Methods and systems for lane changes using a multi-corridor representation of local route regions

Patent metadata

Field	Value
Publication number	US-12434766-B2
Application number	US-202217811164-A
Country	US
Kind code	B2
Filing date	Jul 7, 2022
Priority date	Oct 9, 2019
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

Methods and systems for maneuvering an autonomous vehicle are disclosed. The methods include generating a multi-corridor representation corresponding to a local region around the autonomous vehicle while travelling on a route, and using the multi-corridor representation and perception data corresponding to the local region to generate a trajectory for the autonomous vehicle to traverse the local region. The multi-corridor representation includes a plurality of adjacent corridors that each include one or more lane segments of a road network. A location of executing a lane change along the route is determined dynamically during a trajectory generation phase based on the perception data.

First claim

The invention claimed is:

1. A method of maneuvering an autonomous vehicle, the method comprising:
generating a multi-corridor representation corresponding to a local region around the autonomous vehicle while travelling on a route, the multi-corridor representation comprising a plurality of adjacent corridors that each include one or more lane segments of a road network;
generating, using the multi-corridor representation and perception data corresponding to the local region, a trajectory for the autonomous vehicle to traverse the local region, wherein a location of executing a lane change along the route is determined dynamically during a trajectory generation phase based on the perception data;
generating a stay-in-lane candidate trajectory for the autonomous vehicle to stay in a current corridor in the local region;
generating one or more lane change candidate trajectories for the autonomous vehicle to change from the current corridor to a destination corridor using a permissible lane change region between the current corridor and the destination corridor, wherein the permissible lane change region is associated with a continuous cost-to-go;
using the perception data and the continuous cost-to-go associated with the permissible lane change region to determine a dynamic cost associated with each of the following: the stay-in-lane candidate trajectory and the one or more lane change candidate trajectories, wherein the dynamic cost is associated with passenger comfort and safety; and
identifying the trajectory for the autonomous vehicle to traverse the local region as a candidate trajectory that has a minimum dynamic cost.

2. The method of claim 1 , wherein the one or more lane segments of the road network are stitched together without lane demarcation.

3. The method of claim 2 , wherein a boundary between a pair of adjacent corridors of the plurality of adjacent corridors includes one or more permissible lane change regions where the autonomous vehicle can execute the lane change.

4. The method of claim 3 , wherein generating the trajectory comprises:
receiving a static cost associated with each of the one or more lane segments, the static cost being associated with a lane change to be executed by the autonomous vehicle while travelling on the route; and
using the static cost to identify the one or more permissible lane change regions.

5. The method of claim 4 , wherein the static cost associated with a lane segment is based on information included in a road network map without taking into account the perception data.

6. The method of claim 2 , further comprising identifying the one or more lane segments of the road network by:
generating the route comprising a plurality of consecutive lane segments;
identifying a neighboring lane segment corresponding to one or more of the plurality of consecutive lane segments; and
identifying the one or more lane segments as a subset of the plurality of consecutive lane segments and the neighboring lane segment, the subset being associated with the local region.

7. The method of claim 2 , further comprising generating a reference path along which the autonomous vehicle will travel in each corridor.

8. The method of claim 1 , further comprising repeating the generation of the multi-corridor representation and the generation of the trajectory steps for a plurality of local regions until the autonomous vehicle reaches a destination.

9. The method of claim 1 , wherein the dynamic cost is increased responsive to the associated trajectory is associated with a jerky movement of the autonomous vehicle.

10. A system for maneuvering an autonomous vehicle, the system comprising: a processor; and
a non-transitory computer-readable medium comprising programming instructions that when executed by the processor will cause the processor to:
generate a multi-corridor representation corresponding to a local region around the autonomous vehicle while travelling on a route, the multi-corridor representation comprising a plurality of adjacent corridors that each include one or more lane segments of a road network,
generate, using the multi-corridor representation and perception data corresponding to the local region, a trajectory for the autonomous vehicle to traverse the local region, wherein a location of executing a lane change along the route is determined dynamically during a trajectory generation phase based on the perception data,
generate a stay-in-lane candidate trajectory for the autonomous vehicle to stay in a current corridor in the local region,
generate one or more lane change candidate trajectories for the autonomous vehicle to change from the current corridor to a destination corridor using a permissible lane change region between the current corridor and the destination corridor, wherein the permissible lane change region is associated with a continuous cost-to-go,
use the perception data and the continuous cost-to-go associated with the permissible lane change region to determine a dynamic cost associated with each of the following: the stay-in-lane candidate trajectory and the one or more lane change candidate trajectories, wherein the dynamic cost is associated with passenger comfort, and
identify the trajectory for the autonomous vehicle to traverse the local region as a candidate trajectory that has a minimum dynamic cost.

11. The system of claim 10 , wherein the one or more lane segments of the road network are stitched together without lane demarcation.

12. The system of claim 11 , wherein a boundary between a pair of adjacent corridors of the plurality of adjacent corridors includes one or more permissible lane change regions where the autonomous vehicle can execute the lane change.

13. The system of claim 12 , wherein the programming instructions that when executed by the processor will cause the processor to generate the trajectory comprise programming instructions to cause the processor to:
receive a static cost associated with each of the one or more lane segments, the static cost being associated with a lane change to be executed by the autonomous vehicle while travelling on the route; and
use the static cost to identify the one or more permissible lane change regions.

14. The system of claim 13 , wherein the static cost associated with a lane segment is based on information included in a road network map without taking into account the perception data.

15. The system of claim 10 , wherein the dynamic cost is increased responsive to the associated trajectory is associated with a jerky movement of the autonomous vehicle.

16. The system of claim 11 , further comprising programming instructions that when executed by the processor will cause the processor to identify the one or more lane segments of the road network by:
generating the route comprising a plurality of consecutive lane segments;
identifying a neighboring lane segment corresponding to one or more of the plurality of consecutive lane segments; and
identifying the one or more lane segments as a subset of the plurality of consecutive lane segments and the neighboring lane segment, the subset being associated with the local region.

17. The system of claim 11 , further comprising programming instructions that when executed by the processor will cause the processor to generate a reference path along which the autonomous vehicle will travel in each corridor.

18. The system of claim 10 , further comprising programming instructions that when executed by the processor will cause the processor to repeat the generation of the multi-corridor

Assignees

• Ford Global Tech Llc

Inventors

• Seegmiller Neal
• Cunningham Christopher
• Hukkeri Ramadev Burigsay
• Petroff Thomas
• Costa Albert

Classifications

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title

• B60W2554/80

  Spatial relation or speed relative to objects · CPC title

• G08G1/163

  involving continuous checking · CPC title

• H04W4/02

  Services making use of location information · CPC title

• G01C21/3626

  Details of the output of route guidance instructions (traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968) · CPC title