Granted Patent B2

US 12,258,044 · App. 17/632,736 · Granted Mar 25, 2025

Inventors: Linus Hagvall (Gothenburg, SE); Emil Klintberg (Torslanda, SE); Oskar Wigström (Gothenburg, SE); Fredrik Sandblom (Mölndal, SE)

Assignee: VOLVO TRUCK CORPORATION

B60W60/0015B60W30/0956B60W40/04B60W2050/0028B60W2554/404B60W2554/4046B60W2556/10

Abstract

Claims (20)

1. A method for controlling a vehicle based on a quantified road user behavior, the method comprising;

obtaining samples of road user behavior b i i=1 n−1 ,

selecting a subset of the road user behavior samples such that the selected samples follow a pre-determined statistical extreme value distribution, wherein the selecting comprises determining a threshold ζ such that the samples of road user behavior in excess of the threshold ζ, {b i :b i ≤ζ},

follow the pre-determined statistical extreme value distribution,

parameterizing the pre-determined statistical extreme value distribution based on the selected samples of road user behavior,

quantifying road user behavior based on the parameterized statistical extreme value distribution, and

controlling the vehicle based on the quantified road user behavior.

2. The method according to claim 1 , wherein the obtaining comprises obtaining a previously stored set of road user behavior samples.

3. The method according to claim 1 , wherein the obtaining comprises obtaining a set of road user behavior samples during operation of an ego vehicle.

4. The method according to claim 1 , comprising measuring a time between exceedances metric indicating the time passed between road user behavior samples exceeding the threshold ζ, and monitoring ODD based on the time between exceedances metric.

5. The method according to claim 1 , wherein the pre-determined statistical extreme value distribution is a Generalized Pareto Distribution, GDP.

6. The method according to claim 1 , wherein the pre-determined statistical extreme value distribution is a Generalized Extreme Value distribution, GEV.

7. The method according to claim 1 , wherein a sample of road user behavior comprises any of; road user position, road user heading, road user longitudinal velocity, road user lateral velocity, road user longitudinal acceleration, road user lateral acceleration, road user yaw rate, road user motion relative to a road surface, road user motion relative to a road lane, road user motion relative to another road user, and road user intention signaling, and road user action in response to an external event.

8. The method according to claim 1 , comprising quantifying the road user behavior as a bounded model by bounding the behavior to lie within a range − w ≤b k ≤ w with probability greater than 1−γ, based on the pre-determined statistical extreme value distribution.

9. The method according to claim 1 , comprising determining a confidence value β associated with the pre-determined statistical extreme value distribution.

10. The method according to claim 9 , comprising assessing a sufficiency of gathered road user behavior data for behavior quantification based on the confidence value β associated with the pre-determined statistical extreme value distribution.

11. The method according to claim 1 , comprising monitoring an operational design domain, ODD, associated with the vehicle by comparing the parameterized pre-determined statistical extreme value distribution to a set of baseline distribution parameters, wherein operation outside the ODD is indicated by a difference between parameterized pre-determined statistical extreme value distribution parameters and the baseline distribution parameters.

12. A computer readable medium carrying a computer program comprising program code for performing the steps of claim 1 when said program code is run on a computer or on processing circuitry of a control unit.

13. A control unit for quantifying road user behavior, the control unit being configured to perform the steps of the method according to claim 1 .

14. A vehicle comprising a control unit according to claim 13 .

Assignments (2)

Continuity (1)

References Cited (38)