US 11,698,638 B2Granted

System and method for predictive path planning in autonomous vehicles

AssigneeHuawei Technologies Co., Ltd.

InventorsPeyman Yadmellat, Mohsen Rohani

Life of this patent

Estimating the term…

Loading patent…

Abstract

A processor-implemented method and system for determining a predictive occupancy grid map (OGM) for an autonomous vehicle are disclosed. The method includes: receiving a set of OGMs including a current predicted OGM and one or more future predicted OGMs, the current OGM associated with a current timestamp and each future predicted OGM associated with a future timestamp; generating a weight map associated with the current timestamp based on one or more kinodynamic parameters of the vehicle at the current time stamp, and one or more weight map associated with a future timestamp; generating a set of filtered predicted OGMs by filtering the current predicted OGM with the weight map associated the current timestamp and filtering each respective future predicted OGM associated with a future timestamp with the weight map associated with the respective future timestamp; and sending a single predicted OGM to a trajectory generator.

Claims21

Dependent claims

A processor-implemented method of motion planning for an autonomous vehicle, the method comprising:

receiving a set of predicted occupancy grid maps (OGMs), the set of predicted OGMs including a current predicted OGM and one or more future predicted OGMs, the current predicted OGM associated with a current timestamp and each future predicted OGM associated with a respective future timestamp;
generating a current weight map associated with the current timestamp based on one or more kinodynamic parameters of the autonomous vehicle at the current timestamp and a future weight map associated with each respective future timestamp based on one or more kinodynamic parameters of the autonomous vehicle at the respective future timestamp;
generating a set of area of interest maps comprising a current area of interest map associated with the current timestamp and a future area of interest map associated with each respective future timestamp;
generating a set of filtered weight maps by filtering the current weight map with the current area of interest map and filtering each future weight map with a respective future area of interest map;
generating a set of filtered predicted OGMs by filtering the current predicted OGM with a current filtered weight map associated the current timestamp to generate a filtered current predicted OGM and filtering each future predicted OGM with a future filtered weight map associated with the respective future timestamp to generate one or more filtered future predicted OGMs;
generating a single predicted OGM representative of the set of filtered predicted OGMs by combining the filtered current predicted OGM and each filtered future predicted OGM in the set of filtered predicted OGMs;
and
generating a trajectory for the autonomous vehicle to follow based on the single predicted OGM.

5 more elements

A processor-implemented method of motion planning for an autonomous vehicle, the method comprising:

receiving a set of predicted occupancy grid maps (OGMs), the set of predicted OGMs including a current predicted OGM and one or more future predicted OGMs, the current predicted OGM associated with a current timestamp and each future predicted OGM associated with a respective future timestamp;
generating a current weight map associated with the current timestamp based on one or more kinodynamic parameters of the autonomous vehicle at the current timestamp and a future weight map associated with each respective future timestamp based on one or more kinodynamic parameters of the autonomous vehicle at the respective future timestamp;
generating a current area of interest map associated with the current timestamp and a future area of interest map associated with each respective future timestamp;
generating a set of first filtered predicted OGMs by filtering the current predicted OGM with the current weight map associated the current timestamp to generate a first filtered current predicted OGM and filtering each future predicted OGM with the future weight map associated with the respective future timestamp to generate one or more first filtered future predicted OGMs;
generating a set of second filtered predicted OGMs by filtering the first filtered current predicted OGM with the current area of interest map associated the current timestamp to generate a second filtered current predicted OGM and filtering each first filtered future predicted OGM with the future area of interest map associated with the respective future timestamp to generate one or more second filtered future predicted OGMs;
generating a single predicted OGM representative of the second set of filtered predicted OGMs by combining the second filtered current predicted OGM and each second filtered future predicted OGM in the set of second filtered predicted OGMs;
and
generating a trajectory for the autonomous vehicle to follow based on the single predicted OGM.

5 more elements

A processor-implemented method of motion planning for an autonomous vehicle, the method comprising:

receiving a set of predicted occupancy grid maps (OGMs), the set of predicted OGMs including a current predicted OGM and one or more future predicted OGMs, the current predicted OGM associated with a current timestamp and each future predicted OGM associated with a respective future timestamp;
generating a current weight map associated with the current timestamp based on one or more kinodynamic parameters of the autonomous vehicle at the current timestamp and a future weight map associated with each respective future timestamp based on one or more kinodynamic parameters of the autonomous vehicle at the respective future timestamp;
generating a current area of interest map associated with the current timestamp and a future area of interest map associated with each respective future timestamp;
generating a set of first filtered predicted OGMs by filtering the current predicted OGM with the current area of interest map associated the current timestamp to generate a first filtered current predicted OGM and filtering each future predicted OGM with the future area of interest map associated with the respective future timestamp to generate one or more first filtered future predicted OGMs;
generating a set of second filtered predicted OGMs by filtering the first filtered current predicted OGM with the current weight map associated the current timestamp to generate a second filtered current predicted OGM and filtering each first filtered future predicted OGM with the future weight map associated with the respective future timestamp to generate one or more second filtered future predicted OGMs;
generating a single predicted OGM representative of the second set of filtered predicted OGMs by combining the second filtered current predicted OGM and each second filtered future predicted OGM in the set of second filtered predicted OGMs;
and
generating a trajectory for the autonomous vehicle to follow based on the single predicted OGM.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/708,886Filed 30 Mar 2022 · continuation
Priority: 30 Aug 2019
Published: US 2022/0221866 A114 Jul 2022
Granted: 11 Jul 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification14 codes

G05D 1/0212
Specially adapted to land vehicles: with means for defining a desired trajectory
G05D 1/0214
With means for defining a desired trajectory: in accordance with safety or protection criteria, e.g. avoiding hazardous areas
G01C 21/34
Specially adapted for navigation in a road network: route searching; Route guidance
G05D 1/0274
Using internal positioning means: using mapping information stored in a memory device

Family

Application16/557,368Parent of this continuation · filed 30 Aug 2019
US 2022/0221866 A1Pre-grant publication · published 14 Jul 2022
US 11,300,959 B2Parent of this continuation
US 2021/0064040 A1Published application
US 11,698,638 B2This patent

From the US filing history. Foreign family members aren’t listed.