Pass route planning method and apparatus, device and readable storage medium

Patent metadata

Field	Value
Publication number	US-2020183401-A1
Application number	US-201916703999-A
Country	US
Kind code	A1
Filing date	Dec 5, 2019
Priority date	Dec 5, 2018
Publication date	Jun 11, 2020
Grant date	—

Abstract

Provided are a pass route planning method and apparatus, a device and a readable storage medium. The method includes: obtaining current road environment information in front of a vehicle; determining a current passable area according to the current road environment information; setting pass candidate points in the current passable area; and determining a current optimal passable route according to the pass candidate points. Firstly, the passable area is determined, and then the pass candidate points are set in the passable area, and thus the current optimal passable route is calculated according to the pass candidate points in the passable area, which can effectively reduce a calculation amount of unreachable pass routes in the prior art in which candidate points are set in all areas directly in front of an unmanned vehicle, thereby reducing a calculation amount for planning a pass route and improving a planning speed of the pass route.

First claim

What is claimed is:

1 . A pass route planning method, comprising:
obtaining current road environment information in front of a vehicle; determining a current passable area according to the current road environment information; setting pass candidate points in the current passable area; and determining a current optimal passable route according to the pass candidate points.

2 . The method according to claim 1 , wherein after the determining a current passable area according to the current road environment information, the method further comprises:
if there are multiple current passable areas, determining a current optimal passable area from the current passable areas according to an optimal area selection policy; correspondingly, the setting pass candidate points in the current passable area is: setting the pass candidate points in the current optimal passable area.

3 . The method according to claim 2 , wherein the determining a current passable area according to the current road environment information comprises:
determining multiple current passable subareas from a current starting position to a current target position according to the current road environment information; and determining at least one current passable area according to the multiple current passable subareas arranged in order from the current start position to the current target position.

4 . The method according to claim 3 , wherein the setting the pass candidate points in the current optimal passable area is:
setting the pass candidate points in the current optimal passable area according to a candidate point setting policy.

5 . The method according to claim 4 , wherein the setting the pass candidate points in the current optimal passable area according to a candidate point setting policy comprises:
setting the pass candidate points according to a first density in a first preset area near a moving vehicle obstacle in the current optimal passable area.

6 . The method according to claim 5 , wherein the setting the pass candidate points in the current optimal passable area according to a candidate point setting policy further comprises:
setting the pass candidate points according to a second density in a second preset area away from the moving vehicle obstacle in the current optimal passable area, wherein the first density is greater than the second density.

7 . The method according to claim 1 , wherein the determining a current optimal passable route according to the pass candidate points comprises:
calculating multiple current passable routes according to the pass candidate points; determining the current optimal passable route from the multiple current passable routes according to an optimal route selection policy.

8 . The method according to claim 7 , wherein the calculating multiple current passable routes according to the pass candidate points is:
calculating the multiple current passable routes according to the pass candidate points using a route determining algorithm.

9 . The method according to claim 7 , wherein the determining the current optimal passable route from the multiple current passable routes according to an optimal route selection policy comprises:
calculating safety indicators and/or comfort indicators corresponding to the multiple current passable routes; determining the current optimal passable route from the multiple current passable routes according to the safety indicators and/or the comfort indicators corresponding to the multiple current passable routes.

10 . The method according to claim 9 , wherein each of the safety indicators at least comprises: a distance indicator of a current passable route with respect to a moving vehicle obstacle and lane lines; and each of the comfort indicators at least comprises: a curvature indicator of the current passable route.

11 . A pass route planning apparatus, comprising:
a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor, when running the computer program, is configured to: obtain current road environment information in front of a vehicle; determine a current passable area according to the current road environment information; set pass candidate points in the current passable area; and determine a current optimal passable route according to the pass candidate points.

12 . The pass route planning apparatus according to claim 11 , wherein the processor is further configured to:
if there are multiple current passable areas, determine a current optimal passable area from the current passable areas according to an optimal area selection policy; and set the pass candidate points in the current optimal passable area.

13 . The pass route planning apparatus according to claim 12 , wherein the processor is further configured to
determine multiple current passable subareas from a current starting position to a current target position according to the current road environment information; and determine at least one current passable area according to the multiple current passable subareas arranged in order from the current start position to the current target position.

14 . The pass route planning apparatus according to claim 13 , wherein the processor is further configured to set the pass candidate points in the current optimal passable area according to a candidate point setting policy.

15 . The pass route planning apparatus according to claim 14 , wherein the processor is further configured to:
set the pass candidate points according to a first density in a first preset area near a moving vehicle obstacle in the current optimal passable area, and set the pass candidate points according to a second density in a second preset area away from the moving vehicle obstacle in the current optimal passable area, wherein the first density is greater than the second density.

16 . The pass route planning apparatus according to claim 11 , wherein the processor is further configured to:
calculate multiple current passable routes according to the pass candidate points, and determine the current optimal passable route from the multiple current passable routes according to an optimal route selection policy.

17 . The pass route planning apparatus according to claim 16 , wherein the processor is further configured to calculate the multiple current passable routes according to the pass candidate points using a route determining algorithm.

18 . The pass route planning apparatus according to claim 16 , wherein the processor is further configured to:
calculate safety indicators and/or comfort indicators corresponding to the multiple current passable routes; and determine the current optimal passable route from the multiple current passable routes according to the safety indicators and/or the comfort indicators corresponding to the multiple current passable routes.

19 . The pass route planning apparatus according to claim 18 , wherein each of the safety indicators at least comprises: a distance indicator of a current passable route with respect to a moving vehicle obstacle and lane lines; and each of the comfort indicators at least comprises: a curvature indicator of the current passable route.

20 . A nonvolatile memory with a computer program stored thereon, wherein the computer program is executed by a processor to implement the method according to claim 1 .

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Yang Fan
• Zhu Fan
• Zhu Weicheng
• Lv Leibing
• Ma Lin
• Yu Ning
• Liu Bei

Classifications

• G08G1/167 Primary

  Driving aids for lane monitoring, lane changing, e.g. blind spot detection · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• G05D1/0212 Primary

  with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287) · CPC title

• G05D2201/0213

  Physics · mapped topic

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title