Driving information prediction method, apparatus and autonomous vehicle

Patent metadata

Field	Value
Publication number	US-2026091782-A1
Application number	US-202519410659-A
Country	US
Kind code	A1
Filing date	Dec 5, 2025
Priority date	Dec 13, 2024
Publication date	Apr 2, 2026
Grant date	—

Abstract

Provided is a driving information prediction method, apparatus, and autonomous driving vehicle, which relate to the field of autonomous driving, especially to the field of artificial intelligence, and particularly to the technical fields of autonomous driving and intelligent transportation. The method includes: determining a first leader-follower relationship between a target vehicle and a first obstacle based on a motion parameter of the target vehicle at a current moment, path information of the target vehicle within a first time period, a motion parameter of the first obstacle at the current moment, and predicted path information of the first obstacle within the first time period; obtaining first predicted driving information based on the first leader-follower relationship; and determining first optimal driving information based on an evaluation result corresponding to the first predicted driving information.

First claim

What is claimed is:

1 . A driving information prediction method, comprising:
determining a first leader-follower relationship between a target vehicle and a first obstacle based on a motion parameter of the target vehicle at a current moment, path information of the target vehicle within a first time period, a motion parameter of the first obstacle at the current moment, and predicted path information of the first obstacle within the first time period; obtaining first predicted driving information based on the first leader-follower relationship, wherein the first predicted driving information comprises: first predicted motion parameters of the target vehicle at a plurality of prediction moments within the first time period, and second predicted motion parameters of the first obstacle at the plurality of prediction moments within the first time period; and determining first optimal driving information based on an evaluation result corresponding to the first predicted driving information, wherein the first optimal driving information comprises: optimal predicted motion parameters of the target vehicle at the plurality of prediction moments within the first time period, and optimal predicted motion parameters of the first obstacle at the plurality of prediction moments within the first time period.

2 . The method of claim 1 , wherein the determining of the first optimal driving information based on the evaluation result corresponding to the first predicted driving information comprises one of:
in response to the evaluation result corresponding to the first predicted driving information satisfying a first condition, using the first predicted driving information as the first optimal driving information; and in response to the evaluation result corresponding to the first predicted driving information not satisfying the first condition, alternating the first leader-follower relationship to obtain a second leader-follower relationship between the target vehicle and the first obstacle, obtaining second predicted driving information based on the second leader-follower relationship, and determining the first optimal driving information from the first predicted driving information and the second predicted driving information based on an evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information.

3 . The method of claim 2 , wherein the first condition comprises at least one of: a first safety evaluation value in the evaluation result corresponding to the first predicted driving information is higher than a safety threshold, or a first somatosensory evaluation value in the evaluation result corresponding to the first predicted driving information is higher than a somatosensory evaluation threshold.

4 . The method of claim 1 , wherein the determining of the first optimal driving information based on the evaluation result corresponding to the first predicted driving information comprises:
alternating the first leader-follower relationship to obtain a second leader-follower relationship between the target vehicle and the first obstacle; obtaining second predicted driving information based on the second leader-follower relationship; and determining, from the first predicted driving information and the second predicted driving information, the first optimal driving information based on an evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information.

5 . The method of claim 2 , wherein the second predicted driving information comprises: third predicted motion parameters of the target vehicle at the plurality of prediction moments within the first time period, and fourth predicted motion parameters of the first obstacle at the plurality of prediction moments within the first time period.

6 . The method of claim 2 , further comprising at least one of:
calculating to obtain a first safety evaluation value in the evaluation result corresponding to the first predicted driving information based on a safety evaluation formula, the first leader-follower relationship and the first predicted driving information; calculating to obtain a first somatosensory evaluation value in the evaluation result corresponding to the first predicted driving information based on a somatosensory evaluation formula, the first leader-follower relationship and the first predicted driving information; calculating to obtain a second safety evaluation value in the evaluation result corresponding to the second predicted driving information based on the safety evaluation formula, the second leader-follower relationship and the second predicted driving information; or calculating to obtain a second somatosensory evaluation value in the evaluation result corresponding to the second predicted driving information based on the somatosensory evaluation formula, the second leader-follower relationship, and the second predicted driving information.

7 . The method of claim 2 , wherein the determining of, from the first predicted driving information and the second predicted driving information, the first optimal driving information based on the evaluation result corresponding to the second predicted driving information and the evaluation result corresponding to the first predicted driving information comprises:
determining a first reference value corresponding to the first predicted driving information based on the evaluation result corresponding to the first predicted driving information; determining a second reference value corresponding to the second predicted driving information based on the evaluation result corresponding to the second predicted driving information; and selecting, from the first predicted driving information and the second predicted driving information, the first optimal driving information based on a maximum value in the first reference value and the second reference value.

8 . The method of claim 1 , wherein the obtaining of the first predicted driving information based on the first leader-follower relationship comprises:
performing forward simulation based on the first leader-follower relationship, the motion parameter of the target vehicle at the current moment, and the motion parameter of the first obstacle at the current moment, to obtain the first predicted motion parameters of the target vehicle at the plurality of prediction moments within the first time period and the second predicted motion parameters of the first obstacle at the plurality of prediction moments within the first time period; and using the first predicted motion parameters of the target vehicle at the plurality of prediction moments within the first time period and the second predicted motion parameters of the first obstacle at the plurality of prediction moments within the first time period as the first predicted driving information.

9 . The method of claim 2 , wherein the obtaining of the second predicted driving information based on the second leader-follower relationship comprises:
performing forward simulation based on the second leader-follower relationship, the motion parameter of the target vehicle at the current moment, and the motion parameter of the first obstacle at the current moment, to obtain third predicted motion parameters of the target vehicle at the plurality of prediction moments within the first time period and fourth predicted motion parameters of the first obstacle at the plurality of prediction moments within the first time period; and using the third predicted motion parameters of the target vehicle at the plurality of prediction moments within the first time

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Cao Zhihui
• Pan Hongfei
• Gao Han
• Xie Yuanfan

Classifications

• B60W50/0097

  Predicting future conditions · CPC title

• B60W30/0956

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

• B60W2554/4045

  Intention, e.g. lane change or imminent movement · CPC title

• B60W60/00274

  considering possible movement changes · CPC title

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title