METHOD FOR OPERATING AN AUTONOMOUS VEHICLE

Abstract

The present disclosure relates to a computer implemented method for operating an autonomous vehicle based on sensor data representative of an area in a driving direction of and in the vicinity of the vehicle. The vehicle is equipped with a control unit adapted to determine if a plurality of detailed actions to be performed by the vehicle successfully may be used for fulfilling a desired general action plan for the vehicle. The present disclosure also relates to a corresponding control system and to a computer program product.

Claims

1. A computer implemented method for operating an autonomous vehicle, comprising: receiving, at a control unit arranged in communication with at least one sensor arranged to capture information in an area in a driving direction of and in a vicinity of a vehicle, sensor data from the at least one sensor, determining, by the control unit using a general action module and based on the sensor data, a desired general action plan to be performed by the vehicle when the vehicle is driving on a road, selecting, by the control unit, at least one detailed action module matching at least a portion of the desired general action plan, determining, using the selected at least one detailed action module and based on the sensor data, a plurality of detailed actions to be performed for fulfilling the desired general action plan, and estimating, using the control unit and based on a combination of the plurality of determined detailed actions, a success rate for fulfilling the desired general action plan.

2. The method of claim 1, wherein the desired general action plan includes one or a combination of general action plans.

3. The method of claim 1, wherein the desired general action plan is selected from a group comprising a lane change, creating gap for a lane change, forcing a gap for a lane change, facilitating surrounding traffic for a lane change, navigating an intersection, navigating a roundabout, navigating a road construction area, stopping at a side of a road, decreasing a time gap, increasing a time gap, initiating a longitudinal velocity change, initiating a lateral velocity change, and initiating an abort maneuver.

4. The method of claim 1, wherein the detailed actions are selected from a group comprising an acceleration request, a deceleration request, a steering angle request, an operation of turn indicator lights, and an operation of a vehicle horn.

5. The method of claim 1, wherein the method further comprises: operating the vehicle according to the plurality of detailed actions only if the estimated success rate is above a threshold level.

6. The method of claim 1, wherein the desired general action plan is indicative of an action to be taken within the next 20 seconds.

7. The method of claim 1, wherein the plurality of detailed actions are indicative of actions to be taken within less than 10 seconds.

8. The method of claim 1, wherein the desired general action plan is related to a traffic planning maneuver for the vehicle.

9. The method of claim 5, wherein the threshold level is dependent on a current speed of the vehicle.

10. The method of claim 1, wherein the plurality of detailed actions relates to operating the vehicle according to an estimated travel path.

11. A control unit arranged and adapted for controlling an autonomous vehicle, the control unit adapted to: receive sensor data from at least one sensor arranged to capture information in an area in a driving direction of and in a vicinity of a vehicle, determine, using the general action module and based on the sensor data, a desired general action plan to be performed by the vehicle when the vehicle is driving on a road, select at least one detailed action module matching at least a portion of the desired general action plan, determine using the selected at least one detailed action module and based on the sensor data, a plurality of detailed actions to be performed for fulfilling the desired general action plan, and estimate, based on a combination of the plurality of determined detailed actions, a success rate for fulfilling the desired general action plan.

12. The control unit of claim 11, wherein the desired general action plan includes one or a combination of general actions.

13. The control unit of claim 11, wherein the control unit is further adapted to: operate the vehicle according to the plurality of detailed actions only if the estimated success rate is above a predetermined threshold.

14. The control unit of claim 8, wherein the desired general action plan is indicative of an action to be taken within the next 20 seconds.

15. The control unit of claim 8, wherein the plurality of detailed actions are indicative of actions to be taken within less than 10 seconds.

16-17. (canceled)

18. The control unit of claim 8, wherein the plurality of detailed actions relates to operating the vehicle according to an estimated travel path.

19. The control unit claim 8, wherein the at least one sensor comprises a radar, a LiDAR sensor, or a camera.

20-21. (canceled)

22. A computer program product comprising a non-transitory computer readable medium having stored thereon computer program instructions to cause a processor device to: receive, at a control unit arranged in communication with at least one sensor arranged to capture information in an area in a driving direction of and in a vicinity of a vehicle, sensor data from the at least one sensor, determine, by the control unit using a general action module and based on the sensor data, a desired general action plan to be performed by the vehicle when the vehicle is driving on a road, select, by the control unit, at least one detailed action module matching at least a portion of the desired general action plan, determine, using the selected at least one detailed action module and based on the sensor data, a plurality of detailed actions to be performed for fulfilling the desired general action plan, and estimate, using the control unit and based on a combination of the plurality of determined detailed actions, a success rate for fulfilling the desired general action plan.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0031] With reference to the appended drawings, below follows a more detailed description of embodiments of the present disclosure cited as examples.

[0032] In the drawings:

[0033] FIGS. 1A illustrates a truck, 1B a bus and 1C a wheel loader in which the control system according to the present disclosure may be incorporated;

[0034] FIG. 2 illustrates a conceptual control system in accordance to a currently preferred embodiment of the present disclosure;

[0035] FIG. 3 exemplifies an operation of the control system, and

[0036] FIG. 4 illustrates the processing steps for performing the method according to the present disclosure.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS OF THE INVENTION

[0037] The present disclosure will now be described more fully hereinafter with reference to the accompanying drawings, in which currently preferred embodiments of the present disclosure are shown. This disclosure may, however, be embodied in many different forms 3and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided for thoroughness and completeness, and fully convey the scope of the disclosure to the skilled addressee. Like reference characters refer to like elements throughout.

[0038] Referring now to the drawings and to FIG. 1A in particular, there is depicted an exemplary vehicle, here illustrated as a truck 100, in which a control system 200 (as shown in FIG. 2) according to the present disclosure may be incorporated. The control system 200 may of course be implemented, possibly in a slightly different way, in a bus 102 as shown in FIG. 1B, wheel loader as shown in FIG. 1C, a car, a bus, etc.

[0039] The vehicle may for example be one of an electric or hybrid vehicle, or possibly a gas, gasoline or diesel vehicle. The vehicle comprises an electric machine (in case of being an electric or hybrid vehicle) or an engine (such as an internal combustion engine in case of being a gas, gasoline or diesel vehicle). The vehicle may further be manually operated, fully or semi-autonomous.

[0040] FIG. 2 shows a conceptual and exemplary implementation of the control system 200, comprising a control unit 202, such as an electronic control unit (ECU), adapted for operating e.g. any one of the vehicles 100, 102, 104. The ECU 202 implements an interface for receiving data from a plurality of sensors 204, 206, 208, such as e.g. a radar 204, a LiDAR sensor arrangement 206 and a camera 208. The control system 200 may also be provided with an interface for operating the vehicle based on the above discussed general action plan(s) and plurality of determined detailed actions.

[0041] For reference, the ECU 202 may for example be manifested as a general-purpose processor, an application specific processor, a circuit containing processing components, a group of distributed processing components, a group of distributed computers configured for processing, a field programmable gate array (FPGA), etc. The processor may be or include any number of hardware components for conducting data or signal processing or for executing computer code stored in memory. The memory may be one or more devices for storing data and/or computer code for completing or facilitating the various methods described in the present description. The memory may include volatile memory or non-volatile memory. The memory may include database components, object code components, script components, or any other type of information structure for supporting the various activities of the present description. According to an exemplary embodiment, any distributed or local memory device may be utilized with the systems and methods of this description. According to an exemplary embodiment the memory is communicably connected to the processor (e.g., via a circuit or any other wired, wireless, or network connection) and includes computer code for executing one or more processes described herein.

[0042] The ECU 202 may preferably also be arranged in communication with e.g. a radionavigation system, for example including a GPS receiver 220 as well as a map database 222 e.g. holding map navigation data relating to a road where the vehicle 100, 102, 104 is travelling.

[0043] During operation of the control system 200 for controlling the operation of the vehicle 100, 102, 104, with further reference to FIGS. 3 and 4, the ECU 202 is adapted to implement at least a general action module 210 and a plurality of detailed action modules 212, 214, 216, 218. As discussed above, the general action module 302 is adapted to implement a macro portion of forming an overall action plan as how to operate the vehicle 100, 102, 104, such as within e.g. the next 20 seconds (or alternatively 200-500 meters ahead of the vehicle). As such, the general action module 210 is configured to form one or a plurality of general action plans relating to e.g. a lane change, creating gap for a lane change, forcing a gap for a lane change, facilitating surrounding traffic for a lane change, navigating an intersection, navigating a roundabout, navigating a road construction area, stopping at a side of a road, decreasing a time gap, increasing a time gap, initiating a longitudinal velocity change, initiating a lateral velocity change, and initiating an abort maneuver.

[0044] Correspondingly, the detailed action modules 212, 214, 216, 218 are then rather each provided for implementing a micro portion of the operating the vehicle, such as for determining detailed actions that needs to be taken for operating the vehicle within the next e.g. 10 seconds (or alternatively 0-200 meters ahead of the vehicle) and with the purpose of fulfilling the general action plan formed by the general action module 302. Examples of detailed actions may for example generally include what combination of trajectories the vehicle must operate according to for fulfilling the general action plan, and more specifically including acceleration requests, deceleration requests, adjustment of a steering angle, a magnitude of a longitudinal velocity change, a magnitude of a lateral velocity change, an operation of turn indicator lights, and an operation of a vehicle horn, etc.

[0045] In line with the example as is illustrated in FIG. 3, the process starts by the ECU 202 of the vehicle 100, 102, 104 receives, S1, sensor data from at least one of the plurality of sensors 204, 206, 208, and possibly also from further sensors comprised with the vehicle 100, 102, 104, such as information comprised with e.g. a CAN bus of the vehicle 100, 102, 104 (e.g. speed, acceleration, etc.) and relating to the operation of the vehicle 100, 102, 104. The ECU 202 may also receive information from the GPS receiver 220 and the map database 222, relating to where the vehicle is e.g. presently located. The map database 222 may in some embodiments hold a predetermined travel path relating to how the vehicle 100, 102, 104 is to generally drive from a start position to a destination.

[0046] Within the context of the present disclosure, a module may be seen as an independent, possibly interchangeable portion of the overall scheme, where each module each contains everything necessary to execute only one aspect of the desired functionality. Due to this structure, existing modules may be easily changed and/or further modules may be added.

[0047] The general action module 210 and based on the sensor data form an “understanding” of 1the surrounding of the vehicle 100, 102, 104, for example including where other vehicles such as exemplary vehicles 302 and 304 are located (in relation to the “own” vehicle), e.g. defined as a current traffic situation for the vehicle 100, 102, 104.

[0048] As shown in FIG. 3, the own vehicle, exemplified with vehicle 100, is located in a right-hand lane travelling forward on a twin lane road. Based on the sensor data it is determined that vehicle 302 is located ahead of the own vehicle 100, and that the vehicle 304 is located slightly behind and in the left-hand lane. It is further determined that the own vehicle 100 is travelling slightly faster than the forward vehicle 302.

[0049] Based on this information, the general action module 210 determines, S2, a general action plan indicative of a desire to change to the left-hand lane, and in front of the vehicle 304. Based on the determined general action plan, the ECU 202 selects one or a plurality of the detailed action modules 212, 214, 216, 218 that match at least a portion of the determined general action plan. That is and as discussed above, the plurality of the detailed action modules 212, 214, 216, 218 are preferably designed to handle different parts of the actions that needs to be performed for successfully performing the lane change.

[0050] In the present example it may for example be suitable to select e.g. one detailed action module that has been adapted to determine how much the vehicle must accelerate to allow it to be safe to perform the lane change, one detailed action module that has been adapted to determine a steering angle a for safely changing lane, one detailed action module that has been adapted to determine when a turn signal is suitable to be activated, etc. Further detailed action modules may of course be selected.

[0051] As is understood from the above, the selected detailed action modules are provided for together determine, S4, a plurality of detailed actions to be performed for fulfilling the desired general action plan. The different detailed action modules may in some embodiments be implemented to take into account operational parameters for the vehicles, such as maximum speed, maximum steering angles, weight, etc. The different detailed action modules may also be previously “trained” on vehicle operational data, e.g. by arranging the different detailed action modules to at least partly implement a machine learning scheme.

[0052] In some embodiments the plurality of detailed actions may include actual control parameters for operating the vehicle 100. However, the plurality of detailed actions may alternatively (or also) relate to simulation of different scenarios for operating the vehicle, i.e. not necessarily final control parameters but rather estimations of how to operate the vehicle.

[0053] Once the plurality of detailed actions has been determined, the present disclosure implements an estimation, S5, of a success rate based on the plurality of detailed actions. That is, e.g. an overall simulation may be performed for estimating of the combination of at least a portion of the plurality of detailed actions will allow the lane change to be performed in a safe manner. In some embodiments of the present disclosure, the success rate may be determined for “different scenarios”. In line with the example presented in FIG. 3, different scenarios may for example relate to e.g. different levels of acceleration, etc.

[0054] Preferably, the success rate is benchmarked towards a threshold for determining if the combination of the plurality of detailed actions should be “executed” for controlling the vehicle to change the lane. In case the success rate is considered above the threshold the vehicle is controlled based on the plurality of detailed actions. As indicated above, the threshold may be allowed to be dependent on external factors, such as e.g. a current speed of an allowed speed for the road where the own vehicle 100 is currently travelling.

[0055] Conversely, in case the success rate is below the threshold, this result may be used by the ECU 202 for initiating a new determination of an “alternative” general action plan. Such a general action plan may in fact also relate to changing lane, but for example including that the own vehicle 100 should allow the vehicle 304 to pass before changing to the left-hand lane. Detailed actions in such a scenario may for example include deacceleration (to ensure that the own vehicle 100 doesn't collide with the forwards vehicle 302), and a further steering angle a for safely changing lane once the vehicle 304 has safely passed the own vehicle 100 (in the left-hand lane).

[0056] It should further be understood that in case more than a single scenario is evaluated, it may be allowed to sort the success rates for the different scenarios and then proceed with the scenario that is considered to have the highest success rate and still being above the threshold.

[0057] The present disclosure contemplates methods, devices and program products on any machine-readable media for accomplishing various operations. The embodiments of the present disclosure may be implemented using existing computer processors, or by a special purpose computer processor for an appropriate system, incorporated for this or another purpose, or by a hardwired system. Embodiments within the scope of the present disclosure include program products comprising machine-readable media for carrying or having machine-executable instructions or data structures stored thereon. Such machine-readable media can be any available media that can be accessed by a general purpose or special purpose computer or other machine with a processor.

[0058] By way of example, such machine-readable media can comprise RAM, ROM, EPROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code in the form of machine-executable instructions or data structures and which can be accessed by a general purpose or special purpose computer or other machine with a processor. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a machine, the machine properly views the connection as a machine-readable medium. Thus, any such connection is properly termed a machine-readable medium. Combinations of the above are also included within the scope of machine-readable media. Machine-executable instructions include, for example, instructions and data that cause a general-purpose computer, special purpose computer, or special purpose processing machines to perform a certain function or group of functions.

[0059] Although the figures may show a specific order of method steps, the order of the steps may differ from what is depicted. In addition, two or more steps may be performed concurrently or with partial concurrence. Such variation will depend on the software and hardware systems chosen and on designer choice. All such variations are within the scope of the disclosure. Likewise, software implementations could be accomplished with standard programming techniques with rule-based logic and other logic to accomplish the various connection steps, processing steps, comparison steps and decision steps.

[0060] Additionally, even though the disclosure has been described with reference to specific exemplifying embodiments thereof, many different alterations, modifications and the like will become apparent for those skilled in the art.

[0061] Variations to the disclosed embodiments can be understood and effected by the skilled addressee in practicing the claimed disclosure, from a study of the drawings, the disclosure, and the appended claims. Furthermore, in the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality.