Context-specific tolerance for motion control in autonomous vehicles

• US 10,571,922 B2
• Filed: 08/28/2019
• Issued: 02/25/2020
• Est. Priority Date: 09/15/2017
• Status: Active Grant

• Current Assignee: Aurora Operations Incorporated (Aurora Innovation, Inc.)
• Original Assignee: Uatc, LLC (Uber Technologies, Inc.)
• Inventors: Greenfield, Aaron L., Tschanz, Frederic, Bradley, David McAllister, Yanakiev, Diana
• Primary Examiner(s): Alharbi, Adam M
• Application Number:
  US16/553,929
• Publication Number:
  US 20190384301A1
• Time in Patent Office: 181 Days
• CPC Class Codes: B60W 2554/4023 large-size vehicles, e.g. trucks
• CPC Class Codes: B60W 2556/25 Data precision
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• CPC Class Codes: B60W 60/0011 involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
• CPC Class Codes: B60W 60/0013 specially adapted for occupant comfort
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0212 with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13

Abstract

The present disclosure provides systems and methods that employ tolerance values defining a level of vehicle control precision for motion control of an autonomous vehicle. More particularly, a vehicle controller can obtain a trajectory that describes a proposed motion path for the autonomous vehicle. A constraint set of one or more tolerance values (e.g., a longitudinal tolerance value and/or lateral tolerance value) defining a level of vehicle control precision can be determined or otherwise obtained. Motion of the autonomous vehicle can be controlled to follow the trajectory within the one or more tolerance values (e.g., longitudinal tolerance value(s) and/or a lateral tolerance value(s)) identified by the constraint set. By creating a motion control framework for autonomous vehicles that includes an adjustable constraint set of tolerance values, autonomous vehicles can more effectively implement different precision requirements for different driving situations.

Claims

1. A vehicle controller configured to perform one or more operations comprising:

generating context information based at least in part on a location of an autonomous vehicle relative to one or more objects in an environment in which the autonomous vehicle is operating;

determining a trajectory of the autonomous vehicle through the environment based at least in part on the context information, wherein the trajectory describes a proposed motion path for an autonomous vehicle through the environment and comprises a series of desired vehicle states of the autonomous vehicle at different points in time;

generating expected controller performance data that describes a threshold amount of permitted deviation that will not be exceeded;

obtaining one or more tolerance values and one or more tolerance parameters, wherein the one or more tolerance values and the one or more tolerance parameters define a level of permitted deviation for the autonomous vehicle with respect to the trajectory and are based at least in part on the series of desired vehicle states of the autonomous vehicle comprising a velocity of the vehicle, and wherein the one or more tolerance parameters are based at least in part on the expected controller performance data; and

generating one or more vehicle actuator commands based at least in part on the one or more tolerance values and the one or more tolerance parameters, wherein the one or more vehicle actuator commands are configured to control motion of the autonomous vehicle to follow the trajectory within the one or more tolerance values.

2. The vehicle controller of claim 1, wherein the one or more tolerance values comprise a longitudinal tolerance value defining a level of permitted deviation in a longitudinal direction for the autonomous vehicle with respect to the trajectory, or a lateral tolerance value defining a level of permitted deviation in the lateral direction for the autonomous vehicle with respect to the trajectory.

3. The vehicle controller of claim 1, wherein the context information comprises information descriptive of an environment in which the autonomous vehicle is currently operating, a maneuver the autonomous vehicle is currently engaged in, a maneuver the autonomous vehicle is about to engage in, a current state of the autonomous vehicle, a current state of the one or more objects in the environment, or a predicted state of the one or more objects in the environment.

4. The vehicle controller of claim 1, wherein the vehicle controller is further configured to generate tolerance feedback descriptive of a current ability of the vehicle controller to follow the trajectory in accordance with the one or more tolerance values.

5. The vehicle controller of claim 4, wherein the tolerance feedback is generated based at least in part on a tracking error check that compares a current measured tracking error for the autonomous vehicle with an expected tracking error.

6. The vehicle controller of claim 4, wherein the tolerance feedback is generated based at least in part on an aggressiveness limit check that compares the one or more tolerance values to one or more predetermined limit values.

7. The vehicle controller of claim 1, wherein the one or more vehicle actuator commands are based at least in part on one or more adjustable parameters, and wherein the vehicle controller is further configured to generate one or more tolerance parameters that are used to alter the one or more adjustable parameters.

8. The vehicle controller of claim 1, wherein the vehicle controller is further configured to apply tolerance parameter limiting to the one or more tolerance parameters to smooth the output of the one or more tolerance parameters.

9. An autonomous vehicle, comprising:

a computing system comprising one or more processors and one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the computing system to perform one or more operations comprising;

generating context information based at least in part on a location of an autonomous vehicle relative to one or more objects in an environment in which the autonomous vehicle is operating;

determining a trajectory of the autonomous vehicle through the environment based at least in part on the context information, wherein the trajectory describes a proposed motion path for an autonomous vehicle through the environment and comprises a series of desired vehicle states of the autonomous vehicle at different points in time;

generating expected controller performance data that describes a threshold amount of permitted deviation that will not be exceeded;

obtaining one or more tolerance values and one or more tolerance parameters, wherein the one or more tolerance values and the one or more tolerance parameters define a level of permitted deviation for the autonomous vehicle with respect to the trajectory and are based at least in part on the series of desired vehicle states of the autonomous vehicle comprising a velocity of the autonomous vehicle, and wherein the one or more tolerance parameters are based at least in part on the expected controller performance data; and

generating one or more vehicle actuator commands based at least in part on the one or more tolerance values and the one or more tolerance parameters, wherein the one or more vehicle actuator commands are configured to control motion of the autonomous vehicle to follow the trajectory within the one or more tolerance values.

10. The autonomous vehicle of claim 9, further comprising a motion planner implemented by the computing system, wherein the motion planner is configured to generate the trajectory that describes the proposed motion path for the autonomous vehicle, and wherein the motion planner is configured to generate a constraint set of the one or more tolerance values.

11. The autonomous vehicle of claim 10, wherein the motion planner is configured to generate the constraint set of the one or more tolerance values based on a relative distance of objects from the location of the autonomous vehicle over the different points in time.

12. The autonomous vehicle of claim 10, wherein the motion planner is configured to generate the constraint set of the one or more tolerance values by obtaining predefined tolerance values from a look up table based on context information generated by a dedicated context controller of the autonomous vehicle.

13. The autonomous vehicle of claim 9, wherein the autonomous vehicle is further configured to determine tolerance feedback descriptive of a current ability of the autonomous vehicle to follow the trajectory within the one or more tolerance values and to provide the tolerance feedback to the motion planner.

14. The autonomous vehicle of claim 9, wherein the at least one lateral vehicle actuator command and the at least one longitudinal vehicle actuator command are respectively determined based on one or more adjustable parameters, and wherein the autonomous vehicle is further configured to generate a longitudinal tolerance parameter and a lateral tolerance parameter that are used to alter the values of the one or more adjustable parameters used to determine the at least one lateral vehicle actuator command and the at least one longitudinal vehicle actuator command.

15. The autonomous vehicle of claim 9, wherein the autonomous vehicle comprises a tolerance parameter generator configured to generate one or more tolerance parameters that are used at least in part to generate the longitudinal actuator command and the lateral actuator command.

16. The autonomous vehicle of claim 15, wherein the tolerance parameter generator further comprises a tolerance parameter limiting system that implements asymmetric rate limiting to smooth the output of the one or more tolerance parameters.

17. A computer-implemented method to control motion of an autonomous vehicle, the method comprising:

generating, by a computing system comprising one or more devices, context information based at least in part on a location of an autonomous vehicle relative to one or more objects in an environment in which the autonomous vehicle is operating;

determining, by the computing system, a trajectory of the autonomous vehicle through the environment based at least in part on the context information, wherein the trajectory describes a proposed motion path for an autonomous vehicle through the environment and comprises a series of desired vehicle states of the autonomous vehicle at different points in time;

generating, by the computing system, expected controller performance data that describes a threshold amount of permitted deviation that will not be exceeded;

obtaining, by the computing system, one or more tolerance values and one or more tolerance parameters, wherein the one or more tolerance values and the one or more tolerance parameters define a level of permitted deviation for the autonomous vehicle with respect to the trajectory and are based at least in part on the series of desired vehicle states of the autonomous vehicle comprising a velocity of the autonomous vehicle, and wherein the one or more tolerance parameters are based at least in part on the expected controller performance data; and

generating, by the computing system, one or more vehicle actuator commands based at least in part on the one or more tolerance values and the one or more tolerance parameters, wherein the one or more vehicle actuator commands are configured to control motion of the autonomous vehicle to follow the trajectory within the one or more tolerance values.

18. The computer-implemented method of claim 17, further comprising:

obtaining, by the computing system, one or more state variables representing the current state of the autonomous vehicle; and

determining, by the computing system, based at least in part on the one or more state variables and the trajectory, a tracking error descriptive of a deviation of the autonomous vehicle from the series of desired states of the autonomous vehicle; and

determining, by the computing system, a constraint set of the one or more tolerance values defining a level of vehicle control precision based at least in part on the one or more state variables and the tracking error.

19. The computer-implemented method of claim 17, wherein the one or more tolerance values comprise a longitudinal tolerance value defining a level of permitted deviation in a longitudinal direction for the autonomous vehicle with respect to the trajectory, or a lateral tolerance value defining a level of permitted deviation in the lateral direction for the autonomous vehicle with respect to the trajectory, and wherein the one or more vehicle actuator commands comprise a longitudinal actuator command for controlling the autonomous vehicle to follow the trajectory within the longitudinal tolerance value and a lateral actuator command for controlling the autonomous vehicle to follow the trajectory within the lateral tolerance value.

20. The computer-implemented method of claim 17, wherein the context information comprises information descriptive of an environment in which the autonomous vehicle is currently operating, a maneuver the autonomous vehicle is currently engaged in, a maneuver the autonomous vehicle is about to engage in, a current state of the autonomous vehicle, a current state of the one or more objects in the environment, or a predicted state of the one or more objects in the environment.