Directed alert notification by autonomous-driving vehicle

• US 10,460,577 B2
• Filed: 02/28/2018
• Issued: 10/29/2019
• Est. Priority Date: 02/28/2018
• Status: Active Grant

• Current Assignee: Pony.ai, Inc.
• Original Assignee: Pony.ai, Inc.
• Inventors: Song, Hao, Zhang, Zhuo, Xiao, Sinan, Yu, Xiang, Lou, Tiancheng, Peng, Jun, Hou, Jie, Li, Tianyi, Liu, Yiming
• Primary Examiner(s): Haile, Benyam
• Application Number:
  US15/908,272
• Publication Number:
  US 20190266859A1
• Time in Patent Office: 608 Days
• CPC Class Codes: B60Q 1/506 specific to silent vehicles, e.g. for warning that a hybrid or electric vehicle is approaching
• CPC Class Codes: B60Q 1/507 specific to autonomous vehicles
• CPC Class Codes: B60Q 1/525 automatically indicating risk of collision between vehicles in traffic or with pedestrians, e.g. after risk assessment using the vehicle sensor data
• CPC Class Codes: B60Q 2400/50 Projected symbol or information, e.g. onto the road or car body
• CPC Class Codes: B60Q 5/005 automatically actuated
• CPC Class Codes: B60Q 5/006 indicating risk of collision between vehicles or with pedestrians
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• CPC Class Codes: B60R 21/34 Protecting non-occupants of a vehicle, e.g. pedestrians B60R19/02 takes precedence
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/095 Predicting travel path or likelihood of collision
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: G01S 19/51 Relative positioning
• 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
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0248 in combination with a laser lasers per se H01S
• CPC Class Codes: G08B 7/06 using electric transmission , e.g. involving audible and visible signalling through the use of sound and light sources
• CPC Class Codes: G08G 1/005 including pedestrian guidance indicator
• CPC Class Codes: G08G 1/16 : Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: G08G 1/166 : for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A system included and a computer-implemented method performed in an autonomous-driving vehicle are described. The system performs: detecting one or more movable objects; determining a target movable object from the one or more detected objects; determining a manner of generating a directed alert notification selectively toward the target movable object; and causing a directed alert notification of the determined manner to be generated toward the target movable object.

Claims

1. A system for an autonomous-driving vehicle, comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the one or more processors to;

detect one or more movable objects;

determine a target movable object from the one or more detected movable objects;

determine a manner of generating a directed alert notification selectively toward the target movable object; and

cause a directed alert notification of the determined manner to be generated toward the target movable object, wherein the determining the target movable object comprises;

determining a risk of a traffic incident caused by each of the one or more movable objects; and

selecting a movable object determined to have a highest risk as the target movable object; and

wherein the determining the manner of generating the directed alert notification selectively toward the target movable object comprises;

determining an item or a position that the target movable object is looking at and generating the directed alert notification directly to the item or the position without harming the target movable object.

2. The system of claim 1, wherein the instructions cause the one or more processors to:

determine a vehicle route of the autonomous-driving vehicle;

determine predicted moving paths of the detected one or more movable objects;

determine one or more of the detected movable objects that are predicted to be within a predetermined distance from the autonomous-driving vehicle as one or more candidate movable objects, based on the vehicle route and the predicted moving paths of the one or more movable objects; and

determine the target movable object from the one or more candidate movable objects.

3. The system of claim 1, wherein the instructions cause the one or more processors to determine one or more perceptibility parameters corresponding to the target movable object at least based on a portion of image data corresponding to the target movable object.

4. The system of claim 3, wherein the one or more perceptibility parameters comprises at least one of a visual perceptibility level, an acoustic perceptibility level, a somatosensory perceptibility level, and a via-electronic-device perceptibility level.

5. The system of claim 3, wherein the instructions cause the one or more processors to determine the one or more perceptibility parameters corresponding to the target movable object also based on one or more environmental attributes, including one or more of weather condition, an ambient brightness level, and an ambient noise level.

6. The system of claim 3, wherein the manner of generating a directed alert notification comprises a type of the directed alert notification, and

the instructions cause the one or more processors to further select the type of the directed alert notification from a group including one or more of a visual directed alert notification, an acoustic directed alert notification, a somatosensory directed alert notification, and an electromagnetic directed alert notification, at least based on the one or more perceptibility parameters.

7. The system of claim 3, wherein the manner of generating a directed alert notification comprises a position to which the directed alert notification is directed, and

the instructions cause the one or more processors to further determine the position to which the directed alert notification is directed, at least based on the one or more perceptibility parameters.

8. The system of claim 3, wherein the manner of generating a directed alert notification comprises timing at which the directed alert notification is generated, and

the instructions cause the one or more processors to further determine the timing at which the directed alert notification is generated, at least based on the one or more perceptibility parameters.

9. The system of claim 1, wherein the target movable object is one of a pedestrian, a person on a human-powered vehicle, a person on a motor vehicle, and an animal.

10. The system of claim 1, wherein the instructions cause the one or more processors to:

determine a predicted movement of the target movable object in response to the directed alert notification; and

control a locomotive mechanism of the autonomous-driving vehicle based on the predicted movement of the target movable object.

11. A computer-implemented method performed in an autonomous-driving vehicle comprising:

detecting one or more movable objects;

determining a target movable object from the one or more detected movable objects, comprising;

determining a risk of a traffic incident caused by each of the one or more movable objects; and

selecting a movable object determined to have a highest risk as the target movable object;

determining a manner of generating a directed alert notification selectively toward the target movable object, comprising;

determining an item or a position that the target movable object is looking at and generating the directed alert notification directly to the item or the position without harming the target movable object; and

causing a directed alert notification of the determined manner to be generated toward the target movable object.

12. The computer-implemented method of claim 11, wherein said determining the target movable object comprises:

determining a vehicle route of the autonomous-driving vehicle;

determining predicted moving paths of the detected one or more movable objects;

determining one or more of the detected one or more movable objects that are predicted to be within a predetermined distance from the autonomous-driving vehicle as one or more candidate movable objects, based on the vehicle route and the predicted moving paths of the one or more movable objects; and

determining the target movable object from the one or more candidate movable objects.

13. The computer-implemented method of claim 11, further comprising determining one or more perceptibility parameters corresponding to the target movable object at least based on a portion of image data corresponding to the target movable object.

14. The computer-implemented method of claim 13, wherein the one or more perceptibility parameters comprises at least one of a visual perceptibility level, an acoustic perceptibility level, a somatosensory perceptibility level, and a via-electronic-device perceptibility level.

15. The computer-implemented method of claim 13, wherein the one or more perceptibility parameters corresponding to the target movable object are determined also based on one or more environmental attributes, including one or more of weather condition, an ambient brightness level, and an ambient noise level.

16. The computer-implemented method of claim 13, wherein the manner of generating a directed alert notification comprises a type of the directed alert notification, and said determining the manner of generating the directed alert notification comprises selecting the type of the directed alert notification from a group including one or more of a visual directed alert notification, an acoustic directed alert notification, a somatosensory directed alert notification, and an electromagnetic directed alert notification, at least based on the one or more perceptibility parameters.

17. The computer-implemented method of claim 13, wherein the manner of generating a directed alert notification comprises a position to which the directed alert notification is directed, and said determining the manner of generating the directed alert notification comprises determining the timing at which the directed alert notification is generated, at least based on the one or more perceptibility parameters.

18. The computer-implemented method of claim 13, wherein the manner of generating a directed alert notification comprises timing at which the directed alert notification is generated, and said determining the manner of generating the directed alert notification comprises determining the timing at which the directed alert notification is generated, at least based on the one or more perceptibility parameters.

19. The computer-implemented method of claim 11, wherein the target movable object is one of a pedestrian, a person on a human-powered vehicle, a person on a motor vehicle, and an animal.

20. The computer-implemented method of claim 11, further comprising:

determining a predicted movement of the target movable object in response to the directed alert notification; and

controlling a locomotive mechanism of the autonomous-driving vehicle based on the predicted movement of the target movable object.