Vehicle traveling control method, electronic device, storage medium, chip and vehicle

Patent metadata

Field	Value
Publication number	US-2023399020-A1
Application number	US-202218072200-A
Country	US
Kind code	A1
Filing date	Nov 30, 2022
Priority date	Jun 14, 2022
Publication date	Dec 14, 2023
Grant date	—

Abstract

A vehicle traveling control method, the method includes: determining predicted motion features of a to-be-avoided object within a perception visual field of a vehicle; determining a safety level of the to-be-avoided object relative to the vehicle according to the predicted motion features and preset safety conditions; and determining a target deceleration of the vehicle according to an attribute feature of the to-be-avoided object and the corresponding safety level, and controlling traveling of the vehicle according to the target deceleration.

First claim

What is claimed is:

1 . A vehicle traveling control method, comprising:
determining predicted motion features of a to-be-avoided object within a perception visual field of a vehicle, wherein the predicted motion features comprise at least one of the following: a position relationship between a current position of the to-be-avoided object and a traveling lane of the vehicle, whether there is a predicted traveling path intersection between the to-be-avoided object with the vehicle, and a predicted position of the to-be-avoided object at the time that the vehicle decelerates to the predicted traveling path intersection at a maximum deceleration in a case that the predicted traveling path intersection exists; determining a safety level of the to-be-avoided object relative to the vehicle according to the predicted motion features and preset safety conditions; and determining a target deceleration of the vehicle according to an attribute feature of the to-be-avoided object and the corresponding safety level, and controlling traveling of the vehicle according to the target deceleration.

2 . The method according to claim 1 , wherein the attribute feature comprises a type of the to-be-avoided object and a historical motion feature in the perception visual field, and determining the target deceleration of the vehicle according to the attribute feature of the to-be-avoided object and the corresponding safety level comprises:
determining a distribution density of other road participants in the perception visual field of the vehicle according to the number of other road participants in the perception visual field of the vehicle and a visual field area of the perception visual field; determining a motion maneuvering feature of the to-be-avoided object according to the distribution density and the type of the to-be-avoided object; determining a target avoidance object from the to-be-avoided object according to the motion maneuvering feature of the to-be-avoided object and the corresponding safety level; and determining the target deceleration of the vehicle according to a historical motion feature of the target avoidance object in the perception visual field.

3 . The method according to claim 2 , wherein determining the target avoidance object from the to-be-avoided object according to the motion maneuvering feature of the to-be-avoided object and the corresponding safety level comprises:
determining a target safety level where the to-be-avoided object is located from a preset safety level according to the motion maneuvering feature of the to-be-avoided object and the corresponding safety level; and obtaining the target avoidance object by removing a to-be-avoided object whose target safety level is lower than a preset safety level threshold.

4 . The method according to claim 2 , wherein determining the motion maneuvering feature of the to-be-avoided object according to the distribution density and the type of the to-be-avoided object comprises:
matching a corresponding predicted moving speed for the to-be-avoided object according to the distribution density and the type of the to-be-avoided object; determining visual angle information of the to-be-avoided object according to a historical motion track of the to-be-avoided object in the perception visual field; and determining the motion maneuvering feature of the to-be-avoided object according to the predicted moving speed and the visual angle information.

5 . The method according to claim 1 , wherein the preset safety conditions comprise:
whether a current position of the to-be-avoided object is in the traveling lane of the vehicle.

6 . The method according to claim 1 , wherein the preset safety conditions comprise:
whether the to-be-avoided object has the predicted traveling path intersection with the vehicle.

7 . The method according to claim 1 , wherein the preset safety conditions comprise:
a distance between the predicted traveling path intersection and the vehicle in a case that predicted traveling path intersection exists.

8 . The method according to claim 1 , wherein the preset safety conditions comprise:
whether a distance between the predicted position of the to-be-avoided object and the predicted traveling path intersection meets a preset safety distance at a time of the vehicle decelerating to the predicted traveling path intersection at the maximum deceleration in a case that the predicted traveling path intersection exists.

9 . The method according to claim 1 , wherein there are the plurality of predicted motion features and preset safety conditions, and determining the safety level of the to-be-avoided object relative to the vehicle according to the predicted motion features and the preset safety conditions comprises:
determining a safety score corresponding to the predicted motion feature according to whether any predicted motion feature of the to-be-avoided object meets the corresponding preset safety condition; and determining the safety level of the to-be-avoided object relative to the vehicle through weighted sum according to a weight value preset for each safety condition and the safety score.

10 . An electronic device, comprising:
a processor; and a memory for storing an executable instruction of the processor; wherein the processor is configured to: determine predicted motion features of a to-be-avoided object within a perception visual field of a vehicle, wherein the predicted motion features comprise at least one of the following: a position relationship between a current position of the to-be-avoided object and a traveling lane of the vehicle, whether there is a predicted traveling path intersection between the to-be-avoided object with the vehicle, and a predicted position of the to-be-avoided object at the time that the vehicle decelerates to the predicted traveling path intersection at a maximum deceleration in a case that the predicted traveling path intersection exists; determine a safety level of the to-be-avoided object relative to the vehicle according to the predicted motion features and preset safety conditions; and determine a target deceleration of the vehicle according to an attribute feature of the to-be-avoided object and the corresponding safety level, and control traveling of the vehicle according to the target deceleration.

11 . The electronic device according to claim 10 , wherein the attribute feature comprises a type of the to-be-avoided object and a historical motion feature in the perception visual field, and the processor is configured to:
determine a distribution density of other road participants in the perception visual field of the vehicle according to the number of other road participants in the perception visual field of the vehicle and a visual field area of the perception visual field; determine a motion maneuvering feature of the to-be-avoided object according to the distribution density and the type of the to-be-avoided object; determine a target avoidance object from the to-be-avoided object according to the motion maneuvering feature of the to-be-avoided object and the corresponding safety level; and determine the target deceleration of the vehicle according to a historical motion feature of the target avoidance object in the perception visual field.

12 . The electronic device according to claim 11 , wherein the processor is configured to:
determine a target safety level where the to-be-avoided object is located from a preset safety level according to the motion maneuvering feature of the to-be-avoided object and the corresponding safety level; and obtain the target avoidance object by removing a to-be-avoided object wh

Assignees

• Xiaomi Ev Tech Co Ltd

Inventors

• Shi Liang
• Zhang Chi

Classifications

• B60W60/0015 Primary

  specially adapted for safety · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W2554/4041

  Position · CPC title

• B60W2554/80

  Spatial relation or speed relative to objects · CPC title

• B60W30/09 Primary

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title