Method and system to predict vehicle traffic behavior for autonomous vehicles to make driving decisions

Patent metadata

Field	Value
Publication number	US-10394245-B2
Application number	US-201615359466-A
Country	US
Kind code	B2
Filing date	Nov 22, 2016
Priority date	Nov 22, 2016
Publication date	Aug 27, 2019
Grant date	Aug 27, 2019

Abstract

Responsive to sensor data received from one or more sensors of an autonomous vehicle, one or more predicted trajectories are generated, with each of the predicted trajectories having an associated probability. One or more driving scenarios that trigger gesture recognition are identified. For each of the identified driving scenarios, one or more gestures from one or more vehicles are detected in accordance with a gesture detection protocol. One or more gestures from the autonomous vehicle are emitted for communication with the vehicles in accordance with a gesture emission protocol based on the detected gestures. The predicted trajectories are modified based on the detected gestures, the emitted gestures and the associated probabilities of the predicted trajectories. The autonomous vehicle is controlled based on the modified predicted trajectories.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous vehicle, the method comprising:
generating one or more predicted trajectories based on sensor data received from one or more sensors of the autonomous vehicle, each of the predicted trajectories being associated with a probability;
detecting one or more gestures from one or more vehicles other than the autonomous vehicle in accordance with a gesture detection protocol;
emitting one or more gestures from the autonomous vehicle to communicate with the one or more vehicles in accordance with a gesture emission protocol based on the detected gestures;
modifying the predicted trajectories based on the detected gestures, the emitted gestures, and the associated probabilities of the predicted trajectories; and
controlling the autonomous vehicle based on the modified predicted trajectories.

2. The method of claim 1 , wherein modifying the predicted trajectories includes removing a first set of trajectories from the predicted trajectories and producing a second set of trajectories.

3. The method of claim 2 , wherein producing the second set of trajectories includes timestamping each trajectory in the second set of trajectories based on the detected one or more gestures.

4. The method of claim 2 , wherein trajectories in the first set of trajectories have lower associated probabilities than trajectories in the second set of trajectories.

5. The method of claim 1 , wherein the one or more vehicles are non-autonomous vehicles, and wherein the one or more detected gestures from the one or more vehicles are human hand motions.

6. The method of claim 1 , wherein the emitted one or more gestures is an overtake gesture when the detected one or more gestures is a yield gesture, and wherein the emitted one or more gestures is a yield gesture when the detected one or more gestures is an overtake gesture or an unrecognized gesture.

7. The method of claim 1 , wherein the gesture detection protocol and the gesture emission protocol include a predefined set of values, each of the values corresponding to a particular gesture.

8. The method of claim 1 , wherein the one or more vehicles are other autonomous vehicles, and wherein detecting the one or more gestures from the one or more vehicles comprises wirelessly receiving one or more signals indicative of the detected one or more gestures from the other autonomous vehicles.

9. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
generating one or more predicted trajectories based on sensor data received from one or more sensors of an autonomous vehicle, each of the predicted trajectories being associated with a probability;
detecting one or more gestures from one or more vehicles other than the autonomous vehicle in accordance with a gesture detection protocol;
emitting one or more gestures from the autonomous vehicle to communicate with the one or more vehicles in accordance with a gesture emission protocol based on the detected gestures;
modifying the predicted trajectories based on the detected gestures, the emitted gestures, and the associated probabilities of the predicted trajectories; and
controlling the autonomous vehicle based on the modified predicted trajectories.

10. The machine-readable medium of claim 9 , wherein modifying the predicted trajectories includes removing a first set of trajectories from the predicted trajectories and producing a second set of trajectories.

11. The machine-readable medium of claim 10 , wherein producing the second set of trajectories includes timestamping each trajectory in the second set of trajectories based on the detected one or more gestures.

12. The machine-readable medium of claim 10 , wherein trajectories in the first set of trajectories have lower associated probabilities than trajectories in the second set of trajectories.

13. The machine-readable medium of claim 9 , wherein the one or more vehicles are non-autonomous vehicles; and the one or more gestures from the vehicles are human hand motions.

14. The machine-readable medium of claim 9 , wherein the emitted one or more gestures is an overtake gesture when the detected one or more gestures is a yield gesture; and wherein the emitted one or more gestures is a yield gesture when the detected one or more gestures is an overtake gesture or an unrecognized gesture.

15. The machine-readable medium of claim 9 , wherein the gesture detection protocol and the gesture emission protocol include a predefined set of values, each of the values corresponding to a particular gesture.

16. The machine-readable medium of claim 9 , wherein the one or more vehicles are other autonomous vehicles; and wherein detecting the one or more gestures from the one or more vehicles comprises wirelessly receiving one or more signals indicative of the detected one or more gestures from the other autonomous vehicles.

17. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including:
generating one or more predicted trajectories based on sensor data received from one or more sensors of an autonomous vehicle, each of the predicted the predicted trajectories being associated with a probability,
detecting one or more gestures from one or more vehicles other than the autonomous vehicle in accordance with a gesture detection protocol,
emitting one or more gestures from the autonomous vehicle to communicate with the one or more vehicles in accordance with a gesture emission protocol based on the detected gestures,
modifying the predicted trajectories based on the detected gestures, the emitted gestures, and the associated probabilities of the predicted trajectories, and controlling the autonomous vehicle based on the modified predicted trajectories.

18. The system of claim 17 , wherein modifying the predicted trajectories includes removing a first set of trajectories from the predicted trajectories and producing a second set of trajectories.

19. The system of claim 18 , wherein producing the second set of trajectories includes timestamping each trajectory in the second set of trajectories based on the detected one or more gestures.

20. The system of claim 18 , wherein trajectories in the first set of trajectories have lower associated probabilities than trajectories in the second set of trajectories.

21. The system of claim 17 , wherein the one or more vehicles are non-autonomous vehicles; and the one or more gestures from the vehicles are human hand motions.

22. The system of claim 17 , wherein the emitted one or more gestures is an overtake gesture when the detected one or more gestures is a yield gesture; and wherein the emitted one or more gestures is a yield gesture when the detected one or more gestures is an overtake gesture or an unrecognized gesture.

23. The system of claim 17 , wherein the gesture detection protocol and the gesture emission protocol include a predefined set of values, each of the values corresponding to a particular gesture.

24. The system of claim 17 , wherein the one or more vehicles are other autonomous vehicles; and wherein detecting the one or more gestures from the one or more vehicles comprises wirelessly receiving one or more signals indicative

Assignees

• Baidu Usa Llc

Inventors

• Li Liyun
• Miao Jinghao
• Fang Shiyuan
• Yang I-Hsuan
• Wang Jingao

Classifications

• B60W2556/65

  Data transmitted between vehicles · CPC title

• B60W2554/00

  Input parameters relating to objects · CPC title

• B60Y2300/08

  Predicting or avoiding probable or impending collision · CPC title

• B60W30/095

  Predicting travel path or likelihood of collision · CPC title

• B60W50/0097

  Predicting future conditions · CPC title