Granted Patent B2

US 12,386,034 · App. 18/064,014 · Granted Aug 12, 2025

Inventors: Linus Hagvall (Gothenburg, SE); Stefan Bergquist (Gothenburg, SE); Christian Grante (Västra Frölunda, SE)

Assignee: Volvo Autonomous Solutions AB

G01S7/40G01S13/931

Abstract

Claims (26)

1. A method performed by a central unit for evaluating a performance of an obstacle detection system comprised in a first object within a set of two or more objects at a confined area, the first object being a vehicle, the method comprising:

obtaining pose data from each object in the set and obstacle detection data from at least the first object, wherein the obstacle detection data comprises a position of an obstacle detected by at least the first vehicle;

determining a relative pose of the objects using the pose data from each object;

comparing the obstacle detection data to the determined relative pose; and

based on the comparison, evaluating the performance of the obstacle detection system of the first object.

2. The method according to claim 1 , wherein at least a second object in the set is a vehicle.

3. The method according to claim 1 , wherein at least a second object in the set is a static object.

4. The method according to claim 1 , wherein the performance of the obstacle detection system is evaluated for at least one operating condition of the first object during which the pose data and obstacle detection data are obtained, and

wherein the performance of the obstacle detection system is evaluated for at least one operating condition to determine in which operating conditions the obstacle detection system provides output data with sufficient quality and accuracy and in which operating conditions the obstacle system provides output data with insufficient quality and accuracy.

5. The method according to claim 4 , wherein the at least one operating condition is at least one of:

weather condition, and

light condition.

6. The method according to claim 1 , wherein the performance of the obstacle detection system is evaluated for at least one object characteristic of the first object when the pose data and obstacle detection data are obtained, and

wherein the performance of the obstacle detection system is evaluated for at least one object characteristic to determine in which object characteristics the obstacle detection system provides output data with sufficient quality and accuracy and in which object characteristics the obstacle detection system provides output data with insufficient quality and accuracy.

7. The method according to claim 6 , wherein the at least one object characteristic is at least one of:

articulation angle,

yaw rate,

object speed,

object acceleration, and

object position relative to a road.

8. The method according to claim 1 , comprising:

obtaining no-object data indicating a sub-area of the confined area where no objects are located; and

wherein the obstacle detection data are further compared to the non-object data and used in the evaluation of the performance to detect if there are any false-positive obstacle detection data.

9. The method according to claim 1 , wherein pose data and obstacle detection data obtained in a sub-area of the confined area that do not fulfill a criterion are excluded from the evaluation.

10. A central unit for evaluating a performance of an obstacle detection system comprised in a first object within a set of two or more objects at a confined area, the first object being a vehicle, the central unit being configured to perform the steps of the method according to claim 1 .

11. A non-transitory computer readable medium carrying a computer program comprising program code for performing the method of claim 1 when said program code is run on a computer.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (13)