Courtesy lane selection paradigm

Patent metadata

Field	Value
Publication number	US-12479477-B2
Application number	US-202318235793-A
Country	US
Kind code	B2
Filing date	Aug 18, 2023
Priority date	Aug 18, 2023
Publication date	Nov 25, 2025
Grant date	Nov 25, 2025

Abstract

Embodiments herein include systems and methods of generating lane selection cost values to control autonomous vehicles to accommodate merging vehicles in a tapering lane (or merge lane). An autonomy system can identify a tapering lane in map data and detect a merging vehicle situated in the tapering lane using perception sensor data. The autonomy system includes a lane-selection cost function that generates lane-selection cost values for the lanes available to the automated vehicle, which the autonomy system references to determine whether to continue traveling a current lane or change lanes into an adjacent lane. The lane-selection cost function may apply a courtesy weight when detecting the merging vehicle, such that the autonomy system causes the automated vehicle to change lanes as a courtesy to the merging vehicle, but without overriding other safety-related factors of the lane-selection cost function or trajectory planning functions.

First claim

What is claimed is:

1 . A method for navigation planning for an autonomous vehicle, the method comprising:
obtaining, by a processor of an autonomous vehicle, sensor data from a plurality of sensors onboard the autonomous vehicle for a roadway, the roadway including a current travel lane of the autonomous vehicle, an adjacent travel lane that is adjacent to the current travel lane, and a tapering travel lane that is adjacent to the current lane of travel and on an opposite side of the current travel lane from the adjacent travel lane; identifying, by the processor, a merging vehicle in the tapering lane by applying an object recognition engine on the sensor data; identifying a first vehicle and a second vehicle in the adjacent travel lane by applying the object recognition engine on the sensor data; determining a traffic gap in the adjacent travel lane, the traffic gap having an amount of distance between the first vehicle and the second vehicle in the adjacent travel lane; obtaining, by the processor, a first cost value for the current travel lane and a second cost value for the adjacent travel lane based upon the sensor data, each cost value representing a cost for traveling in the corresponding lane; determining, by the processor, that the first cost value is comparatively lower than the second cost value when the processor fails to identify the traffic gap satisfying a gap distance; updating, by the processor, a control command for causing the autonomous vehicle to continue driving in the current travel lane; and transmitting, by the processor, the control command that causes the autonomous vehicle to continue driving in the current travel lane to an operating module for driving the autonomous vehicle.

2 . The method according to claim 1 , further comprising:
determining, by the processor, a closing-distance of the autonomous vehicle relative to the merging vehicle; and determining, by the processor, that the closing-distance fails to satisfy a threshold closing-distance, wherein the processor determines the first cost value is comparatively lower than the second cost value in response to determining that the closing-distance fails to satisfy the threshold closing-distance.

3 . The method according to claim 1 , further comprising determining, by the processor, a velocity change for the autonomous vehicle to move into the traffic gap,
wherein the processor determines that the first cost value is comparatively lower than the second cost value when the processor determines the velocity change fails to satisfy a threshold velocity change for moving into the traffic gap.

4 . The method according to claim 1 , wherein the processor updates each cost value and the control command in response to identifying the merging vehicle.

5 . The method according to claim 1 , wherein the processor continually updates each cost value and the control command at a preconfigured interval.

6 . The method according to claim 1 , wherein the processor obtains the first cost value for the current travel lane and the second cost value for the adjacent travel lane based upon detecting each traffic vehicle in the roadway.

7 . The method according to claim 1 , wherein the processor obtains the first cost value for the current travel lane and the second cost value for the adjacent travel lane based upon a courtesy weight of a lane selection cost function.

8 . A system for navigation planning for an autonomous vehicle, the system comprising:
a non-transitory computer-readable memory on board an autonomous vehicle configured to store map data associated with a geographic location having an intersection; and a processor of the autonomous vehicle configured to:
obtain sensor data from a plurality of sensors onboard the autonomous vehicle for a roadway, the roadway including a current travel lane of the autonomous vehicle, an adjacent travel lane that is adjacent to the current travel lane, and a tapering travel lane that is adjacent to the current lane of travel and on an opposite side of the current travel lane from the adjacent travel lane;
identify a merging vehicle in the tapering lane by applying an object recognition engine on the sensor data;
identifying a first vehicle and a second vehicle in the adjacent travel lane by applying the object recognition engine on the sensor data; determining a traffic gap in the adjacent travel lane, the traffic gap having an amount of distance between the first vehicle and the second vehicle in the adjacent travel lane; obtain a first cost value for the current travel lane and a second cost value for the adjacent travel lane based upon the sensor data, each cost value representing a cost for traveling in the corresponding lane; determine a velocity change for the autonomous vehicle to move into the traffic; determine that the first cost value is comparatively lower than the second cost value when the processor determines the velocity change fails to satisfy a threshold velocity change for moving into the traffic gap; update a control command for causing the autonomous vehicle to continue driving in the current travel lane; and transmitting, by the processor, the control command that causes the autonomous vehicle to continue driving in the current travel lane to an operating module for driving the autonomous vehicle.

9 . The system according to claim 8 , wherein the processor is further configured to:
determine a closing-distance of the autonomous vehicle relative to the merging vehicle; and determine that the closing-distance fails to satisfy a threshold closing-distance, wherein the processor determines the first cost value is comparatively lower than the second cost value in response to determining that the closing-distance fails to satisfy the threshold closing-distance.

10 . The system according to claim 8 , wherein the processor determines that the first cost value is comparatively lower than the second cost value when the processor fails to identify the traffic gap satisfying a gap distance.

11 . The system according to claim 8 , wherein the processor updates each cost value and the control command in response to identifying the merging vehicle.

12 . The system according to claim 8 , wherein the processor continually updates each cost value and the control command at a preconfigured interval.

13 . The system according to claim 8 , wherein the processor obtains the first cost value for the current travel lane and the second cost value for the adjacent travel lane based upon detecting each traffic vehicle in the roadway.

14 . The system according to claim 8 , wherein the processor obtains the first cost value for the current travel lane and the second cost value for the adjacent travel lane each cost value for each lane based upon a courtesy weight of a lane selection cost function.

Assignees

• Torc Robotics Inc

Inventors

• Shoemaker Adam
• Blankenhorn John
• Madsen Garrett
• Petrin Joshua
• Tulsyan Ajay
• Brown Paul
• Pereira Savio
• Davis William
• Fernández Daniel
• Hao Yexuan

Classifications

• B60W2554/4045

  Intention, e.g. lane change or imminent movement · CPC title

• B60W2554/4041

  Position · CPC title

• B60W2554/4049

  Relationship among other objects, e.g. converging dynamic objects · CPC title

• B60W2554/802

  Longitudinal distance · CPC title

• B60W2556/40

  High definition maps · CPC title