controller 134, or part of controller 134 and an independent system.

[0045] Controller 134 includes at least one processor 144 and a computer-readable storage device 146. The computer-readable storage device 146 may also be referred to as computer-readable medium 146. In embodiments, the computer-readable storage device 146 includes embodiments of the charging device boot system 110. Processor 144 may be any custom or commercially available processor, central processing unit (CPU), graphics processing unit (GPU), auxiliary processor among a plurality of processors associated with controller 134, semiconductor-based microprocessor (in the form of a microchip or chipset), macroprocessor, any combination thereof, or any device generally used for executing instructions. For example, computer-readable storage device 146 may include volatile and non-volatile memory in read-only memory (ROM), random access memory (RAM), and wear-corrected factor memory (KAM). KAM is persistent or non-volatile memory that can be used to store various operational variables when processor 144 is powered off. The computer-readable storage device 146 can be implemented using any of many known storage devices, such as PROM (programmable read-only memory), EPROM (electric PROM), EEPROM (electrically erasable PROM), flash memory, or any other electrical, magnetic, optical, or combined storage device capable of storing data, some of which represent executable instructions used by the controller 134 to control the autonomous vehicle 100.

[0046] The instructions may include one or more independent programs, each of which includes an ordered list of executable instructions for implementing logical functions. When executed by processor 144, the instructions receive and process signals from vehicle sensor system 128, execute logic, calculations, methods, and / or algorithms to automatically control components of autonomous vehicle 100, and generate control signals to actuator system 130 to automatically control one or more components of autonomous vehicle 100 based on logic, calculations, methods, and / or algorithms. Although in Figure 1 Only one controller 134 is shown in the figure. Alternative embodiments of the autonomous vehicle 100 may include any number of controllers 134 that communicate via any suitable communication medium or combination of communication media and cooperate to process sensor signals, execute logic, calculations, methods and / or algorithms, and generate control signals to automatically control the features of the autonomous vehicle 100.

[0047] In various embodiments, one or more instructions are included to implement controller 134 to provide ADS functionality as described with reference to one or more embodiments herein. Controller 134 or one of its functional modules is configured to implement one or a combination of the functions described in the embodiments of the reference charging device boot system 110.

[0048] refer to Figure 2 This diagram illustrates a functional block diagram of an autonomous vehicle 100 including a charging device guidance system 110 parked in a parking space 200 at a charging station. The user of the autonomous vehicle 100 in the parking space 200 can use two charging devices 202. One of the charging devices 202 is located at a first charging device location 204, and the other is located at a second charging device location 206. The charging device guidance system 110 is configured to receive vehicle location data from a vehicle sensor system 128 and generate a parking space location based on the vehicle location data.

[0049] The charging device guidance system 110 is configured to determine charging device locations 204, 206 of the charging device 202 accessed by a user for charging the autonomous vehicle 100. In an embodiment, the charging device guidance system 110 is configured to receive user location data from the vehicle sensor system 128 associated with the user's movement from the autonomous vehicle 100 to the charging device locations 204, 206 of the charging device 202 and at the charging device 202. The charging device guidance system 110 is configured to generate an observed user velocity sequence associated with the user location data. The charging device guidance system 110 is configured to generate a user state sequence associated with the observed user velocity sequence using a Viterbi algorithm combined with a hidden Markov model of the user state. The charging device guidance system 110 is configured to determine the charging device locations 204, 206 based on the correlation between the user state in the user state sequence and the user location data.

[0050] The charging device guidance system 110 is configured to determine the charging device status of a user-accessed charging device 202 to charge the autonomous vehicle 100 based on the charging rate associated with the charging device 202. The charging device guidance system 110 is configured to upload parking space location, charging device locations 204 and 206 of the user-accessed charging device 202, and the charging device status of the charging device 202 to the edge computing system 150. In an embodiment, the charging device guidance system 110 is configured to upload the vehicle identification number (VIN), vehicle model, charging start time, charging end time, parking space location, charging station identifier, parking space identifier, charging device locations 204 and 206, average charging rate, minimum charging rate, maximum charging rate, and charging device status to the edge computing system 150. Data uploaded from the autonomous vehicle's charging device guidance system 110 to the edge computing system 150 can be referred to as charging session data.

[0051] Although it has been stated that the user of the autonomous vehicle 100 parked in parking space 200 may use two charging devices 202, in an alternative embodiment, the user of the autonomous vehicle 100 parked in parking space 200 may use a greater number of charging devices 202.

[0052] refer to Figure 3This diagram illustrates a functional block diagram representation of multiple autonomous vehicles 100, including a charging device guidance system 110 communicatively coupled to an edge computing system 150. The charging device guidance system 110 for each of the multiple autonomous vehicles 100, represented by group 300, is configured to upload parking space locations, charging device locations 204 and 206 of charging devices 202 accessed by users of the autonomous vehicle 100, and the charging device status of the charging devices 202 to the edge computing system 150. In this embodiment, the charging device guidance system 110 for each of the multiple autonomous vehicles 100, represented by group 300, is configured to upload vehicle identification number (VIN), vehicle model, charging start time, charging end time, parking space location, charging station identifier, parking space identifier, charging device locations 204 and 206, average charging rate, minimum charging rate, maximum charging rate, and charging device status to the edge computing system 150. The data uploaded from the charging device guidance system 110 of the autonomous vehicles 100 to the edge computing system 150 can be referred to as charging session data.

[0053] In one embodiment, edge computing system 150 is configured to preprocess charging session data uploaded by each autonomous vehicle 100 in group 300. In another embodiment, edge computing system 150 is configured to preprocess the charging session data by classifying it in conjunction with associated charging devices 202. In yet another embodiment, edge computing system 150 is configured to preprocess the charging session data by classifying it in conjunction with different vehicle models.

[0054] In one embodiment, the edge computing system 150 is configured to store charging session data uploaded by each autonomous vehicle 100 in the group 300 in a two-dimensional table. The edge computing system 150 is configured to sort the charging session data, for example, by time, by charging station, and / or by vehicle model.

[0055] In one embodiment, the edge computing system 150 is configured to use a clustering algorithm to identify the number of charging devices 202 and the charging device locations 204, 206 associated with each charging device in the charging devices 202. In another embodiment, the edge computing system 150 is configured to use a time decay function to monitor the time-varying charging device state of each charging device in the charging devices 202.

[0056] In one embodiment, the edge computing system 150 is configured to store processing results associated with each charging device 202 in an edge computing database. Examples of processing results include, but are not limited to, charging device identifiers and charging device states. The edge computing system 150 is configured to provide guidance instructions to the charging device guidance system 110 of the autonomous vehicles 100 and 302 to charging device locations 204 and 206 of the charging devices 202, in part based on the charging device states of the charging devices 202. In another embodiment, the autonomous vehicles 100 and 302 are configured to request guidance from the edge computing system 150 to provide guidance instructions to operable charging devices 202 within a predetermined distance of the autonomous vehicles 100 and 302. The edge computing system 150 is configured to respond to the request by providing guidance instructions to the charging device guidance system 110 of the autonomous vehicles 100 and 302 to charging device locations 204 and 206 of the charging devices 202, based on the charging device locations 204 and 206 and the charging device states.

[0057] In one embodiment, the edge computing system 150 is configured to receive vehicle location data generated by the vehicle sensor system 128 from the autonomous vehicle 100 and generate parking space locations based on the received vehicle location data.

[0058] In one embodiment, the edge computing system 150 is configured to determine charging device locations 204, 206 of the charging device 202 accessed by the user to charge the autonomous vehicle 100. In another embodiment, the edge computing system 150 is configured to receive user location data generated by the vehicle sensor system 128 of the autonomous vehicle 100, associated with the user's movement from the autonomous vehicle 100 toward the charging device locations 204, 206 of the charging device 202, and movement at those locations. The edge computing system 150 is configured to generate an observed user velocity sequence associated with the user location data. The edge computing system 150 is configured to generate a user state sequence associated with the observed user velocity sequence using a Viterbi algorithm combined with a hidden Markov model of the user state. The edge computing system 150 is configured to determine the charging device locations 204, 206 based on the correlation between the user state in the user state sequence and the user location data. In one embodiment, the edge computing system 150 is configured to determine the charging device status of the charging device 202 accessed by the user in order to charge the autonomous vehicle 100 based on the charging rate associated with the charging device 202.

[0059] Edge computing system 150 can utilize crowdsourced data associated with charging at charging station 202 for autonomous vehicles 100 to create a map of autonomous vehicle charging stations. Crowdsourced data may include the charging station status, charging rate, and location of charging station 202. Edge computing system 150 can use data aggregation algorithms to aggregate charging session data uploaded by each autonomous vehicle 100. The use of data aggregation algorithms can reduce sensor errors and improve system reliability. Edge computing system 150 can identify non-operating charging stations 202 and monitor whether non-operating charging stations 202 have been repaired. Different autonomous vehicles 100 parked in the same parking space can report slightly different charging station locations associated with charging station 202. Clustering algorithms, such as centroid-based or density-based clustering algorithms, can be used by edge computing system 150 to determine the number and location of charging stations.

[0060] refer to Figure 4 The diagram illustrates a functional block diagram representation of an embodiment of the charging device guidance system 110. The charging device guidance system 110 is configured to upload charging session data associated with the autonomous vehicle 100 charging at the charging device 202 to an edge computing system 150. The charging device guidance system 110 is configured to receive guidance instructions from the edge computing system 150 for an operable charging device 202 within a predetermined distance of the autonomous vehicle 100.

[0061] The charging device guidance system 110 is configured to communicatively couple to the vehicle sensor system 128 and the vehicle communication system 136. The vehicle communication system 136 is configured to communicatively couple to the edge computing system 150. The charging device guidance system 110 includes a controller 402. The controller 402 includes a processor 404 and a memory 406. In an embodiment, the memory 406 includes a parking space positioning module 408, a user speed sequence module 410, a user state sequence module 412, a charging device location module 414, a charging device state module 416, and a charging device guidance module 418. The charging device guidance system 110 may include additional components that facilitate its operation.

[0062] refer to Figure 5 A flowchart illustrating an example of a method 500 for determining charging device locations 204, 206 of charging device 202 using an embodiment of charging device guidance system 100 is shown. Method 500 is performed by an embodiment of charging device guidance system 110. In embodiments, method 500 may be performed by charging device guidance system 110 in conjunction with other components of autonomous vehicle 100. Method 500 may be performed by hardware circuitry, firmware, software, and / or combinations thereof.

[0063] At position 502, the parking space positioning module 408 receives vehicle location data from the vehicle sensor system 128 of the autonomous vehicle 100 parked in a charging station parking space. The vehicle sensor system 128 includes one or more vehicle sensors 140a-140n. Examples of vehicle sensors 140a-140n include, but are not limited to, radar, lidar, global positioning system (GPS), optical cameras, thermal imagers, ultrasonic sensors, and / or other sensors. In this embodiment, the vehicle location data is generated by GPS.

[0064] At position 504, the parking space location module 408 determines the parking space location based on vehicle location data. In this embodiment, the parking space location module 408 is configured to determine the parking space location based on vehicle location data generated by GPS. In this embodiment, the autonomous vehicle 100 is equipped with a high-definition (HD) map. The parking space location module 408 is configured to map the vehicle location data onto the HD map to determine the parking space location.

[0065] At 506, the user velocity sequence module 410 receives user location data generated by the vehicle sensor system 128. In this embodiment, the vehicle sensor system 128 includes a surround-view camera system. The surround-view camera system is configured to acquire and generate user location data associated with user movement when a user of the autonomous vehicle 100 walks to and stops at charging device locations 204, 206 of the charging device 202 to initiate charging of the autonomous vehicle. In this embodiment, an optical flow algorithm is used to generate the user location data.

[0066] In one embodiment, the vehicle sensor system 128 includes a wireless positioning sensor system. The wireless positioning sensor system is configured to collect and generate user location data associated with user movement by tracking the location of a user's smartphone when a user of the autonomous vehicle 100 walks to and stops at charging device locations 204, 206 of the charging device 202. In another embodiment, the wireless positioning sensor system includes one or more wireless positioning devices. Examples of wireless positioning devices include, but are not limited to, Wi-Fi applications and ultra-wideband (UWB) sensors installed on the autonomous vehicle 100.

[0067] In one embodiment, the vehicle sensor system 128 includes a surround-view camera system and a wireless positioning sensor system. The surround-view camera system and the wireless positioning sensor system are configured to collect and generate user location data associated with user movement when a user of the autonomous vehicle 100 walks toward and stops at charging device locations 204, 206 of the charging device 202.

[0068] At 508, the user velocity sequence module 410 generates an observed user velocity sequence based on user location data. The observed user velocity sequence is associated with user movement as the user walks to and stops at charging device locations 204, 206 of charging device 202 to initiate charging of autonomous vehicle 100.

[0069] At point 510, the user state sequence module 412 generates a user state sequence based on the observed user velocity sequence. The user state is either a walking state or a charging device state. The user is in a walking state when walking towards charging device positions 204 and 206 of charging device 202, and in a charging device state when stopping at charging device positions 204 and 206 of charging device 202. The user state is a hidden state. The user state sequence module 412 is configured to use the Viterbi algorithm combined with a hidden Markov model of the user state to generate a user state sequence associated with the observed user velocity sequence.

[0070] At 512, the charging device location module 414 determines the charging device locations 204 and 206 of the charging device 202 based on the user state sequence. The charging device location module 414 is configured to identify the charging device states in the user state sequence. The charging device location module 414 is configured to generate intermediate charging device locations associated with each identified charging device state based on the correlation between the charging device state and the user location data associated with that charging device. The charging device location module 414 is configured to determine the charging device locations 204 and 206 of the charging device 202 based on the average value of the intermediate charging device locations.

[0071] refer to Figure 6 This illustrates an example of a state graph associated with a user-state Hidden Markov Model (HMM). The HMM is defined based on the assumption that a hidden state exists for every observation. The user-state HMM assumes that a hidden user state exists for each observed user speed in the observed user speed sequence. Each observed user speed is based on user position data detected by the vehicle sensor system 128 of the autonomous vehicle 100.

[0072] The user-state Hidden Markov Model is defined based on two user states, X1 and X2. These two user states, X1 and X2, are hidden user states X1 and X2. The two hidden user states X1 and X2 are walking state X1 and charging device state X2. When the user walks towards charging device locations 204 and 206 of charging device 202, the user is in walking state X1, and when the user is already at charging device locations 204 and 206, the user is in charging device state X2. Initial state probabilities are assigned to each of the hidden user states X1 and X2. The initial state probability of walking state P(X1) indicates the probability that the user initially walks from autonomous vehicle 100 to charging device locations 204 and 206. The initial state probability of charging device state P(X2) is zero, indicating that the user is not initially at charging device locations 204 and 206.

[0073] State transition probability matrix A[a 11 ,a 12 ,a 21 ,a 22 This is associated with a hidden Markov model of user states. The first entry, a11, is the probability that the next user state will be walking state X1 if the current user state is walking state X1. The second entry, a12, is the probability that the next user state will be charging device state X2 if the current user state is walking state X1. The third entry, a21, is the probability that the next user state will be walking state X1 if the current user state is charging device state X2. The fourth entry, a22, is the probability that the next user state will be charging device state X2 if the current user state is charging device state X2. A training dataset is used to train the state transition probability matrix A. In this embodiment, the training dataset is a historical dataset.

[0074] The probability of an observation depends on the hidden state that produces the observation. An observation is the observed user speed. A hidden state is a user state. The emission probability defines the probability that the observed user speed will occur within the hidden user state. For example, first graph 602 shows an example of a continuous probability distribution of observed user speeds associated with walking state X1, and second graph 604 shows an example of a continuous probability distribution of observed user speeds associated with charging device state X2. A training dataset is used to train the emission probability. In this embodiment, the training dataset is a historical dataset.

[0075] refer to Figure 7 The diagram illustrates a block diagram representation of an embodiment of the user state sequence module 412. The user state sequence module 412 includes an observed data module 702, a user state hidden Markov model 704, a Viterbi algorithm module 706, and a user state optimal sequence module 708. The user state sequence module 412 may include additional components that facilitate the operation of the user state module 214.

[0076] The observation data module 702 is configured to receive the observed user speed sequence generated by the user speed sequence module 410. The user state hidden Markov model 704 is defined based on the assumption that a hidden user state exists for each observed user speed. Each observed user speed in the observed user speed sequence is based on user position data detected by the vehicle sensor system 128 of the autonomous vehicle 100. The Viterbi algorithm module 706 receives the observed user speed sequence from the observation data module 702 and generates an optimal sequence of user states based on the observed user speed sequence according to the user state hidden Markov model. The optimal sequence of user states is received by the optimal sequence of user states module 708. The user state sequence module 412 is configured to provide the optimal sequence of user states to the charging device location module 414.

[0077] refer to Figure 8 The diagram illustrates an example of a method 800 for determining the charging device state of a charging device 202 using an embodiment of a charging device guidance system 110. Method 800 is performed by the charging device guidance system 110. Method 800 can be performed by the charging device guidance system 110 in conjunction with other components of the autonomous vehicle 100. Method 800 can be performed by hardware circuitry, firmware, software, and / or combinations thereof.

[0078] The charging device guidance system 110 is configured to determine the charging device status of a user-accessed charging device 202 based on one or more charging device parameters to charge the autonomous vehicle 100. In an embodiment, the charging device guidance system 110 is configured to determine the charging device status of the charging device 202 based on the charging rate associated with the charging device 202.

[0079] At 802, the charging device status module 416 receives an observed charging rate associated with the charging of the autonomous vehicle 100 at the charging device 202. In this embodiment, the observed charging rate is received in kilowatt-hours. At 804, the charging device status module 416 generates an observed charging rate sequence based on the observed charging rate.

[0080] At 806, the charging device state module 416 generates a charging device state sequence based on the observed charging rate sequence. The charging device state is one of an active state and a deactivated state. The charging device 202 is in an active state when it is operational and in a deactivated state when it is not operational. The charging device state is a hidden state. The charging device state module 416 is configured to use a Viterbi algorithm combined with a hidden Markov model of the charging device state to generate the charging device state sequence associated with the observed charging rate sequence. At 808, the charging device guidance system 110 generates the charging device state associated with the charging device based on the charging device state sequence. The charging device state is one of an active state and a deactivated state. When the charging device 202 is in an active state, the charging device 202 is an operational charging device 202. When the charging device 202 is in a deactivated state, the charging device 202 is a non-operational charging device 202.

[0081] The charging device guidance module 418 is configured to request a guidance instruction from the edge computing system 150 to an operable charging device 202 within a predetermined distance of the autonomous vehicle 100. The edge computing system 150 is configured to respond to the request by providing guidance instructions to charging device locations 204, 206 of the operable charging device 202. The autonomous vehicle 100's ADS performs one or more actions based on the guidance instructions to guide the autonomous vehicle 100 to the operable charging device 202. The edge computing system 150 identifies the operable charging device 202 based on charging device locations 204, 206 and the charging device status of the charging device 202 stored at the edge computing system 150.

[0082] refer to Figure 9 This example illustrates a state graph associated with a hidden Markov model of charging device states. Hidden Markov models are defined based on the assumption that a hidden state exists for every observation. The charging device state hidden Markov model assumes that a hidden charging device state exists for each observed charging rate in the observed charging rate sequence.

[0083] The hidden Markov model for the charging device state is defined based on two charging device states, CX1 and CX2. These two states, CX1 and CX2, are hidden states. The hidden states CX1 and CX2 represent the in-use state CX1 and the out-of-use state CX2. Initial state probabilities are assigned to each of the hidden states CX1 and CX2. The initial state probability of the in-use state P(CX1) is 0.5, indicating a 50% probability that the charging device 202 is initially in the in-use state. The initial state probability of the out-of-use state P(CX2) is also 0.5, indicating a 50% probability that the charging device 202 is initially in the out-of-use state.

[0084] State transition probability matrix B[b 11 ,b 12 ,b 21 ,b 22 This is associated with a Hidden Markov Model (HMM) of the charging device state. The first entry, b11, is the probability that the next charging device state will be CX1 if the current state is in use. The second entry, b12, is the probability that the next charging device state will be CX2 if the current state is CX1 and the next state is CX2 (disabled). The third entry, b21, is the probability that the next charging state will be CX1 if the current state is CX2 and the next state is CX2 (disabled). The fourth entry, b22, is the probability that the next charging device state will be CX2 (disabled). A training dataset is used to train the state transition probability matrix B. In this embodiment, the training dataset is a historical dataset.

[0085] The probability of an observation depends on the hidden state that produces the observation. An observation is the observed charging rate. A hidden state is the charging device state. The emission probability defines the probability that the observed charging rate will occur while the device is in a hidden state. For example, first graph 902 represents an example of a continuous probability distribution of the observed charging rate associated with the in-use state CX1, and second graph 904 represents an example of a continuous probability distribution of the observed charging rate associated with the out-of-use state CX2. A training dataset is used to train the emission probability. In this embodiment, the training dataset is a historical dataset.

[0086] The Hidden Markov Model (HMM) for the charging device state is defined based on the assumption that a hidden charging device state exists for every observed charging rate. The Viterbi algorithm receives the observed charging rate sequence and generates an optimal sequence of charging device states based on the observed charging rate sequence using the HMM. The charging device state associated with the charging device is based on this optimal sequence of states. The charging device state is either in use or out of use. When charging device 202 is in use, it is an operational charging device. When charging device 202 is out of use, it is an inoperable charging device.

[0087] While an example of a hidden Markov model of the charging device state based on the observed charging rate of the charging device 202 has been described, alternative embodiments may include a hidden Markov model of the charging device state based on other observed charging device parameters associated with the charging device 202. For example, an observed sequence of charging device states may be used to define the hidden Markov model of the charging device state.

[0088] refer to Figure 10This illustrates an example of a method 100 for providing guidance instructions to an operable charging device 202 using an embodiment of a charging device guidance system 110. Method 1000 is performed by the charging device guidance system 110. Method 1000 can be performed by the charging device guidance system 110 in conjunction with other components of the autonomous vehicle 100 and / or the edge computing system 150. Method 1000 can be performed by hardware circuitry, firmware, software, and / or a combination thereof.

[0089] At 1002, the charging device guidance system 110 receives a sequence of user states associated with the user of the first autonomous vehicle 100. Each user state is either a walking state or a charging device state. The user state sequence is based on an observed user speed sequence associated with detected user location data, which is related to the user's movement from the first autonomous vehicle 100 to and from the charging device 202. At 1004, the charging device locations 204 and 206 of the charging device 202 are determined based on the correlation between the charging device states in the user state sequence and the user location data at the charging device guidance system 110. At 1006, the charging device guidance system 110 uploads the charging device locations 204 and 206 associated with the charging device 202 to an edge computing system 150, which is configured to provide guidance instructions to the second autonomous vehicle 100 for the charging device 202, at least in part, based on the charging device locations 204 and 206.

[0090] The charging device guidance system 110 enables users of autonomous vehicle 100 to charge autonomous vehicle 100 using an operational charging device 202 without having to travel to multiple charging devices 202 to find an operational one.

[0091] While at least one exemplary embodiment has been presented in the foregoing detailed descriptions, it should be understood that numerous variations exist. It should also be understood that one or more exemplary embodiments are merely examples and are not intended to limit the scope, applicability, or configuration of this disclosure in any way. Rather, the foregoing detailed descriptions will provide those skilled in the art with a convenient roadmap for implementing one or more exemplary embodiments. It should be understood that various changes can be made to the function and arrangement of the elements without departing from the scope of this disclosure as set forth in the appended claims and their legal equivalents.

Claims

1. A charging device guidance system for autonomous vehicles, the charging device guidance system comprising: processor; as well as The memory includes instructions that, when executed by the processor, cause the processor to: Receive a sequence of user states associated with a user of the first autonomous vehicle, each user state being either a walking state or a charging device state, and the sequence of user states is based on an observed sequence of user speeds associated with detected user location data, which is associated with the user's movement from the first autonomous vehicle to the charging device and at the charging device. The location of the charging device is determined based on the correlation between the charging device status in the user state sequence and the user location data. as well as The location of the charging device associated with the charging device is uploaded to an edge computing system, which is configured to provide guidance instructions to the second autonomous vehicle, at least in part, based on the location of the charging device, to guide the second autonomous vehicle to an operational charging device.

2. The system according to claim 1, wherein, The detected user location data is detected by at least one of the surround-view camera system and the wireless positioning sensor system of the first autonomous vehicle.

3. The system according to claim 1, wherein, The memory includes further instructions that, when executed by the processor, cause the processor to determine the parking space location associated with the charging device based in part on vehicle location data received from the vehicle sensor system of the first autonomous vehicle.

4. The system according to claim 1, wherein, The memory includes further instructions that, when executed by the processor, cause the processor to use the Viterbi algorithm in conjunction with a hidden Markov model of user states to generate a sequence of user states associated with the observed user velocity sequence, wherein the user states are hidden states.

5. The system according to claim 1, wherein, The memory includes further instructions that, when executed by the processor, cause the processor to: Based on the user location data corresponding to at least two charging device states in the user state sequence, at least two intermediate charging device locations are generated; and The charging device position is determined based on the average value of the at least two intermediate charging device positions.

6. The system according to claim 1, wherein, The memory includes further instructions that, when executed by the processor, cause the processor to: Receive a sequence of charging device states associated with the charging device, each of the charging device states being either an active state or a deactivated state, and the sequence of charging device states is based on an observed sequence of charging rates associated with the charging device. as well as The charging device state is determined based on the charging device state sequence.

7. The system according to claim 6, wherein, The memory includes further instructions that, when executed by the processor, cause the processor to upload the charging device status associated with the charging device to the edge computing system, which is configured to provide guidance instructions to the second autonomous vehicle in part based on the charging device status, to guide the second autonomous vehicle to an operational charging device.

8. The system according to claim 6, wherein, The memory includes further instructions that, when executed by the processor, cause the processor to use the Viterbi algorithm in conjunction with a hidden Markov model of the charging device state to generate a sequence of charging device states associated with the observed charging rate sequence, wherein the charging device states are hidden states.

9. A computer-readable medium comprising instructions stored thereon for providing guidance instructions to an autonomous vehicle, the instructions, when executed by a processor, causing the processor to: Receive a sequence of user states associated with a user of the first autonomous vehicle, each user state being either a walking state or a charging device state, and the sequence of user states is based on an observed sequence of user speeds associated with detected user location data, which is associated with the user's movement from the first autonomous vehicle to the charging device and at the charging device. The location of the charging device is determined based on the correlation between the charging device status in the user state sequence and the user location data. as well as The location of the charging device associated with the charging device is uploaded to an edge computing system, which is configured to provide guidance instructions to the second autonomous vehicle, at least in part, based on the location of the charging device, to guide the second autonomous vehicle to an operational charging device.

10. The computer-readable medium of claim 9, further comprising instructions that cause the processor to receive the detected user location data from at least one of the surround-view camera system and the wireless positioning sensor system of the first autonomous vehicle's vehicle sensor system.

Images