System for guiding an autonomous vehicle by a tow taxi

Abstract

An autonomous driving system for an autonomous vehicle, comprising an autonomous driving controller wirelessly connected to a tow taxi. The autonomous driving controller determines that the autonomous driving system is inoperative. In response to determining that the autonomous driving system is inoperative, the autonomous driving controller generates a notification indicating that the autonomous driving system is inoperative. The autonomous driving controller receives a current data string from the tow taxi, the current data string including data points corresponding to the current time point and predicted data points for each of one or more future prediction time points. The current data string is compared with a previous data string recorded at a previous time point. In response to determining that the current data string matches the previous data string, the autonomous driving controller determines one or more driving maneuvers for the autonomous vehicle based on the current data string.

Description

Technical Field

[0001] The present disclosure relates to an autonomous vehicle guided by a tow taxi. More specifically, the present disclosure relates to an autonomous vehicle guided by a tow taxi in a situation where the autonomous driving system is non-functional. Background Art

[0002] Autonomous vehicles can use a variety of different on-vehicle technologies and sensors to travel from a starting point to a predetermined destination with limited or no human intervention. Autonomous vehicles include various autonomous sensors for detecting the external environment and state of the vehicle, such as but not limited to: cameras, acoustic sensors, radars, lidars, global positioning systems (GPS), and inertial measurement units (IMU). The on-vehicle controller of the vehicle determines an appropriate driving route based on the destination input by the user and in combination with the information collected by the various autonomous sensors.

[0003] Sometimes problems may occur in the hardware or software of the vehicle, causing the autonomous system to be non-functional and no longer able to drive the vehicle to the destination indicated by the vehicle user. For example, a hardware failure may occur when one of the vehicle sensors, such as a lidar, is damaged. Alternatively, a software failure (e.g., a failure in the planning algorithm) may cause the on-vehicle controller to no longer be able to guide the vehicle to the destination. It should be understood that although the autonomous system is non-functional, other vehicle components, such as the propulsion system or chassis system of the autonomous vehicle, may still operate. In other words, the motor and drivetrain components that propel the autonomous vehicle are still operating; however, the system that manages the autonomous operation cannot guide the vehicle. Although the propulsion components are operating, the autonomous vehicle can no longer travel to the destination input by the vehicle user.

[0004] Therefore, although current autonomous vehicles achieve their intended purpose, there is a need in the art for an improved system that allows an autonomous vehicle to continue traveling even when there are problems with one or more of the autonomous sensors or autonomous vehicle algorithms. Summary of the Invention

[0005] According to several aspects, a self-driving system for an autonomous vehicle is disclosed. The self-driving system includes an autonomous driving controller that is wirelessly connected to a tow taxi, and when the self-driving system is inoperative, the tow taxi guides the autonomous vehicle. The autonomous driving controller determines that the self-driving system is inoperative according to an instruction. In response to determining that the self-driving system is inoperative, the autonomous driving controller generates a notification indicating that the self-driving system is inoperative, where the notification causes the tow taxi to be dispatched to the geographical location of the autonomous vehicle. The autonomous driving controller receives a current data string from the tow taxi, and the current data string includes data points corresponding to the current time point and predicted data points for each of one or more future prediction time points. The autonomous driving controller compares the current data string with a previous data string recorded at a previous time point that occurred immediately before the current time point. Finally, in response to determining that the current data string matches the previous data string, the autonomous driving controller determines one or more driving maneuvers for the autonomous vehicle based on the current data string.

[0006] In another aspect, the data points corresponding to the current time point and the predicted data points for each of one or more future prediction time points are represented by a final command determined by the tow taxi.

[0007] In yet another aspect, the final command represents the driver input position of the autonomous vehicle.

[0008] In yet another aspect, the driver input position includes an accelerator pedal position, a brake pedal position, and a steering wheel angle position.

[0009] In another aspect, the final command represents a reference trajectory set point of the autonomous vehicle.

[0010] In yet another aspect, the reference trajectory set point includes a speed trajectory point or a heading angle trajectory point of the autonomous vehicle.

[0011] In yet another aspect, the final command represents the target of the autonomous vehicle.

[0012] In one aspect, the data points corresponding to the current time point and the predicted data points for each of one or more future prediction time points are represented by sensed data determined by the tow taxi.

[0013] In another aspect, the autonomous driving controller executes an instruction to transmit driving restrictions and a request for specifying a required data type to the tow taxi, and the tow taxi transmits the sensed data in response to receiving the driving restrictions and the request for specifying the data type.

[0014] In yet another aspect, the autonomous driving controller communicates wirelessly with a back-end system including a back-end facility.

[0015] In yet another aspect, a notification indicating that the autonomous driving system is inoperative is transmitted to a back-end facility of a back-end system.

[0016] In another aspect, the autonomous vehicle includes a plurality of on-vehicle autonomous sensors that are in electronic communication with an autonomous driving controller.

[0017] In yet another aspect, a failure of at least one of the autonomous driving controller and the plurality of on-vehicle autonomous sensors causes the autonomous driving system to be inoperative.

[0018] In yet another aspect, the plurality of on-vehicle autonomous sensors includes at least one of the following: one or more cameras, one or more radars, an inertial measurement unit (IMU), a global positioning system (GPS), and one or more lidars.

[0019] In another aspect, the autonomous driving controller executes instructions to repeatedly receive a predicted rolling horizon data set from a lead taxi, where the predicted rolling horizon data set includes at least one of the following: future command predictions and perception data predictions.

[0020] In yet another aspect, the autonomous driving controller executes instructions to determine that data loss has occurred between the autonomous driving controller and the lead taxi, and in response, determines one or more driving maneuvers based on data included in a previous data string.

[0021] In yet another aspect, data loss occurs when a particular data string at a current time point is missing and not transmitted from the lead taxi to the autonomous driving controller.

[0022] In one aspect, an autonomous driving system for an autonomous vehicle is disclosed. The autonomous driving system includes a plurality of on-vehicle autonomous sensors that sense data related to the operation of the autonomous vehicle and the surrounding environment. The autonomous driving system also includes an autonomous driving controller that is in electronic communication with the plurality of on-vehicle autonomous sensors and is wirelessly connected to a tow taxi that guides the autonomous vehicle when the autonomous driving system is inoperative. The autonomous driving controller determines that the autonomous driving system is inoperative according to an instruction. In response to determining that the autonomous driving system is inoperative, the autonomous driving controller generates a notification indicating that the autonomous driving system is inoperative, wherein the notification causes the tow taxi to be dispatched to the geographical location where the autonomous vehicle is located. The autonomous driving controller sends a raw sensor data request to the tow taxi and compares the raw sensor data received from the tow taxi with the data collected from the plurality of on-vehicle autonomous sensors that are still operating. The autonomous driving controller determines that the raw sensor data received from the tow taxi matches the data collected from the plurality of on-vehicle autonomous sensors that are still operating. In response to determining that the raw sensor data received from the tow taxi matches the data collected from the plurality of on-vehicle autonomous sensors that are still operating, the autonomous driving controller determines one or more driving maneuvers based on the raw sensor data received from the tow taxi.

[0023] In one aspect, the raw sensor data received from the tow taxi includes one or more of the following: image data, signals from a radar, data from an IMU, GPS coordinates, and signals from a lidar.

[0024] In another aspect, a non-transitory computer-readable storage medium is disclosed that is readable by a processing circuit and stores instructions that, when executed by the processing circuit, implement method operations. The method includes determining that an autonomous driving system is inoperative, wherein the autonomous driving system is for an autonomous vehicle. In response to determining that the autonomous driving system is inoperative, the method includes generating a notification indicating that the autonomous driving system is inoperative. The notification causes the tow taxi to be dispatched to the geographical location of the autonomous vehicle. The method also includes receiving a current data string from the tow taxi, the current data string including data points corresponding to a current time point and predicted data points for each of one or more future prediction time points. The method also includes comparing the current data string with a previous data string recorded at a previous time point immediately preceding the current time point. Finally, in response to determining that the current data string matches the previous data string, the method includes determining one or more driving maneuvers for the autonomous vehicle based on the current data string.

[0025] From the description provided herein, further applicable fields will become apparent. It should be understood that the description and specific examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Description of the Drawings

[0026] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way.

[0027] Figure 1 is a schematic diagram of an autonomous vehicle including an autonomous driving controller that wirelessly communicates with a tow taxi and a back-end system according to an exemplary embodiment;

[0028] Figure 2 is of a tow taxi positioned relative to the autonomous vehicle according to an exemplary embodiment Figure 1 as shown in;

[0029] Figure 3 is a schematic diagram illustrating a tow controller that electronically communicates with the autonomous driving controller of the autonomous vehicle according to an exemplary embodiment;

[0030] Figure 4 illustrates a graph including a current data string plotted relative to a previous data string according to an exemplary embodiment;

[0031] Figure 5 is a process flow diagram illustrating a method for guiding an autonomous vehicle based on a centralized method according to an exemplary embodiment;

[0032] Figure 6 is a process flow diagram illustrating a method for guiding an autonomous vehicle based on a projection method according to an exemplary embodiment; and

[0033] Figure 7 illustrates a computer program product including one or more storage media according to an exemplary embodiment. Detailed Description

[0034] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0035] Reference Figure 1, an exemplary autonomous vehicle 10 that communicates wirelessly with a tow taxi 12 is illustrated. The autonomous vehicle 10 can be any type of vehicle, such as, but not limited to, a sedan, a truck, a sport utility vehicle, a van, or a recreational vehicle. In one non-limiting embodiment, the autonomous vehicle 10 is a fully autonomous vehicle that includes an autonomous driving system (ADS) for performing all driving tasks. Alternatively, in another embodiment, the autonomous vehicle 10 is a semi-autonomous vehicle that includes an advanced driver assistance system (ADAS) for assisting a driver with steering, braking, and / or accelerating. The autonomous vehicle 10 has an autonomous driving system 14 that includes an autonomous driving controller 20. The autonomous driving system 14 also includes a plurality of on-vehicle autonomous sensors 22, a plurality of vehicle systems 24, and an antenna 26; all of which are in electronic communication with the autonomous driving controller 20. The antenna 26 wirelessly connects the autonomous driving controller 20 to a satellite 27 that is part of a back-end system 28 and a guidance system 30 that is part of the tow taxi 12.

[0036] As described below, in the event that the autonomous driving controller 20 becomes inoperative, the tow taxi 12 guides the autonomous vehicle 10. Specifically, in the event that either the autonomous driving controller 20 or one of the on-vehicle autonomous sensors 22 fails, rendering the autonomous driving system 14 inoperative, the tow taxi 12 provides guidance. When inoperative, the autonomous driving system 14 cannot drive the autonomous vehicle 10 to a predetermined location. Also as described below, the tow taxi 12 can employ a centralized method or a projection method to guide the autonomous vehicle 10. Specifically, the centralized method for guiding the autonomous vehicle 10 includes transmitting a final command to the autonomous driving controller 20. In contrast, the projection-based method includes transmitting raw sensor data or perception data to the autonomous driving controller 20. The autonomous driving controller 20 then determines the final command based on the raw sensor data or perception data received from the tow taxi 12.

[0037] The autonomous driving controller 20 determines autonomous driving characteristics of the autonomous vehicle 10, such as perception, planning, localization, mapping, and control. Although Figure 1 the autonomous driving controller 20 is illustrated as a single controller, it should be understood that multiple controllers can also be included. The plurality of on-vehicle autonomous sensors 22 sense data related to the operation and surrounding environment of the autonomous vehicle 10, and this data is sent to the autonomous driving controller 20. The plurality of on-vehicle autonomous sensors 22 includes one or more cameras 32, radar 34, an inertial measurement unit (IMU) 36, a global positioning system (GPS) 38, and lidar 40; however, it should be understood that additional sensors can also be used.

[0038] The plurality of vehicle systems 24 includes, but is not limited to, a braking system 50, a steering system 52, a power system 54, and a suspension system 56. The autonomous controller 20 sends vehicle control commands to the plurality of vehicle systems 24 to guide the autonomous vehicle 10 to a predetermined destination. For example, a user of the autonomous vehicle 10 may use an input device 58 that is in electronic communication with the autonomous controller 20 to input a predetermined destination. In one embodiment, the input device 58 may be a keyboard.

[0039] In Figure 1 the example shown, the tow taxi 12 is an automobile. However, it should be understood that Figure 1 merely exemplary in nature, the tow taxi 12 is any type of land-based or air-based vehicle, such as, but not limited to, a truck, a van, or a drone (UAV). Now referring to Figure 2 , the autonomous vehicle 10 is positioned along a road 60. The tow taxi 12 is positioned along the road 60 in front of the autonomous vehicle 10. If the tow taxi 12 is a land-based vehicle, the tow taxi 12 may be positioned along the road 60; or in an alternative, if the tow taxi 12 is an air-based vehicle, the tow taxi is positioned above the road 60.

[0040] As Figure 2 seen, the guidance system 30 of the tow taxi 12 includes: a tow controller 62 that is in electronic communication with an antenna 64; and a plurality of autonomous sensors 66 that sense data related to the operation of the tow taxi 12 and the surrounding environment. The antenna 64 wirelessly connects the tow controller 62 of the tow taxi 12 to a satellite 27 of the back-end system 28 and the autonomous controller 20 of the autonomous vehicle 10. The plurality of autonomous sensors 66 includes, for example, one or more cameras 72, radar 74, an IMU 76, a GPS 78, and lidar 80; however, it should be understood that additional sensors may also be used. As described below, the data collected by the plurality of autonomous sensors 66 is processed by the tow controller 62 and may be sent as a final command to the autonomous controller 20 of the autonomous vehicle 10. In an alternative, the data collected by the plurality of autonomous sensors 66 is transmitted to the autonomous controller 20 as raw sensor data or perception data.

[0041] Continuing to refer to Figure 2, the back-end system 28 includes a satellite 27 and back-end facilities 82. The back-end facilities 82 can be, for example, a data center equipped with on-site personnel. The back-end facilities 82 receive, via the satellite 27, a notification from the autonomous driving controller 20 of the autonomous vehicle 10 indicating that the autonomous driving system 14 cannot guide the autonomous vehicle 10. The notification generated by the autonomous driving controller 20 includes information such as, but not limited to: original trip information, fault codes, passenger information, available autonomous sensor data, and vehicle limitations. Some examples of passenger information include: the number of passengers, their respective destinations, preferences such as arrival times, and road types (e.g., highways or toll roads). An example of a vehicle limitation includes speed. The autonomous driving system 14 may not be able to guide the autonomous vehicle 10 in the case where one or more of the on-vehicle autonomous sensors 22 of the autonomous vehicle 10 are not functioning and / or if a software fault occurs in the autonomous driving controller 20 such that the autonomous driving system 14 can no longer guide the autonomous vehicle 10 to the destination indicated by the vehicle passengers.

[0042] In response to receiving the notification from the autonomous driving controller 20, the back-end facilities 82 dispatch a tow taxi 12 to the geographical location where the autonomous vehicle 10 is located. The back-end facilities 82 also send a message to the autonomous driving controller 20 that includes information about the tow taxi 12. The message includes information such as, but not limited to: tow taxi description, specific towing mechanism (i.e., space-based or land-based), and updated destination. For example, the updated destination can be a repair facility. The back-end facilities 82 also send a message such as a security code to establish a communication link 84 between the autonomous driving controller 20 of the autonomous vehicle 10 and the tow controller 62.

[0043] Figure 3 is a schematic diagram of the autonomous driving controller 20 of the autonomous vehicle 10 wirelessly communicating with the tow controller 62 of the tow taxi 12 via the communication link 84. As described below, the tow controller 62 transmits a final command to the autonomous driving controller 20 of the autonomous vehicle 10 or, in an alternative, transmits original sensor data or perception data to the autonomous driving controller 20 of the autonomous vehicle 10. Based on the final command or the sensor and perception data received from the tow controller 62, the autonomous driving controller 20 sends vehicle control commands to a plurality of vehicle systems 24, and the vehicle control commands guide the autonomous vehicle 10 along the road 60 (see Figure 2 ). The autonomous driving controller 20 also transmits a real-time feedback signal to the tow controller 62 of the tow taxi 12 via the communication link 84. Some examples of the information included in the real-time feedback signal include, but are not limited to: available data collected by a plurality of on-vehicle autonomous sensors 22 in operation, communication status (i.e., whether the data received from the tow taxi 12 is received, partially received, or lost), passenger feedback, and biometric information.

[0044] In Figure 3 the illustrated embodiment, the autonomous driving controller 20 includes: a vehicle health monitoring module 90, a notification module 92, a request module 94, a receding horizon monitoring module 96, a verification module 98, and a driving module 100. The vehicle health monitoring module 90 determines that one or more hardware or software failures have occurred within the autonomous driving system 14, resulting in the inoperability of the autonomous driving system 14. The notification module 92 generates a notification indicating the inoperability of the autonomous driving system 14, and the notification is transmitted to the back-end facility 82 via the satellite 27. The notification causes the back-end system 28 to dispatch the tow taxi 12 to the geographical location where the autonomous vehicle 10 is located. The request module 94 of the autonomous driving controller 20 sends one or more requests to the tow controller 62 of the tow taxi 12 via the communication link 84 to request data.

[0045] The receding horizon monitoring module 96 of the autonomous driving controller 20 repeatedly receives the predicted receding horizon data set from the tow taxi 12. Specifically, the predicted receding horizon data set includes predictions of future commands such as dynamic object positions or perception data, and is determined based on data collected by a plurality of autonomous sensors 66 as part of the tow taxi 12 and transmitted via the communication link 84. If the tow taxi 12 adopts a centralized method to guide the autonomous vehicle 10, the tow controller 62 of the tow taxi 12 calculates a final command indicating the final trajectory of the autonomous vehicle 10 based on the data collected by the plurality of autonomous sensors 66. Referring to Figure 3 and Figure 4 , the tow controller 62 calculates the current data string 110, which includes: a data point at the current time point, denoted as t0; and predicted data points at one or more future prediction time points, illustrated in Figure 4 as the shaded area 112 spanning from t0 to t n-1 . Specifically, as Figure 4 illustrated, the one or more future prediction time points are denoted as t n-3 , t n-2 and t n-1 ; however, it should be understood that Figure 4 this is merely exemplary in nature, and more than three future prediction time points may also be used.

[0046] Continuing to refer to Figure 3 and Figure 4, the receding horizon monitoring module 96 receives the current data string 110 as input. The current data string 110 includes data points corresponding to the current time point and predicted data points for each of one or more future prediction time points. Specifically, when using a centralized approach to guide the autonomous vehicle 10, the data points correspond to the final commands determined by the traction controller 62 of the tow taxi 12. The receding horizon monitoring module 96 compares the current data string 110 with the previous data string 114 recorded at the previous time point t 0-1 occurring immediately before the current time point t0. In response to determining that the current data string 110 matches the previous data string 114, the receding horizon monitoring module 96 determines that the current data string 110 is valid, and the driving module 100 determines one or more driving maneuvers for the autonomous vehicle 10 based on the current data string 110, as described below. However, if the current data string 110 does not match the previous data string 114, the receding horizon monitoring module 96 determines that the current data string 110 is invalid, and the current data string 110 is discarded. However, in an embodiment, there may be an exception when the tow taxi 12 notifies the autonomous vehicle 10 that there has been a change in the data signal compared to the previous time point, and the autonomous vehicle 10 may accept the new data string regardless of the observable deviation.

[0047] It should be understood that when the data falls within a predetermined error range, the receding horizon monitoring module 96 determines that the current data string 110 and the previous data string 114 match each other. The predetermined error range takes into account data differences based on factors such as, but not limited to: sensor errors or relatively small modifications to the information used by the tow taxi 12. Additionally, in some cases, the receding horizon monitoring module 96 may determine that data loss has occurred between the autonomous driving controller 20 and the traction controller 62 of the tow taxi 12. Data loss occurs when a particular data string at the current time point is missing and not transmitted to the autonomous driving controller 20. For example, there may be an interruption in the communication link 84 between the autonomous vehicle 10 and the tow taxi 12. In response to determining that data loss has occurred, the autonomous driving controller 20 determines one or more driving maneuvers based on the data included in the previous data string 114.

[0048] Once the current data string 110 is verified, the verification module 98 selects a specific data point of the current data string 110 for use based on the timestamp. Then, the driving module 100 of the autonomous driving controller 20 determines one or more driving maneuvers based on the specific data type of the current data string 110. Specifically, whether the final command determined by the traction controller 62 of the tow taxi 12 represents the driver input position of the autonomous vehicle 10. In an embodiment, the driver input position includes: accelerator pedal position, brake pedal position, and steering wheel angle position. For example, in one embodiment, the driving module 100 can set the positions of the accelerator pedal and the steering wheel of the autonomous vehicle 10 based on the final command determined by the traction controller 62 of the tow taxi 12.

[0049] In another embodiment, the final command determined by the traction controller 62 of the tow taxi 12 includes the reference trajectory set points of the autonomous vehicle 10. In an embodiment, the reference trajectory set points include speed trajectory points and heading angle trajectory points. In yet another embodiment, the final command indicates the target of the autonomous vehicle 10, such as the target position, lane, speed, and distance from other vehicles on the road; and the driving module 100 executes a planning algorithm to determine the set points of the autonomous vehicle 10 based on the target.

[0050] As mentioned above, in another embodiment, the traction controller 62 of the taxi 12 employs a projection-based method instead of a centralized method. When the projection method is adopted, the autonomous driving controller 20 first transmits the driving restrictions to the traction controller 62 of the tow taxi 12 via the communication link 84. Some examples of driving restrictions include but are not limited to speed and acceleration. The autonomous driving controller 20 also sends a request for defining the required data type. Specifically, the autonomous driving controller 20 requests the raw sensor data or the perception data. In response to receiving the driving restrictions and the request for defining the required data type, the traction controller 62 transmits the raw sensor data or the perception data to the autonomous driving controller 20 of the autonomous vehicle 10 via the communication link 84, and the driving module 100 of the autonomous driving controller 20 executes the planning and control algorithms based on the raw sensor data or the perception data.

[0051] Some examples of the raw sensor data include but are not limited to: image data from the camera 72, signals from the radar 74, data from the IMU 76, GPS coordinates, or signals from the lidar 80. Specifically refer to Figure 3, if the traction controller 62 transmits the raw sensor data to the autonomous driving controller 20 of the autonomous vehicle 10, the rolling horizon monitoring module 96 can be omitted from the autonomous driving controller 20. Instead, the verification module 98 compares the raw sensor data received from the traction controller 62 of the tow taxi 12 with the data collected from the plurality of on-vehicle autonomous sensors 22 that are still operating. In the case where the raw sensor data collected from the tow taxi 12 matches the data collected from the plurality of on-vehicle autonomous sensors 22, the verification module 98 of the autonomous driving controller 20 determines that the raw sensor data is valid. In response to determining that the raw sensor data received from the tow taxi 12 is valid, the driving module 100 of the autonomous driving controller 20 determines one or more driving maneuvers based on the raw sensor data received from the tow taxi 12.

[0052] Alternatively, in another embodiment, a request sent from the autonomous driving controller 20 of the autonomous vehicle 10 to the traction controller 62 of the tow taxi 12 indicates a need for perception data. In response to receiving the request from the autonomous driving controller 20, the traction controller 62 transmits the perception data to the autonomous driving controller 20 via the communication link 84. The perception data indicates data regarding the surrounding environment, such as obstacles, lane markings, and their predictions.

[0053] Reference Figure 3 and Figure 4 , if the perception data is transmitted via the communication link 84, the rolling horizon monitoring module 96 receives the current data string 110 as an input, and the current data string 110 includes perception data points corresponding to the current time point and perception data points for each of one or more future prediction time points. The rolling horizon monitoring module 96 compares the current data string 110 with the previous data string 114 recorded at the previous time point t that occurred immediately before the current time point t0. In response to determining that the current data string 110 matches the previous data string 114, the rolling horizon monitoring module 96 determines that the current data string 110 is valid. In response to verifying that the current data string 110 is valid, the verification module 98 selects specific data points of the current data string 110 based on the time stamps for use. Then, the driving module 100 of the autonomous driving controller 20 determines one or more driving maneuvers based on the perception data points of the current data string 110 indicated by the time stamps. 0-1 is a process flow diagram illustrating a method 200 for guiding the autonomous vehicle 10 based on a centralized approach. Generally referring to

[0054] Figure 5 is a process flow diagram illustrating a method 200 for guiding the autonomous vehicle 10 based on a centralized approach. Generally referring to Figures 1 to 5 , the method 200 begins at block 202. At block 202, the vehicle health monitoring module 90 of the autonomous driving controller 20 ( Figure 3)It is determined that the autonomous driving system 14 is not functioning. Then, method 200 can proceed to block 204.

[0055] In block 204, in response to determining that the autonomous driving system 14 is not functioning, the notification module 92 of the autonomous driving controller 20 generates a notification indicating that the autonomous driving system 14 is not functioning. As mentioned above, the notification causes the tow taxi 12 to be dispatched to the geographical location of the autonomous vehicle 10. Then, method 200 can proceed to block 206.

[0056] In block 206, the autonomous driving controller 20 receives the current data string 110 ( Figure 4 ) from the tow taxi 12, where the current data string 110 includes data points corresponding to the current time point and predicted data points for each of one or more future prediction time points. Then, method 200 can proceed to block 208.

[0057] In block 208, the rolling horizon monitoring module 96 of the autonomous driving controller 20 (see Figure 3 ) compares the current data string 110 with the previous data string 114 ( 0-1 ) recorded at the previous time point t that occurred immediately before the current time point t0. Then, method 200 can proceed to block 210. Figure 4 ) is compared. Then, method 200 can proceed to block 210.

[0058] In block 210, in response to determining that the current data string 110 matches the previous data string 114 (see Figure 4 ), the driving module 100 of the autonomous driving controller 20 (see Figure 3 ) determines one or more driving maneuvers for the autonomous vehicle based on the current data string 110. Then, method 200 can end.

[0059] Figure 6 is a process flow diagram illustrating method 300 for guiding autonomous vehicle 10 based on a centralized approach. Generally referring to Figures 1 to 3 and Figure 6 , method 300 begins at block 302. In block 302, the vehicle health monitoring module 90 of the autonomous driving controller 20 determines that the autonomous driving system 14 is not functioning. Then, method 300 can proceed to block 304.

[0060] In block 304, in response to determining that the autonomous driving system is not functioning, the notification module 92 generates a notification indicating that the autonomous driving system 14 is not functioning, where the notification causes the tow taxi 12 to be dispatched to the geographical location where the autonomous vehicle 10 is located. Then, method 300 can proceed to block 306.

[0061] In block 306, the autonomous driving controller 20 sends a request for raw sensor data to the tow taxi 12. Then, method 300 may proceed to block 308.

[0062] In block 308, the verification module 98 of the autonomous driving controller 20 compares the raw sensor data received from the tow taxi 12 with the data collected from the multiple on-vehicle autonomous sensors 22 that are still operating. Then, method 300 may proceed to block 310.

[0063] In block 310, the verification module 98 of the autonomous driving controller 20 determines that the raw sensor data received from the tow taxi 12 matches the data collected from the multiple on-vehicle autonomous sensors 22 that are still operating. Then, method 300 may proceed to block 312.

[0064] In block 312, in response to determining that the raw sensor data received from the tow taxi 12 matches the data collected from the multiple on-vehicle autonomous sensors 22 that are still operating, the driving module 100 of the autonomous driving controller 20 determines one or more driving maneuvers based on the raw sensor data received from the tow taxi 12. Then, method 300 may terminate.

[0065] Now referring Figure 7 , computer program product 400 includes one or more non-transitory computer-readable storage media 402. Stored on the storage media 402 is computer-readable program code or logic 404 to provide and facilitate one or more aspects of the embodiments described herein. The program code or logic is created using a compiler or assembler, such as assembly instructions; the instructions, when executed, implement aspects of the embodiments. The program code, when created and stored on a tangible medium, is referred to as a computer-readable medium. Some examples of computer-readable media include, but are not limited to: electronic memory modules (RAM), flash memory, and optical discs (CDs). The computer program product medium can be read by a processing circuit in a computer system for execution by the processing circuit.

[0066] Generally referring to the accompanying drawings, the autonomous vehicle and the tow taxi provide various technical effects and benefits. Specifically, in the case where the autonomous driving system is no longer operating, the tow taxi guides the autonomous vehicle to a predetermined destination. The tow taxi can be particularly advantageous when the autonomous vehicle is fully autonomous and does not include driver inputs such as a steering wheel, since the user will not be able to drive the autonomous vehicle. Additionally, when the tow taxi is an air-based vehicle and has an aerial view, the disclosed tow taxi can be particularly advantageous in challenging scenarios such as road closures.

[0067] The controller can refer to: an electronic circuit, a combinational logic circuit, a field programmable gate array (FPGA), a processor (shared, dedicated, or in a group) that executes code or a part thereof, or some or all of the above combinations, such as in a system on a chip. Additionally, the controller can be microprocessor-based, such as a computer having at least one processor, memory (RAM and / or ROM), and associated input and output buses. The processor can operate under the control of an operating system resident in the memory. The operating system can manage computer resources such that computer program code implemented as one or more computer software applications (e.g., applications resident in the memory) can have instructions executed by the processor. In an alternative embodiment, the processor can directly execute the application, in which case the operating system can be omitted.

[0068] The description of the present disclosure is merely exemplary in nature, and variations that do not depart from the gist of the present disclosure are intended to fall within the scope of the present disclosure. Such variations should not be regarded as departing from the spirit and scope of the present disclosure.

Claims

1. An autonomous driving system for an autonomous vehicle, the autonomous driving system comprising: An autonomous driving controller, wirelessly connected to a towing taxi, which guides the autonomous vehicle when the autonomous driving system is inoperative; Wherein the autonomous driving controller, according to instructions: Determine that the autonomous driving system is inoperative; In response to determining that the autonomous driving system is inoperative, generate a notification indicating that the autonomous driving system is inoperative, wherein the notification causes the towing taxi to be dispatched to the geographical location of the autonomous vehicle; Receive a current data string from the towing taxi, the current data string including data points corresponding to the current time point and predicted data points for each of one or more future prediction time points; Compare the current data string with a previous data string recorded at a previous time point immediately preceding the current time point; And In response to determining that the current data string matches the previous data string, determine one or more driving maneuvers for the autonomous vehicle based on the current data string.

2. The autonomous driving system according to claim 1, wherein the data point corresponding to the current time point and the predicted data points for each of the one or more future prediction time points are represented by a final command determined by the towing taxi.

3. The autonomous driving system according to claim 2, wherein the final command represents the driver input position of the autonomous vehicle.

4. The autonomous driving system according to claim 3, wherein the driver input position includes an accelerator pedal position, a brake pedal position, and a steering wheel angle position.

5. The autonomous driving system according to claim 2, wherein the final command represents a reference trajectory set point of the autonomous vehicle.

6. The autonomous driving system according to claim 5, wherein the reference trajectory set point includes a speed trajectory point or a heading angle trajectory point of the autonomous vehicle.

7. The autonomous driving system according to claim 2, wherein the final command represents the target of the autonomous vehicle.

8. The autonomous driving system according to claim 1, wherein the data point corresponding to the current time point and the predicted data points for each of the one or more future prediction time points are represented by sensed data determined by the towing taxi.

9. The autonomous driving system according to claim 8, wherein the autonomous driving controller executes instructions to: Transmit driving restrictions and a request for defining a required data type to the towing taxi, wherein the towing taxi transmits the sensed data in response to receiving the driving restrictions and the request for defining the data type.

10. The autonomous driving system according to claim 1, wherein the autonomous driving controller communicates wirelessly with a backend system including a backend facility.

Images