Green wave speed determination method, electronic device and storage medium

Patent metadata

Field	Value
Publication number	US-11798408-B2
Application number	US-202117532407-A
Country	US
Kind code	B2
Filing date	Nov 22, 2021
Priority date	May 31, 2021
Publication date	Oct 24, 2023
Grant date	Oct 24, 2023

Abstract

Provided are a green wave speed determination method, an electronic device and a storage medium, which relates to the field of artificial intelligence, particularly, the field of intelligent traffic technology. The implementation scheme is as follows: a stop position of a vehicle to be detected at an intersection and waiting time of an indicator light at the intersection are acquired; and a green wave speed of the vehicle to be detected is determined according to a traffic condition type, the stop position and the waiting time.

First claim

What is claimed is:

1. A green wave speed determination method, comprising:
acquiring a stop position of a to-be-detected vehicle at an intersection and waiting time of an indicator light at the intersection; and
determining a green wave speed of the to-be-detected vehicle according to a traffic condition type, the stop position and the waiting time;
wherein acquiring the stop position of the to-be-detected vehicle at the intersection comprises:
acquiring the traffic condition type of the intersection; and
screening out the stop position matching with the traffic condition type from a plurality of pre-calculated stop positions;
wherein before acquiring the stop position of the to-be-detected vehicle at the intersection, the method further comprises:
acquiring path sequences of historical vehicles passing through the intersection;
dividing the path sequences according to different traffic condition types to form a clear path sequence set corresponding to a clear traffic type and a congestion path sequence set corresponding to a congestion traffic type;
for each path sequence comprised in the congestion path sequence set, acquiring at least one queue tail position of a vehicle queuing queue corresponding to the path sequence, and determining a stop position matching with the congestion traffic type according to the at least one queue tail position; and
for each path sequence comprised in the clear path sequence set, dividing, according to a historical travel direction of the path sequence, the path sequence into a path sequence set of a right-turning travel direction, a path sequence set of a straight-traveling direction, or a path sequence set of a left-turning travel direction;

determining a key point of the historical travel direction in the path sequence corresponding to the historical travel direction, and determining a position of the key point as a stop position matching with the clear traffic type, wherein the key point is a speed point at which a vehicle speed changes in the travel direction, wherein the key point in straight-travelling is a position of a lowest speed point; and the key point in right turning or left turning is a position of a point with a largest change.

2. The method of claim 1 , wherein determining the green wave speed of the to-be-detected vehicle according to the traffic condition type, the stop position and the waiting time comprises:
calculating a travel distance between a current position of the to-be-detected vehicle and the stop position;
determining passing time of the to-be-detected vehicle according to the traffic condition type, a passing speed and the waiting time; and
calculating the green wave speed of the to-be-detected vehicle according to the travel distance and the passing time.

3. The method of claim 2 , wherein determining the passing time of the to-be-detected vehicle according to the traffic condition type, the passing speed and the waiting time comprises:
in a case where the traffic condition type is the congestion traffic type, determining a pre-counted queuing passing speed as the passing speed;
acquiring a queuing length between the stop position and the intersection; and
calculating the passing time of the to-be-detected vehicle according to the waiting time, the queuing length and the passing speed.

4. The method of claim 2 , wherein determining the passing time of the to-be-detected vehicle according to the traffic condition type, the passing speed and the waiting time comprises:
in a case where the traffic condition type is the clear traffic type, determining a pre-configured maximum passing speed as the passing speed;
calculating a ratio of the travel distance to the maximum passing speed, wherein the waiting time comprises a countdown and a timing period of the indicator light;
in a case where the ratio is less than or equal to the countdown, determining the countdown as the passing time of the to-be-detected vehicle; and
in a case where the ratio is greater than the countdown, determining a sum of the countdown and the timing period of the indicator light as the passing time of the to-be-detected vehicle.

5. The method of claim 1 , wherein screening out the stop position matching with the traffic condition type comprises:
in a case where the traffic condition type is the clear traffic type, screening out a stop position according to a predicted travel direction of the to-be-detected vehicle, and determining the stop position as the stop position matching with the traffic condition type.

6. The method of claim 1 , wherein determining the key point of the historical travel direction comprises:
in a case where the historical travel direction is turning, calculating a gradient of each position point in the path sequence, and determining a position point with a maximum gradient as a key point of the turning;
in a case where the historical travel direction is straight travelling, acquiring a travel speed of a road segment between two adjacent position points in the path sequence; and selecting one of two position points between which the travel speed is minimum as a key point of the straight travelling.

7. The method of claim 1 , wherein acquiring the waiting time of the indicator light at the intersection comprises:
acquiring a predicted travel direction of the to-be-detected vehicle;
determining a target indicator light in indicator lights of the intersection according to the predicted travel direction; and
acquiring at least one of a timing period or a countdown of the target indicator light, and determining the at least one of the timing period or the countdown as the waiting time of the indicator light at the intersection.

8. The method of claim 7 , wherein acquiring the predicted travel direction of the to-be-detected vehicle comprises:
acquiring historical tracks of the to-be-detected vehicle passing through the intersection, and determining travel directions of the historical tracks;
counting numbers of times that the to-be-detected vehicle passes through the intersection in different travel directions according to the travel directions of the historical tracks, and determining a weight of each of the different travel directions; and
determining the predicted travel direction of the to-be-detected vehicle according to the weight of each of the different travel directions.

9. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor;
wherein the memory stores an instruction executable by the at least one processor, and the instruction, when executed by the at least one processor, causes the at least one processor to perform the following steps:
acquiring a stop position of a to-be-detected vehicle at an intersection and waiting time of an indicator light at the intersection; and
determining a green wave speed of the to-be-detected vehicle according to a traffic condition type, the stop position and the waiting time;
wherein the at least one processor is caused to perform acquiring the stop position of the to-be-detected vehicle at the intersection by:
acquiring the traffic condition type of the intersection; and
screening out the stop position matching with the traffic condition type from a plurality of pre-calculated stop positions;
wherein the at least one processor is caused to further perform the following:
acquiring path sequences of historical vehicles passing through the intersection;
dividing the path sequences according to different traffic condition types to form a clear path sequence set corresponding to a clear traffic type and a congestion path sequence set corresponding to a congestion traffic type;
for each path sequence comprised in

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Wang Yile
• Yang Ning
• Zhang Chuanming

Classifications

• G08G1/0145 Primary

  for active traffic flow control · CPC title

• G08G1/0129

  for creating historical data or processing based on historical data · CPC title

• G08G1/052

  with provision for determining speed or overspeed {(speed measuring in general G01P)} · CPC title

• G08G1/081

  Plural intersections under common control · CPC title

• G08G1/0125 Primary

  Traffic data processing · CPC title