IP Library › Granted Patent US 10,788,834
Granted Patent B2
US 10,788,834 · App. 16/029,242 · Granted Sep 29, 2020

System, method, and computer-readable medium for autonomous vehicle response to bicycles at intersections

Inventors: Michael J. Delp (Ann Arbor, MI); Ruijia Feng (Ann Arbor, MI); Shan Bao (Ann Arbor, MI)
Assignees: TOYOTA RESEARCH INSTITUTE, INC.; The Regents of the University of Michigan
G05D1/0214G05D1/0088G05D1/0246G06K9/00805G06N7/005G06T7/70G08G1/166G05D2201/0213G06T2207/30261
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,788,834
App. No.
16/029,242
Granted
Sep 29, 2020
Kind
B2
Abstract

An autonomous vehicle can plan a path of the autonomous vehicle at an intersection where cyclists are also present. The autonomous vehicle includes an imaging device and processing circuitry configured to receive information from the imaging device and then identify a position of a cyclist in a traffic intersection based on the information from the imaging device. Additionally, a future path of the cyclist is predicted based on the position of the cyclist in the traffic intersection and a path of the autonomous vehicle is planned based on the predicted future path of the cyclist. Further, it can be determine if the cyclist followed the predicted future path, and the planned path of the autonomous vehicle is updated in response to the cyclist not following the predicted future path.

Claims (40)

1. A system, comprising:

an imaging device; and

processing circuitry configured to

receive information from the imaging device,

identify a position of a cyclist in a traffic intersection based on the information from the imaging device,

predict a future path of the cyclist based on the position of the cyclist in the traffic intersection, and

plan a path of an autonomous vehicle based on the predicted future path of the cyclist, the planned path including a limit to a rate of acceleration of the autonomous vehicle while overtaking the cyclist.

2. The system of claim 1 , wherein the processing circuitry is further configured to

determine if the cyclist followed the predicted future path, and

update the planned path of the autonomous vehicle in response to the cyclist not following the predicted future path.

3. The system of claim 1 , wherein each position of the cyclist in the traffic intersection is associated with statistical information corresponding to a probability for a plurality of the cyclist's possible movements through the traffic intersection.

4. The system of claim 3 , wherein the plurality of the cyclist's movements through the intersection include turning left, turning right, traveling straight, and not moving.

5. The system of claim 1 , wherein the predicted future path of the cyclist is displayed in the autonomous vehicle.

6. The system of claim 1 , wherein the planned path of the autonomous vehicle is displayed in the autonomous vehicle.

7. The system of claim 3 , wherein the probabilities for the plurality of the cyclist's possible movements through the traffic intersection are based on real world data observing cyclists traveling through traffic intersections.

8. A method for planning a path of an autonomous vehicle, comprising:

receiving, via processing circuitry, information from an imaging device;

identifying, via the processing circuitry, a position of a cyclist in a traffic intersection based on the information from the imaging device;

predicting, via the processing circuitry, a future path of the cyclist based on the position of the cyclist in the traffic intersection; and

planning, via the processing circuitry, a path of the autonomous vehicle based on the predicted future path of the cyclist the planned path including a limit to a rate of acceleration of the autonomous vehicle while overtaking the cyclist.

9. The method of claim 8 , further comprising:

determining if the cyclist followed the predicted future path; and

updating the planned path of the autonomous vehicle in response to the cyclist not following the predicted future path.

10. The method of claim 8 , wherein each position of the cyclist in the traffic intersection is associated with statistical information corresponding to a probability for a plurality of the cyclist's possible movements through the traffic intersection.

11. The method of claim 10 , wherein the plurality of the cyclist's movements through the intersection include turning left, turning right, traveling straight, and not moving.

12. The method of claim 8 , wherein the predicted future path of the cyclist is displayed in the autonomous vehicle.

13. The method of claim 8 , wherein the planned path of the autonomous vehicle is displayed in the autonomous vehicle.

14. The method of claim 10 , wherein the probabilities for the plurality of the cyclist's possible movements through the traffic intersection are based on real world data observing cyclists traveling through traffic intersections.

15. A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by a computer, cause the computer to perform a method, the method comprising:

receiving information from the imaging device;

identifying a position of a cyclist in a traffic intersection based on the information from an imaging device;

predicting a future path of the cyclist based on the position of the cyclist in the traffic intersection; and

planning a path of the autonomous vehicle based on the predicted future path of the cyclist, the planned path including a limit to a rate of acceleration of the autonomous vehicle while overtaking the cyclist.

16. The non-transitory computer-readable storage medium of claim 15 , further comprising:

determining if the cyclist followed the predicted future path; and

updating the planned path of the autonomous vehicle in response to the cyclist not following the predicted future path.

17. The non-transitory computer-readable storage medium of claim 15 , wherein each position of the cyclist in the traffic intersection is associated with statistical information corresponding to a probability for a plurality of the cyclist's possible movements through the traffic intersection.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the plurality of the cyclist's movements through the intersection include turning left, turning right, traveling straight, and not moving.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the predicted future path of the cyclist and the planned path of the autonomous vehicle are displayed in the autonomous vehicle.

20. The non-transitory computer-readable storage medium of claim 17 , wherein the probabilities for the plurality of the cyclist's possible movements through the traffic intersection are based on real world data observing cyclists traveling through traffic intersections.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 20, 2020
From: TOYOTA RESEARCH INSTITUTE, INC.
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 054429/0766 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 16, 2019
From: DELP, MICHAEL J.
To: TOYOTA RESEARCH INSTITUTE, INC.
Reel/Frame 050070/0515 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 16, 2019
From: FENG, RUIJIA; BAO, SHAN
To: THE REGENTS OF THE UNIVERSITY OF MICHIGAN
Reel/Frame 050070/0517 →
Continuity (1)
Related Publication 20200012285A1 · Jan 9, 2020