Method for assigning ego vehicle to a lane
AssigneeZenuity AB
InventorsViktor Runemalm, Markus Hammarsten, Jonatan Silvlin, Albin Manhof
Life of this patent
Estimating the term…
Abstract
The present invention relates to methods and arrangements for assigning a vehicle to a lane in a road for a vehicle. The proposed solution obtains an estimated pose for the vehicle, projects the pose to nearby lanes, obtains uncertainty values for the pose and lanes, creates a distribution by combining the pose and lane uncertainties, creates a momentary likelihood for the vehicle being in each lane, adjusts the momentary likelihoods with prior values obtained in a previous iteration, and determines the most likely lane.
Claims16
A method, performed by a processor of a vehicle control system, for assigning a vehicle to a lane in a road, wherein the method comprises:
- obtaining an estimated pose, E, of the vehicle;
- obtaining an uncertainty value, V, to the estimated pose of the vehicle, the uncertainty value, V, being indicative of a precision of the estimated pose, E;
- projecting the estimated pose, E, onto nearby lanes in a map;
- obtaining a position uncertainty value, U, of a position of each nearby lane;
- creating a probability distribution, P, by combining uncertainty values V and U for each nearby lane;
- creating a current momentary probability hypothesis for the vehicle for being in each lane by evaluating the probability distribution, P, with the estimated pose, E, for each projected pose;
- adjusting the current momentary probability hypothesis for the vehicle being in each lane with a prior probability determined in an earlier iteration;
- and
- comparing all the adjusted momentary probabilities;
- determining the lane with the highest probability;
- and
- controlling the vehicle based on determining the lane with the highest probability.
A vehicle control system comprising at least one processor, at least one memory for storing instructions and data, at least one sensor interface, and at least one communication interface, wherein the processor is arranged to execute instruction sets stored in the memory, acquire data via the sensor interface and:
- obtaining an estimated pose, E, of the vehicle;
- obtaining an uncertainty value, V, to the estimated pose of the vehicle, the uncertainty value, V, being indicative of a precision of the estimated pose, E;
- projecting the estimated pose, E, onto nearby lanes in a map;
- obtaining a position uncertainty value, U, of a position of each nearby lane;
- creating a probability distribution, P, by combining uncertainty values V and U for each nearby lane;
- creating a current momentary probability hypothesis for the vehicle for being in each lane by evaluating the probability distribution, P, with the estimated pose, E, for each projected pose;
- adjusting the current momentary probability hypothesis for the vehicle being in each lane with a prior probability determined in an earlier iteration;
- comparing all the adjusted momentary probabilities;
- determining the lane with the highest probability;
- and
- sending control parameters on the communication interface for controlling the vehicle in accordance with the determined most probable lane.
A vehicle comprising:
- a vehicle control system, controlling driving functions of the vehicle, comprising at least one processor, at least one memory for storing instructions and data, at least one sensor input interface;
- at least one sensor for acquiring an estimation of vehicle position,
- wherein the vehicle control system is arranged to execute instructions in the processor, the processor is configured to:
- obtain an estimated pose, E, of the vehicle;
- obtain an uncertainty value, V, to the estimated pose of the vehicle, the uncertainty value, V, being indicative of a precision of the estimated pose, E;
- project the estimated pose, E, onto nearby lanes in a map;
- obtain a position uncertainty value, U, of a position of each nearby lane;
- create a probability distribution, P, by combining uncertainty values V and U for each nearby lane;
- create a current momentary probability hypothesis for the vehicle for being in each lane by evaluating the probability distribution, P, with the estimated pose, E, for each projected pose;
- adjust the current momentary probability hypothesis for the vehicle being in each lane with a prior probability determined in an earlier iteration;
- and
- compare all the adjusted momentary probabilities;
- determine the lane with the highest probability;
- and
- control, via a processor, the vehicle based on determining the lane with the highest probability.
Dependencies are inferred from the claim text.