Localization using dynamic landmarks

1. A method for determining a map position of an ego-vehicle, the ego-vehicle having a geographical position including a set of geographical coordinates of the ego-vehicle, said method comprising:

acquiring map data comprising a road geometry of a surrounding environment of the ego-vehicle;

initializing at least one dynamic landmark, by:

detecting and selecting at least one surrounding vehicle out of a plurality of surrounding vehicles in the surrounding environment of the ego-vehicle that fulfill a predefined one or more selection criteria, the selected at least one surrounding vehicle forming the at least one dynamic landmark;

measuring a position and velocity, relative to the ego-vehicle, only of the selected at least one surrounding vehicle; and

determining a first map position only of the selected at least one surrounding vehicle based on the measured position of the selected at least one surrounding vehicle and the geographical position of the ego-vehicle;

predicting a second map position of the selected at least one surrounding vehicle, based on the determined first map position of the selected at least one surrounding vehicle, the measured velocity of the selected at least one surrounding vehicle, and the road geometry;

measuring a location, relative to the ego-vehicle, of the selected at least one surrounding vehicle, when the selected at least one surrounding vehicle is estimated to be at the second map position; and

updating the geographical position of the ego-vehicle based on the predicted second map position of the selected at least one surrounding vehicle and the measured location of the selected at least one surrounding vehicle,

wherein said predefined one or more selection criteria comprises at least one of:

the velocity of the selected at least one surrounding vehicle is V±10%, where V is the velocity of the ego-vehicle;

a traveling direction of the selected at least one surrounding vehicle is the same as the ego-vehicle; and

a relative distance between the selected at least one surrounding vehicle and the ego-vehicle is below a predefined threshold distance.

2. The method according to claim 1 , further comprising: determining the set of geographical coordinates of the ego-vehicle by means of a Global Navigation Satellite System, GNSS.

3. The method according to claim 2 , further comprising:

determining the set of geographical coordinates of the ego-vehicle by:

measuring the ego-vehicle's IMU data; and

evaluating the IMU data in view of the road geometry in order to determine the set of geographical coordinates of the ego-vehicle.

4. The method according to claim 1 , wherein the map data further comprises stationary landmark location coordinates for at least one stationary landmark in the surrounding environment of the ego-vehicle, and wherein the method further comprises:

determining the set of geographical coordinates of the ego-vehicle by:

measuring a stationary landmark position, relative to the ego-vehicle, of the at least one stationary landmark; and

comparing the measured stationary landmark position and the stationary landmark location coordinates.

5. The method according to claim 1 , further comprising forming a state vector comprising a set of ego-vehicle elements representative of the geographical coordinates of the ego-vehicle and an orientation of the ego-vehicle.

6. The method according to claim 5 , wherein the step of updating the geographical position comprises updating the set of ego-vehicle elements in the state vector.

7. The method according to claim 6 , wherein the step of determining the first map position of the selected at least one surrounding vehicle comprises extending the state vector to include new elements representative of the first map position of the selected at least one surrounding vehicle, and

wherein the step of predicting the second map position of the selected at least one surrounding vehicle further comprises updating the elements representative of the determined first map position of the selected at least one surrounding vehicle in the state vector.

8. The method according to claim 1 , wherein the step of predicting the second map position of the selected at least one surrounding vehicle is further based on a predefined vehicle motion model.

9. The method according to claim 8 , wherein the predefined motion model is based on an assumption that a lateral motion of the selected at least one surrounding vehicle is slower than a longitudinal motion of the selected at least one surrounding vehicle.

10. A non-transitory computer-readable storage medium storing one or more instructions configured to be executed by one or more processors of a vehicle control system, the one or more instructions cause the one or more processors to perform the method according to claim 1 .

11. A vehicle control system for determining a map position of an ego-vehicle, the system comprising:

a localization system configured to determine a set of geographical coordinates of the ego-vehicle and an orientation of the ego-vehicle;

a vehicle perception system comprising at least one sensor for detecting objects that are external to the ego-vehicle;

a vehicle control circuitry connected to the localization system and the vehicle perception system, wherein the vehicle control circuitry is configured to:

acquire map data comprising a road geometry of a surrounding environment of the ego-vehicle;

estimate a geographical position of the ego-vehicle by means of the localization system;

initialize at least one dynamic landmark by:

detecting and selecting at least one surrounding vehicle out of a plurality of surrounding vehicles in the surrounding environment of the ego-vehicle that fulfill a predefined one or more selection criteria, the selected at least one surrounding vehicle forming the at least one dynamic landmark,

measuring, by means of the vehicle perception system, a position and velocity, relative to the ego-vehicle, only of the selected at least one surrounding vehicle, and

determining a first map position only of the selected at least one surrounding vehicle based on the geographical position of the ego-vehicle and the measured position of the selected at least one surrounding vehicle;

predict a second map position of the selected at least one surrounding vehicle based on the determined first map position of the selected at least one surrounding vehicle, the measured velocity of the selected at least one surrounding vehicle, and the road geometry;

measure, by means of the localization system, a location of the ego-vehicle relative to the selected at least one surrounding vehicle, when the selected at least one surrounding vehicle is estimated to be at the second map position; and

update the estimated geographical position of the ego-vehicle based on the predicted second map position of the selected at least one surrounding vehicle and the measured location of the selected at least one surrounding vehicle,

wherein said predefined one or more selection criteria comprises at least one of:

the velocity of the selected at least one surrounding vehicle is V±10%, where V is the velocity of the ego-vehicle;

a traveling direction of the selected at least one surrounding vehicle is the same as the ego-vehicle; and

a relative distance between the selected at least one surrounding vehicle and the ego-vehicle is below a predefined threshold distance.

12. An ego-vehicle comprising the vehicle control system according to claim 11 .