System and method for automated merging

Patent metadata

Field	Value
Publication number	US-12097862-B2
Application number	US-202117477729-A
Country	US
Kind code	B2
Filing date	Sep 17, 2021
Priority date	Sep 17, 2021
Publication date	Sep 24, 2024
Grant date	Sep 24, 2024

Abstract

A system and method for controlling a merge vehicle travelling along a highway having a merge lane and a main lane. The method includes receiving merge data about the merge vehicle and a surrounding environment of the merge vehicle. The method includes detecting an intent to perform a merge maneuver by the merge vehicle from the merge lane to the main lane based on the merge data. Further, the method includes generating a graph having a plurality of nodes connected by edges. The plurality of nodes includes a start node set to a current position of the merge vehicle and a goal node located in the main lane after the merge lane has ended. The method includes calculating a three-dimensional (3D) trajectory based on the graph by optimizing edge costs from the start node to the goal node, and controlling the merge vehicle based on the 3D trajectory.

First claim

The invention claimed is:

1. A computer-implemented method for controlling a merge vehicle travelling along a highway having a merge lane and a main lane, comprising:
receiving merge data about the merge vehicle and a surrounding environment of the merge vehicle including the merge lane, the main lane, and one or more traffic actors;
detecting an intent to perform a merge maneuver by the merge vehicle from the merge lane to the main lane based on the merge data, wherein detecting the intent to perform the merge maneuver includes detecting a hard nose landmark separating the merge lane from the main lane based on the merge data;
generating a graph having a plurality of nodes connected by edges, wherein the plurality of nodes includes a start node set to a current position of the merge vehicle and a goal node located in the main lane after the merge lane has ended, the plurality of nodes are associated with standardized coordinates and absolute coordinates, and the standardized coordinates are interpolated into the absolute coordinates using the merge data about the surrounding environment of the merge vehicle;
calculating a three-dimensional (3D) trajectory based on the graph by optimizing edge costs from the start node to the goal node; and
controlling the merge vehicle based on the 3D trajectory.

2. The computer-implemented method of claim 1 , wherein generating the graph includes the graph having three axes including a longitudinal axis, a lateral axis and time and one of the dimensions in the 3D trajectory is time.

3. The computer-implemented method of claim 1 , wherein generating the graph includes setting a zero point of the graph to a position of the merge vehicle when the intent to perform the merge maneuver is detected.

4. The computer-implemented method of claim 3 , including receiving updated merge data and upon receiving the updated merge data, updating the graph, calculating a new 3D trajectory based on the graph, and optimizing edge costs includes calculating a total cost of the new 3D trajectory.

5. The computer-implemented method of claim 4 , wherein updating the graph includes updating the start node based on a current position and a current heading of the merge vehicle relative to the zero point.

6. The computer-implemented method of claim 1 , wherein the goal node includes one or more goal positions located in the main lane after an end of the merge lane, and optimizing edge costs includes calculating a total cost for each path between the start node and the one or more goal positions.

7. The computer-implemented method of claim 6 , wherein the 3D trajectory is a path between the start node and the goal node having a lowest total cost.

8. The computer-implemented method of claim 1 , wherein controlling the merge vehicle based on the 3D trajectory includes determining an actual trajectory based on absolute coordinate values of each node included in the 3D trajectory and controlling the merge vehicle based on the actual trajectory.

9. The computer-implemented method of claim 1 , wherein controlling the merge vehicle based on the 3D trajectory includes controlling motion of the merge vehicle based on the 3D trajectory to complete the merge maneuver.

10. A system for controlling a merge vehicle travelling along a highway having a merge lane and a main lane, comprising:
a plurality of sensors for capturing merge data about the merge vehicle and a surrounding environment of the merge vehicle including the merge lane, the main lane, and one or more traffic actors; and
a processor operatively connected for computer communication with the plurality of sensors, wherein the processor:
detects an intent to perform a merge maneuver by the merge vehicle from the merge lane to the main lane based on the merge data;
generates a graph having a plurality of nodes connected by edges, wherein the plurality of nodes includes a start node set to a current position of the merge vehicle and a goal node located in the main lane after the merge lane has ended, the plurality of nodes are associated with standardized coordinates and absolute coordinates, and the standardized coordinates are interpolated into the absolute coordinates using the merge data about the surrounding environment of the merge vehicle;
calculates a three-dimensional (3D) trajectory based on the graph by optimizing edge costs from the start node to the goal node;
transmits the 3D trajectory to the merge vehicle thereby controlling the merge vehicle to perform the merge maneuver according to the 3D trajectory; and
controls the merge vehicle based on the 3D trajectory.

11. The system of claim 10 , wherein the processor optimizes the edge costs by selecting a path having a lowest total cost and calculates the 3D trajectory based on the path having the lowest total cost.

12. The system of claim 10 , wherein the processor calculates a new 3D trajectory upon receiving updated merge data.

13. The system of claim 12 , wherein upon receiving the updated merge data, the processor updates the graph by updating the start node based on a current position and a current heading of the merge vehicle relative to a position of the merge vehicle stored upon detecting the intent to perform the merge maneuver.

14. The system of claim 10 , wherein the processor determines an actual trajectory based on the 3D trajectory by converting the 3D trajectory to absolute coordinate values, and the processor transmits the actual trajectory to the merge vehicle.

15. The system of claim 10 , wherein detecting an intent to perform a merge maneuver by the merge vehicle includes detecting a hard nose landmark as the intent to perform the merge maneuver.

16. A non-transitory computer-readable storage medium including instructions that when executed by a processor, cause the processor to:
receive merge data about a merge vehicle and a surrounding environment of the merge vehicle including a merge lane, a main lane, and one or more traffic actors;
detect an intent to perform a merge maneuver by the merge vehicle from the merge lane to the main lane based on the merge data;
detect a hard nose landmark as the intent to perform the merge maneuver;
generate a graph having a plurality of nodes connected by edges, the graph having three axes corresponding to longitudinal position, lateral position and time, wherein the plurality of nodes includes a start node set to the current position of the merge vehicle and a goal node located in the main lane after the merge lane has ended, the plurality of nodes are associated with standardized coordinates and absolute coordinates, and the standardized coordinates are interpolated into the absolute coordinates using the merge data about the surrounding environment of the merge vehicle;
calculate a three-dimensional (3D) trajectory based on the graph by optimizing edge costs from the start node to the goal node;
communicate motion control signals to the merge vehicle based on the 3D trajectory; and
control the merge vehicle according to the motion control signals to complete the merge maneuver.

17. The non-transitory computer-readable storage medium of claim 16 , including causing the processor to set a zero point of the graph to a position of the merge vehicle when the intent to perform the merge maneuver is detected.

18. The non-transitory computer-readable storage medium of claim 16 , including causing the processor to capture updated merge data, update the graph based on the updated merge data, and calculate a new 3D trajectory based on the graph.

19. The non-transito

Assignees

• Honda Motor Co Ltd
• Virginia Tech Intellectual Properties Inc

Inventors

• Rajab Samer
• Saigusa Shigenobu
• Kelkar Paritosh
• Al-Nadawi Yasir Khudhair
• Chen Yusen
• Naes Tyler
• Schultz James
• Rainey Cameron
• Huggins Steven
• Mclaughlin Shane
• Kefauver Kevin

Classifications

• B60W2554/4045

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

• B60W2554/4046

  Behavior, e.g. aggressive or erratic · CPC title

• B60W2554/4049

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

• B60W40/10

  related to vehicle motion · CPC title

• B60W2552/53

  Road markings, e.g. lane marker or crosswalk · CPC title