Adaptive vehicle motion control system

Patent metadata

Field	Value
Publication number	US-9964952-B1
Application number	US-201715423233-A
Country	US
Kind code	B1
Filing date	Feb 2, 2017
Priority date	Feb 2, 2017
Publication date	May 8, 2018
Grant date	May 8, 2018

Abstract

Systems and methods for controlling the motion of an autonomous are provided. In one example embodiment, a computer implemented method includes obtaining, by one or more computing devices on-board an autonomous vehicle, data associated with one or more objects that are proximate to the autonomous vehicle. The data includes a predicted path of each respective object. The method includes identifying at least one object as an object of interest based at least in part on the data associated with the object of interest. The method includes generating cost data associated with the object of interest. The method includes determining a motion plan for the autonomous vehicle based at least in part on the cost data associated with the object of interest. The method includes providing data indicative of the motion plan to one or more vehicle control systems to implement the motion plan for the autonomous vehicle.

First claim

What is claimed is:

1. A computer-implemented method of controlling the motion of an autonomous vehicle, comprising:
obtaining, by one or more computing devices on-board an autonomous vehicle, data associated with one or more objects that are proximate to the autonomous vehicle, wherein the data comprises a predicted path of each respective object;
identifying, by the one or more computing devices, at least one object as an object of interest based at least in part on the data associated with the object of interest;
generating, by the one or more computing devices, cost data associated with the object of interest, wherein the cost data is indicative of an effect of controlling a motion of the autonomous vehicle such that the autonomous vehicle travels behind or in front of the object of interest in a manner that corresponds to a motion of the object of interest;
determining, by the one or more computing devices, a motion plan for the autonomous vehicle based at least in part on the cost data associated with the object of interest; and
providing, by the one or more computing devices, data indicative of the motion plan to one or more vehicle control systems to implement the motion plan for the autonomous vehicle.

2. The computer-implemented method of claim 1 , wherein the object of interest comprises a lead vehicle and traveling in the manner that corresponds to the object of interest comprises following the lead vehicle.

3. The computer-implemented method of claim 1 , wherein the cost data comprises a cost function that is indicative of a cost of controlling the motion of the autonomous vehicle in the manner that corresponds to the motion of the object of interest.

4. The computer-implemented method of claim 3 , wherein one or more inputs of the cost function comprise at least a subset of the data associated with the object of interest and a travel route of the autonomous vehicle.

5. The computer-implemented method of claim 1 , wherein the cost data is based at least in part on one or more constraints, and wherein the one or more constraints comprise at least one of a headway between the autonomous vehicle and the object of interest, a time to a potential collision between the autonomous vehicle and the object of interest, and a minimum preferred distance between the autonomous vehicle and the object of interest.

6. The computer-implemented method of claim 1 , wherein the one or more computing devices identify the object of interest based at least in part on one or more of a travel lane position of the object of interest and a speed associated with the object of interest.

7. The computer-implemented method of claim 6 , wherein the motion plan comprises a trajectory by which the autonomous vehicle is to travel behind the object of interest or a trajectory by which the autonomous vehicle is to travel in front of the object of interest.

8. The computer-implemented method of claim 7 , wherein the motion plan further comprises a distance between the autonomous vehicle and the object of interest, and wherein the motion plan is indicative of a modulation of a speed of the autonomous vehicle such that the autonomous vehicle maintains at least the distance between the autonomous vehicle and the object of interest.

9. A computing system for controlling the motion of an autonomous vehicle, comprising:
one or more processors on-board an autonomous vehicle; and
one or more memory devices on-board the autonomous vehicle, the one or more memory devices storing instructions that when executed by the one or more processors cause the computing system to perform operations, the operations comprising:
obtaining data associated with one or more objects that are proximate to the autonomous vehicle, wherein the data comprises a predicted path of each respective object;
identifying at least one object as an object of interest based at least in part on at least the data associated with the object of interest and a travel route of the autonomous vehicle;
generating cost data associated with the object of interest, wherein the cost data is indicative of an effect of controlling a motion of the autonomous vehicle such that the autonomous vehicle travels behind or in front of the object of interest in a manner that corresponds to a motion of the object of interest; and
outputting data indicative of the cost data associated with the object of interest.

10. The computing system of claim 9 , wherein the operations further comprise:
determining a motion plan for the autonomous vehicle based at least in part on the cost data associated with the object of interest; and
providing data indicative of the motion plan to one or more vehicle control systems to implement the motion plan for the autonomous vehicle, wherein implementation of the motion plan causes the autonomous vehicle to travel in the manner that corresponds to the motion of the object of interest with at least a minimum distance between the autonomous vehicle and the object of interest.

11. The computing system of claim 9 , wherein the one or more objects include a plurality of objects, and wherein the data associated with the one or more objects is indicative of an object class for each respective object of the plurality of objects, and wherein identifying at least one object as an object of interest comprises:
identifying at least one object as the object of interest based at least in part on the object class associated with the object of interest.

12. The computing system of claim 9 , wherein the cost data is based at least in part on one or more constraints, and wherein the one or more constraints comprise at least one of a headway between the autonomous vehicle and the object of interest and a time to a potential collision between the autonomous vehicle and the object of interest.

13. The computing system of claim 12 , wherein the headway between the autonomous vehicle and the time to the potential collision between the autonomous vehicle and the object of interest are dynamically adjustable while the vehicle is traveling.

14. The computing system of claim 9 , wherein the travel route of the autonomous vehicle indicates that the autonomous vehicle is to travel through an intersection, and wherein the predicted path of the object of interest indicates that the object of interest is to travel through the intersection.

15. The computing system of claim 9 , wherein the object of interest is a vehicle, and wherein the predicted path of the object of interest predicts that the object of interest is to merge into a current travel lane of the autonomous vehicle.

16. An autonomous vehicle comprising:
one or more vehicle control systems;
one or more processors on-board the autonomous vehicle; and
one or more memory devices on-board the autonomous vehicle, the one or more memory devices storing instructions that when executed by the one or more processors cause the one or more processors to perform operations, the operations comprising:
obtaining data associated with one or more objects that are proximate to the autonomous vehicle, wherein the data associated with the one or more objects comprises a predicted path of each respective object;
identifying at least one object as a first object of interest based at least in part on the data associated with the first object of interest;
generating a first set of cost data associated with the first object of interest, wherein the first set of cost data is indicative of an effect of controlling a motion of the autonomous vehicle such that the autonomous vehicle travels behind or in front of the first object of interest;
d

Assignees

• Uber Technologies Inc

Inventors

• Costa Albert
• Phillips Michael L
• Bode Michael

Classifications

• G05D1/0088 Primary

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G05D1/0212

  with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287) · CPC title

• G05D2201/0213

  Physics · mapped topic

• G05D1/0289 Primary

  with means for avoiding collisions between vehicles (vehicle fittings for automatically controlling speed including means for detecting potential obstacles B60K31/0008; avoiding obstacles by action on the steering system B62D; radar, sonar, lidar systems designed for anti-collision purposes G01S13/93, G01S15/93, G01S17/93) · CPC title

• G05D1/0217

  in accordance with energy consumption, time reduction or distance reduction criteria · CPC title