Systems and Methods of Controlling an Autonomous Vehicle Using an Enhanced Trajectory Following Configuration

• US 20190064813A1
• Filed: 08/29/2017
• Published: 02/28/2019
• Est. Priority Date: 08/29/2017
• Status: Active Grant

• Current Assignee: Aurora Operations Incorporated (Aurora Innovation, Inc.)
• Original Assignee: Uber Technologies, Inc.
• Inventors: Binet, Guillaume, Yanakiev, Diana, Collins, Dillon, Bradley, David McAllister, Tschanz, Frederic
• Granted Patent: US 10,809,719 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• 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: G05D 1/0061 for transition from automatic pilot to manual pilot and vice versa
• 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

Abstract

Systems and methods for controlling an autonomous vehicle are provided. In one example embodiment, a computer-implemented method includes obtaining data representing a first trajectory including one or more states corresponding to a motion path. The method includes determining a second trajectory based at least in part on the first trajectory, the second trajectory including a first state corresponding to the motion path, and one or more secondary states corresponding to the motion path, the one or more secondary states indicating a state of the autonomous vehicle relative to the first state. The method includes determining one or more control signals based at least in part on the second trajectory. The method includes controlling a motion of the autonomous vehicle according to the motion path, based at least in part on the one or more control signals.

Claims

1. A computer-implemented method for controlling an autonomous vehicle, the method comprising:

obtaining, by a computing system comprising one or more computing devices, data representing a first trajectory of an autonomous vehicle that indicates a motion path between an initial state of the autonomous vehicle and a final state of the autonomous vehicle, the first trajectory including one or more intermediate states corresponding to the motion path;

determining, by the computing system, a second trajectory based at least in part on the first trajectory, the second trajectory including a first state corresponding to the motion path, and one or more secondary states corresponding to the motion path, the one or more secondary states indicating a state of the autonomous vehicle relative to the first state;

determining, by the computing system, one or more control signals based at least in part on the second trajectory, wherein the control signals cause the autonomous vehicle to execute at least part of the motion path; and

controlling a motion of the autonomous vehicle according to the motion path, based at least in part on the one or more control signals.

2. The computer-implemented method of claim 1, wherein determining the second trajectory comprises:

adjusting, by the computing system, a spatial resolution of the first trajectory from a first spatial resolution to a second spatial resolution, wherein the first trajectory indicates a position of the autonomous vehicle at the first spatial resolution, and the second trajectory indicates a position of the autonomous vehicle at the second spatial resolution that is less precise than the first spatial resolution.

3. The computer-implemented method of claim 1, wherein determining the second trajectory comprises:

adjusting, by the computing system, a temporal window of the first trajectory, wherein the first trajectory indicates a state of the autonomous vehicle over a first duration of time, and the second trajectory indicates a state of the autonomous vehicle over a second duration of time less than the first duration of time.

4. The computer-implemented method of claim 1, wherein determining the one or more control signals comprises:

encoding, by the computing system, the first state in a first data structure that corresponds to the first trajectory;

appending, by the computing system, the secondary states to the first data structure to generate a second data structure that corresponds to the second trajectory; and

determining, by the computing system, the one or more control signals based at least in part on the second data structure.

5. The computer-implemented method of claim 1, wherein the second trajectory includes a plurality of datapoints, the plurality of datapoints including a reference datapoint for an initial time and a plurality of trajectory datapoints at subsequent times after the initial time that are defined relative to the reference datapoint.

6. The computer-implemented method of claim 5, wherein the reference datapoint includes data indicative of the first state of the autonomous vehicle included in the first trajectory, and the plurality of trajectory datapoints include data indicative of a state of the autonomous vehicle relative to the first state.

7. The computer-implemented method of claim 5, wherein the plurality of trajectory datapoints indicate a state of the autonomous vehicle in discrete time intervals.

8. The computer-implemented method of claim 5, wherein the plurality of trajectory datapoints are an ordered list, a first trajectory datapoint in the ordered list indicating a state of the autonomous vehicle with respect to the reference datapoint, and each subsequent trajectory datapoint in the ordered list indicating a state of the autonomous vehicle with respect to a preceding trajectory datapoint in the ordered list.

9. The computer-implemented method of claim 1, wherein controlling the motion of the autonomous vehicle comprises:

providing, by the computing system, the one or more control signals to an electronic control unit that is independent from the computing system, wherein the electronic control unit, in response to receiving the one or more control signals, controls the motion of the autonomous vehicle accordingly.

10. The computer-implemented method of claim 1, wherein controlling the motion of the autonomous vehicle comprises:

providing, by the computing system, a control signal to an electronic control unit, the control signal representing a fault associated with one or more systems of the autonomous vehicle, wherein the electronic control unit, in response to receiving the control signal, controls the motion of the autonomous vehicle according to a predetermined vehicle command associated with the control signal representing the fault.

11. A computing system for controlling an autonomous vehicle, the system comprising:

one or more processors; and

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

determining a first trajectory of an autonomous vehicle indicating a motion path between an initial state and final state of the autonomous vehicle, the first trajectory including one or more intermediate states corresponding to the motion path;

determining a second trajectory based at least in part on the first trajectory, the second trajectory including a first state corresponding to the motion path, and one or more secondary states corresponding to the motion path, the one or more secondary states indicating a state of the autonomous vehicle relative to the first state;

determining one or more control signals based at least in part on the second trajectory, wherein the control signals cause the autonomous vehicle to execute at least part of the motion path; and

controlling a motion of the autonomous vehicle according to the motion path, based at least in part on the one or more control signals.

12. The computing system of claim 11, wherein the second trajectory includes a plurality of datapoints, the plurality of datapoints including a reference datapoint for an initial time and a plurality of trajectory points at subsequent times after the initial time that are defined relative to the reference point.

13. The computing system of claim 11, wherein determining the one or more control signals comprises:

encoding the first state in a first data structure that corresponds to the first trajectory;

appending the secondary states to the first data structure to generate a second data structure that corresponds to the second trajectory; and

determining the one or more control signals based at least in part on the second data structure.

14. The computing system of claim 13, wherein determining the one or more control signals further comprises:

adjusting a spatial resolution of one or more states represented by the second data structure; and

determining the one or more control signals based at least in part on the adjusted second data structure.

15. The computing system of claim 11, wherein controlling the motion of the autonomous vehicle comprises:

providing the one or more control signals to an electronic control unit that is independent from the computing system, wherein the electronic control unit, in response to receiving the one or more control signals, controls the motion of the autonomous vehicle accordingly.

16. The computing system of claim 11, wherein controlling the motion of the autonomous vehicle comprises:

providing a control signal to an electronic control unit, the control signal representing a fault associated with one or more systems of the autonomous vehicle, wherein the electronic control unit, in response to receiving the control signal, controls the motion of the autonomous vehicle according to a predetermined vehicle command associated with the control signal representing the fault.

17. A computer-implemented method for controlling an autonomous vehicle, the method comprising:

obtaining, by a computing system comprising one or more computing devices, data representing one or more vehicle commands to be cached;

monitoring, by the computing system, a diagnostics channel of the autonomous vehicle, and detecting one or more faults associated with the autonomous vehicle;

identifying, by the computing system, one or more cached vehicle commands that correspond to the one or more detected faults;

controlling, by the computing system, a motion of the autonomous vehicle, based at least in part on the identified cached vehicle commands.

18. A computing system for controlling an autonomous vehicle, the system comprising:

one or more processors; and

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

receiving one or more control signals to control a motion of the autonomous vehicle according to at least part of a motion path of the autonomous vehicle;

analyzing the one or more control signals to determine a data structure corresponding to the one or more control signals;

controlling the motion of the autonomous vehicle based at least in part on the data structure corresponding to the one or more control signals.

19. The computing system of claim 18, wherein if the data structure corresponding to the one or more control signals is a first data structure that includes one or more states between an initial state and final state of the autonomous vehicle, then the autonomous vehicle is controlled to assume each state indicated by the one or more control signals.

20. The computing system of claim 18, wherein if the data structure corresponding to the one or more control signals is a second data structure that includes one or more relative states between an initial state and final state of the autonomous vehicle, then the autonomous vehicle is controlled to assume the initial state, each relative state, and the final state indicated by the one or more control signals.