Systems and methods for controlling a vehicle using high precision and high recall detection

Patent metadata

Field	Value
Publication number	US-12415513-B2
Application number	US-202218147906-A
Country	US
Kind code	B2
Filing date	Dec 29, 2022
Priority date	Dec 13, 2022
Publication date	Sep 16, 2025
Grant date	Sep 16, 2025

Abstract

This disclosure provides systems and methods for detecting and tracking objects or obstacles in an environment of an autonomous vehicle. The method may include receiving data from a set of sensors, wherein the data represents objects or obstacles in an environment of the autonomous vehicle; and using a processor: generating high precision detection data based on the received data; identifying, from the high precision detection data, a set of objects that are classifiable by at least one known classifier; generating high recall detection data based on the received data; identifying from the high recall detection data a set of obstacles; and performing an operation on the high precision detection data of the objects and the high recall detection data of the obstacles, based on a status of the autonomous vehicle or based on one or more characteristics of the objects or the obstacles.

First claim

What is claimed is:

1. A method for detecting and tracking objects or obstacles in an environment of an autonomous vehicle, comprising:
receiving data from a set of sensors, wherein the data represents objects or obstacles in an environment of the autonomous vehicle; and
using a processor to perform the steps of:
generating high precision detection data based on the received data;
identifying, from the high precision detection data, a set of objects that are classifiable by at least one known classifier;
generating high recall detection data based on the received data;
identifying from the high recall detection data a set of obstacles; and
performing an operation on the high precision detection data of the objects and the high recall detection data of the obstacles, based on a status of the autonomous vehicle or based on one or more characteristics of the objects or the obstacles, wherein the operation comprises jointly optimizing the high precision detection data of the objects and the high recall detection data of the obstacles, when the autonomous vehicle is performing fallback maneuvers, and wherein the operation comprises determining a cover value between an obstacle in the high recall detection data and an object in the high precision detection data, by dividing area of intersection of the obstacle and the object by area of the obstacle.

2. The method of claim 1 , wherein the operation comprises removing an obstacle from the high recall detection data if the cover value is greater than a threshold cover value.

3. The method of claim 2 , wherein the operation comprises removing an obstacle from the high recall detection data if the cover value is about 1.0 or the obstacle is identical to an object from the high precision detection data.

4. The method of claim 2 , wherein if the cover value is between 1.0 and the threshold cover value, the step of removing is performed after dilating representation boundaries of the object to encompass the obstacle.

5. The method of claim 2 , wherein the threshold cover value is 0.8.

6. The method of claim 2 , wherein if a protrusion on the obstacle is the only difference between the obstacle and the object, the operation comprises associating the protrusion with the object and removing the obstacle from the high recall detection data.

7. The method of claim 1 , wherein if the cover value is smaller than the threshold cover value, the operation comprises maintaining respective representations of the obstacle and the object.

8. The method of claim 1 , wherein if the cover value is smaller than the threshold cover value and if the obstacle is associated with the object, the operation comprises integrating one or more characteristics of the object into characteristics of the obstacle while maintaining respective representations of the obstacle and the object.

9. A method of controlling an autonomous vehicle, comprising:
detecting and tracking objects or obstacles in an environment of the autonomous vehicle according to the method of claim 1 ;
determining a candidate trajectory for the autonomous vehicle based on the high precision detection data and/or the high recall detection data; and
controlling the autonomous vehicle according to the candidate trajectory.

10. The method of claim 9 , wherein the operation comprises removing an obstacle from the high recall detection data if the cover value is greater than a threshold cover value.

11. The method of claim 10 , wherein the operation comprises removing an obstacle from the high recall detection data if the cover value is about 1.0 or the obstacle is identical to an object from the high precision detection data.

12. The method of claim 10 , wherein if the cover value is between 1.0 and the threshold cover value, the step of removing is performed after dilating representation boundaries of the object to encompass the obstacle.

13. The method of claim 10 , wherein the threshold cover value is 0.8.

14. The method of claim 10 , wherein if a protrusion on the obstacle is the only difference between the obstacle and the object, the operation comprises associating the protrusion with the object and removing the obstacle from the high recall detection data.

15. The method of claim 9 , wherein if the cover value is smaller than the threshold cover value, the operation comprises maintaining respective representations of the obstacle and the object.

16. The method of claim 9 , wherein if the cover value is smaller than the threshold cover value and if the obstacle is associated with the object, the operation comprises integrating one or more characteristics of the object into characteristics of the obstacle while maintaining respective representations of the obstacle and the object.

17. A system for controlling an autonomous vehicle, comprising:
a set of sensors, configured to receive data that represents objects or obstacles in an environment of the autonomous vehicle; and
a processor, configured to:
generate high precision detection data based on the received data;
identify, from the high precision detection data, a set of objects that are classifiable by at least one known classifier;
generate high recall detection data based on the received data;
identify from the high recall detection data a set of obstacles; and
perform an operation on the high precision detection data of the objects and the high recall detection data of the obstacles, based on a status of the autonomous vehicle or based on one or more characteristics of the objects or the obstacles, wherein the operation comprises jointly optimizing the high precision detection data of the objects and the high recall detection data of the obstacles, when the autonomous vehicle is performing fallback maneuvers, and wherein the operation comprises determining a cover value between an obstacle in the high recall detection data and an object in the high precision detection data, by dividing area of intersection of the obstacle and the object by area of the obstacle.

18. The system of claim 17 , wherein the operation comprises removing an obstacle from the high recall detection data if the cover value is greater than a threshold cover value.

19. The system of claim 18 , wherein the operation comprises removing an obstacle from the high recall detection data if the cover value is about 1.0 or the obstacle is identical to an object from the high precision detection data.

20. The system of claim 18 , wherein if the cover value is between 1.0 and the threshold cover value, the step of removing is performed after dilating representation boundaries of the object to encompass the obstacle.

21. The system of claim 18 , wherein the threshold cover value is 0.8.

22. The system of claim 18 , wherein if a protrusion on the obstacle is the only difference between the obstacle and the object, the operation comprises associating the protrusion with the object and removing the obstacle from the high recall detection data.

23. The system of claim 17 , wherein if the cover value is smaller than the threshold cover value, the operation comprises maintaining respective representations of the obstacle and the object.

24. The system of claim 17 , wherein if the cover value is smaller than the threshold cover value and if the obstacle is associated with the object, the operation comprises integrating one or more characteristics of the object into characteristics of the obstacle while maintaining respective representations o

Assignees

• Kodiak Robotics Inc

Inventors

• Phillips Derek J
• Otis Collin C
• Wendel Andreas
• Rusch Jackson P

Classifications

• B60W2420/408

  Radar; Laser, e.g. lidar · CPC title

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W50/06

  Improving the dynamic response of the control system, e.g. improving the speed of regulation or avoiding hunting or overshoot · CPC title

• B60W30/09

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title

• B60W60/001 Primary

  Planning or execution of driving tasks · CPC title