US 12,444,202 B2
Method and system for estimating a drivable surface
Erik Rosen, Alingsås (SE); Nicholas Wickström, Halmstad (SE); Peter Hall, Linköping (SE); Mattias Brännström, Gothenburg (SE); and Ognjan Hedberg, Stenungsund (SE)
Assigned to ZENUITY AB, Gothenburg (SE)
Appl. No. 17/622,284
Filed by ZENUITY AB, Gothenburg (SE)
PCT Filed Jun. 25, 2020, PCT No. PCT/EP2020/067817
§ 371(c)(1), (2) Date Dec. 23, 2021,
PCT Pub. No. WO2020/260455, PCT Pub. Date Dec. 30, 2020.
Claims priority of application No. 19182994 (EP), filed on Jun. 27, 2019.
Prior Publication US 2022/0262136 A1, Aug. 18, 2022
Int. Cl. G06V 20/56 (2022.01); B60W 40/06 (2012.01); G01B 21/30 (2006.01); G01S 13/931 (2020.01); G06V 10/54 (2022.01); G06V 10/80 (2022.01)
CPC G06V 20/56 (2022.01) [G01B 21/30 (2013.01); G01S 13/931 (2013.01); G06V 10/54 (2022.01); G06V 10/806 (2022.01); G06V 20/588 (2022.01); B60W 40/06 (2013.01); B60W 2420/403 (2013.01); B60W 2420/408 (2024.01)] 8 Claims
OG exemplary drawing
 
1. A method for estimating a drivable space in a surrounding environment of a vehicle, the method comprising:
obtaining sensor data comprising information about the surrounding environment of the vehicle;
determining, using a first algorithm, a surface flatness of the surrounding environment of the vehicle based on the obtained sensor data in order to obtain a surface flatness parameter for each of a first plurality of portions of the surrounding environment of the vehicle, wherein each obtained surface flatness parameter is indicative of a presence of a bump, indentation, and/or object on a corresponding portion of the first plurality of portions of the surrounding environment of the vehicle;
forming a first model representation indicative of the obtained surface flatness parameters of the first plurality of portions of the surrounding environment of the vehicle;
wherein forming the first model representation comprises:
for each time sample, updating the surface flatness parameters of a previous time sample based the obtained surface flatness parameters by adding or multiplying the obtained surface flatness parameters to the first model representation of the previous time sample;
determining, using a second algorithm, a surface texture of the surrounding environment of the vehicle based on the obtained sensor data in order to obtain a surface texture parameter for each of a second plurality of portions of the surrounding environment of the vehicle, wherein each obtained surface texture parameter is indicative of a presence of a road surface on a corresponding portion of the second plurality of portions of the surrounding environment of the vehicle;
forming a second model representation indicative of the obtained surface texture parameters of the second plurality of portions of the surrounding environment of the vehicle;
wherein forming the second model representation comprises:
for each time sample, updating the surface texture parameters of a previous time sample with the obtained surface texture parameters by adding or multiplying the obtained surface texture parameters to the second model representation of the previous time sample;
storing, in a separate layer or a separate counter, the obtained surface flatness parameters and the determined surface texture parameters at each time sample;
fusing the obtained surface flatness parameters and the obtained surface texture parameters in order to obtain a combined estimation of the presence of drivable space in the surrounding environment, wherein fusing the determined surface flatness parameters with the determined surface texture parameters is performed where the first and second model representations overlap;
wherein the updating of the surface flatness parameters and the updating of the surface texture parameters is performed before fusing the obtained surface flatness parameter-parameters and the obtained surface texture parameters;
generating a control signal indicative of the presence of drivable space of the surrounding environment based on the combined estimation of the presence of drivable space; and
controlling driving of the vehicle in the drivable space of the surrounding environment based on the combined estimation of the presence of drivable space.