Feedback for an autonomous vehicle

Patent metadata

Field	Value
Publication number	US-11318952-B2
Application number	US-201716479380-A
Country	US
Kind code	B2
Filing date	Jan 24, 2017
Priority date	Jan 24, 2017
Publication date	May 3, 2022
Grant date	May 3, 2022

Abstract

A controller receives sensor data during a ride and provides it to a server system. A passenger further provides feedback concerning the ride in the form of some or all of an overall rating, flagging of ride anomalies, and flagging of road anomalies. The sensor data and feedback are input to a training algorithm, such as a deep reinforcement learning algorithm, which updates an artificial intelligence (AI) model. The updated model is then propagated to controllers of one or more autonomous vehicle which then perform autonomous navigation and collision avoidance using the updated AI model.

First claim

The invention claimed is:

1. A method comprising, by a computer system:
receiving a first input from a first passenger of an autonomous vehicle, the first input including first feedback relating to a first portion of a first trip performed by the autonomous vehicle with the first passenger;
receiving a second input from a second passenger of an autonomous vehicle, the second input including second feedback relating to a first portion of a second trip performed by the autonomous vehicle with the second passenger, wherein the first portion of the first trip and the first portion of the second trip include a same location;
receiving sensor data from the autonomous vehicle relating to the first portion of the trip; and
updating an artificial intelligence (AI) model used by the autonomous vehicle for navigation based on the first feedback, the second feedback, and the sensor data.

2. The method of claim 1 , wherein updating the artificial intelligence (AI) model comprises updating the AI model using a deep reinforcement learning algorithm.

3. The method of claim 1 , wherein the first input includes a report of a driving anomaly.

4. The method of claim 1 , wherein the first input includes a report of a lane deviation.

5. The method of claim 1 , wherein the first input includes a report of a deviation during a turn.

6. The method of claim 1 , wherein receiving the first input comprises receiving the first input from a mobile device of the passenger.

7. The method of claim 6 , wherein receiving the first input comprises receiving a user selection of one or more locations on a map displayed on the mobile device and an indication that the one or more locations correspond to at least one of a road anomaly and a driving anomaly.

8. The method of claim 1 , wherein the sensor data includes outputs of at least one of a light detection and ranging (LIDAR) sensor, a radio detection and ranging (RADAR) sensor, and one or more cameras.

9. The method of claim 1 , further comprising:
receiving, by a controller of the autonomous vehicle, outputs of one or more sensors; and
autonomously driving, by the controller, the autonomous vehicle using the outputs processed according to the artificial intelligence (AI) model.

10. A system comprising one or more processing devices and one or more memory devices operably coupled to the one or more processing devices, the one or more memory devices storing executable code effective to cause the one or more processing devices to:
receive a first input from a first passenger of an autonomous vehicle, the first input including first feedback relating to a first portion of a first trip performed by the autonomous vehicle with the first passenger;
receive a second input from a second passenger of an autonomous vehicle, the second input including second feedback relating to a first portion of a second trip performed by the autonomous vehicle with the second passenger, wherein the first portion of the first trip and the first portion of the second trip include a same location;
receive sensor data from the autonomous vehicle relating to the first portion of the trip; and
update an artificial intelligence (AI) model used by the autonomous vehicle for navigation based on the first feedback, the second feedback, and the sensor data.

11. The system of claim 10 , wherein the executable code is further effective to cause the one or more processing devices to update the artificial intelligence (AI) model by updating the AI model using a deep reinforcement learning algorithm.

12. The system of claim 10 , wherein the first input includes a report of a driving anomaly.

13. The system of claim 10 , wherein the first input includes a report of a lane deviation.

14. The system of claim 10 , wherein the first input includes a report of deviation during a turn.

15. The system of claim 10 , wherein the executable code is further effective to cause the one or more processing devices to receive the first input by receiving the first input from a mobile device of the passenger.

16. The system of claim 15 , wherein the executable code is further effective to cause the one or more processing devices to receive the first input by receiving a user selection of one or more locations on a map displayed on the mobile device and an indication that the one or more locations correspond to at least one of a road anomaly and a driving anomaly.

17. The system of claim 10 , wherein the sensor data includes outputs of at least one of a light detection and ranging (LIDAR) sensor, a radio detection and ranging (RADAR) sensor, and one or more cameras.

18. The system of claim 10 , further comprising the autonomous vehicle comprising a controller, the controller being programmed to:
receive outputs of one or more sensors; and
autonomously drive the autonomous vehicle using the outputs processed according to the artificial intelligence (AI) model.

19. The method of claim 1 , wherein the first feedback and the second feedback indicate a negative experience in the first trip and second trip associated with the first portion, wherein the negative experience includes an action taken by the autonomous vehicle at the first portion or an external condition at the first portion.

20. The method of claim 19 , wherein updating an artificial intelligence (AI) model further includes reinforcing the AI model to avoid the action taken by the autonomous vehicle at the first portion.

Assignees

• Ford Global Tech Llc

Inventors

• Hotson Guy
• Moosaei Maryam
• Nariyambut Murali Vidya
• Jain Jinesh J

Classifications

• G06N3/092

  Reinforcement learning · CPC title

• B60W30/02

  Control of vehicle driving stability · CPC title

• B60W50/02 Primary

  Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures · CPC title

• B60W50/10

  Interpretation of driver requests or demands · CPC title

• B60W60/00253

  Taxi operations · CPC title