Vehicle control method and apparatus, device and computer storage medium

Patent metadata

Field	Value
Publication number	US-12183196-B2
Application number	US-202117753817-A
Country	US
Kind code	B2
Filing date	Nov 17, 2021
Priority date	Jun 22, 2021
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

A vehicle control method and apparatus, a device and a computer storage medium are disclosed, which relates to the technical fields of autonomous driving and intelligent transportation. A specific implementation solution involves: determining vehicles in a preset geo-fencing region; determining a vehicle weight of each said vehicles according to a vehicle type and a waiting duration of each said vehicles; estimating, according to the vehicle weights of the vehicles in each of lanes in the geo-fencing region and positions of the vehicles in each said lanes, a duration to be waited in each said lanes; and generating a control instruction for each said vehicles according to the respective durations to be waited in each said lanes and the respective positions of the vehicles in each said lanes, the control instruction including a state instruction and/or a target speed instruction.

First claim

What is claimed is:

1. A method for vehicle control, comprising:
determining vehicles in a preset geo-fencing region including N lanes, the included lanes having a length of I threshold , where N is an integer greater than 1;
determining a vehicle weight of each of the vehicles according to a vehicle type and a waiting duration of each of the vehicles, the vehicle weight reflecting a priority of passage of a vehicle, and the waiting duration being a duration that has been waited from the time when the vehicle entered a respective lane;
estimating, according to the vehicle weights of the vehicles in each of the lanes in the geo-fencing region and positions of the vehicles in each of the lanes, a duration to be waited in each of the lanes, comprising: determining a lane weight of each of the lanes according to the vehicle weights of the vehicles in the lanes in the geo-fencing region; and determining, for a first lane with the highest weight, the duration to be waited in the first lane as zero; and for other lanes, determining queuing weights of the vehicles in the other lanes according to the vehicle weights of the vehicles in the other lanes; determining a number of vehicles to be waited by first vehicles in the lanes according to the queuing weights of the vehicles in the lanes, each queuing weight of the vehicles being an average value of weights of a first vehicle and subsequent vehicles after the first vehicle in the lane; and determining durations to be waited in the lanes according to the number of vehicles to be waited by the first vehicles in the lanes and unit time for the vehicles to pass; and
generating a control instruction for each of the vehicles according to the respective durations to be waited in each of the lanes and the respective positions of the vehicles in each of the lanes, the control instruction comprising a state instruction and a target speed instruction, wherein the state instruction indicates what state each vehicle is in, comprising start, keep, slow and stop, and the target speed instruction indicates what speed each vehicle has achieved.

2. The method according to claim 1 , wherein the step of determining vehicles in a preset geo-fencing region comprises: determining vehicle positions, determining whether the vehicle positions fall within the preset geo-fencing region, and determining a road side unit corresponding to the geo-fencing region; and
the method further comprises:
sending the control instructions to corresponding vehicles through the road side unit corresponding to the geo-fencing region.

3. The method according to claim 1 , further comprising:
acquiring information of the lanes of the vehicles determined by on board unit combined cameras of the vehicles; or
acquiring information of the lanes of the vehicles determined by the vehicles according to vehicle positioning results and lane-level map data; or
acquiring vehicle positioning results, and determining information of the lanes of the vehicles according to lane-level map data deployed in a mobile edge computing device.

4. The method according to claim 1 , wherein the step of generating a control instruction for each of the vehicles according to the respective durations to be waited in each of the lanes and the respective positions of the vehicles in each of the lanes comprises:
generating a start instruction for a vehicle if a current speed of the vehicle is zero, a duration for the vehicle to wait in the lane is zero, and the vehicle is at a first place in the lane;
generating the start instruction for the vehicle if an estimated start speed of the vehicle is greater than or equal to a preset maximum speed threshold, the estimated start speed being a maximum speed at which the vehicle can be assumed to start and being related to a front spacing of the vehicle and the duration for the vehicle to wait in the lane;
generating the start instruction for the vehicle if a front spacing of the vehicle is greater than or equal to a preset maximum spacing threshold;
generating a keep instruction for the vehicle if the estimated start speed of the vehicle is greater than or equal to the current speed of the vehicle;
generating a slow instruction for the vehicle if the estimated start speed of the vehicle is less than the current speed of the vehicle and greater than a preset minimum speed threshold;
generating a stop instruction for the vehicle if the estimated start speed of the vehicle is less than or equal to the preset minimum speed threshold; and
generating the stop instruction for the vehicle if the front spacing of the vehicle is less than or equal to a preset minimum spacing threshold;
wherein the estimated start speed of the vehicle is determined by the front spacing of the vehicle and the duration for the vehicle to wait in the lane.

5. The method according to claim 1 , wherein the step of generating a control instruction for each of the said vehicles according to the respective durations to be waited in each of the lanes and the respective positions of the vehicles in each of the lanes comprises:
determining a target speed of a vehicle as a preset regular speed if a current speed of the vehicle is zero, a duration for the vehicle to wait in the lane is zero, and the vehicle is at a first place in the lane;
determining the target speed of the vehicle as the preset regular speed if an estimated start speed of the vehicle is greater than or equal to a preset maximum speed threshold, the estimated start speed being a maximum speed at which the vehicle can be assumed to start and being related to a front spacing of the vehicle and the duration for the vehicle to wait in the lane;
determining the target speed of the vehicle as the preset regular speed if a front spacing of the vehicle is greater than or equal to a preset maximum spacing threshold;
determining the target speed of the vehicle as the current speed if the estimated start speed of the vehicle is greater than or equal to the current speed of the vehicle;
determining the target speed of the vehicle as the estimated start speed of the vehicle if the estimated start speed of the vehicle is less than the current speed of the vehicle and greater than a preset minimum speed threshold, the estimated start speed of the vehicle being determined by the front spacing of the vehicle and the duration for the vehicle to wait in the lane;
determining the target speed of the vehicle as zero if the estimated start speed of the vehicle is less than or equal to the preset minimum speed threshold; and
determining the target speed of the vehicle as zero if the front spacing of the vehicle is less than or equal to a preset minimum spacing threshold.

6. An electronic device, comprising:
at least one processor; and
a memory communicatively connected with the at least one processor;
wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a method for vehicle control, wherein the method comprises:
determining vehicles in a preset geo-fencing region including N lanes, the included lanes having a length of I threshold , where N is an integer greater than 1;
determining a vehicle weight of each of the vehicles according to a vehicle type and a waiting duration of each of the vehicles, the vehicle weight reflecting a priority of passage of a vehicle, and the waiting duration being a duration that has been waited from the time when the vehicle entered a respective lane;
estimating, according to the vehicle weights of the vehicles in each of the lanes in the geo-fencing region and positions of the vehicles in each of the lanes, a duration to be waited in each of the lanes, comprising: determining a lane weight of ea

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Huang Jizhou
• Xia Deguo
• Wang Haifeng

Classifications

• G08G1/096783

  where the origin of the information is a roadside individual element · CPC title

• G08G1/08

  according to detected number or speed of vehicles · CPC title

• G08G1/0133

  for classifying traffic situation · CPC title

• B60W40/04 Primary

  Traffic conditions · CPC title

• B60W30/18018 Primary

  Start-stop drive, e.g. in a traffic jam · CPC title