Method of road detection for an automotive vehicle fitted with a LIDAR sensor

1 . A road detection method for a motor vehicle provided with a rotary multilayer LIDAR sensor and data processing circuitry, the method comprising:

acquiring LIDAR data of an environment of the motor vehicle as polar coordinates with the LIDAR sensor;

eliminating the data for which the polar coordinate relating to an angle of a beam with respect to a plane of the vehicle is greater than or equal to zero from the acquired LIDAR data; and

for each angle of the beam with respect to the plane of the vehicle, and for each LIDAR datum, the following are carried out:

determining theoretical coordinates of a point, corresponding to the LIDAR datum, as a function of the angle of the beam with respect to the plane of the vehicle and of the angle of the beam in the plane of the vehicle,

determining a standard deviation between the theoretical coordinates and the coordinates of the LIDAR datum, and

determining that the LIDAR datum forms part of the road when the standard deviation is lower than a predefined threshold, wherein

a LIDAR datum is a point of a cloud of points acquired by the LIDAR sensor over one revolution, or a section comprising at least two consecutive points of the cloud of points acquired by the LIDAR sensor that have the same beam angle with respect to the plane of the vehicle, and

when the LIDAR datum is a point of the cloud of points, the theoretical coordinates of the point corresponding to the LIDAR datum are determined as those of a point contained within an ideal circle inscribed within the plane of the road centered on the vehicle, the ideal circle surrounding the vehicle,

at least two sectors are determined in the plane of the vehicle for each angle of the beam with respect to the plane of the vehicle, each sector being associated with a direction of scanning the sector,

for each sector, the LIDAR data are scanned in the scanning direction, a determination is made as to whether each LIDAR datum belongs to the road, the scanning of the LIDAR data is interrupted when the method determines that a LIDAR datum does not belong to the road and when the method determines that the LIDAR data of the sector that have not been scanned do not belong to the road,

a sector of the at least two sectors comprises a LIDAR datum having a same angle of the beam with respect to the plane of the vehicle as a LIDAR datum of another sector of the at least two sectors, and

each LIDAR datum within each sector of the at least two sectors has the same angle of the beam with respect to the plane of the vehicle as all other LIDAR datum within the same sector.

2 . The method as claimed in claim 1 , wherein, when the LIDAR datum is a section comprising at least two points of the cloud of points,

the theoretical coordinates and the coordinates of the sections being defined as Cartesian coordinates and comprising a coordinate in a direction of movement of the vehicle in the plane of the vehicle, a coordinate in a direction at right angles to the direction of movement of the vehicle in the plane of the vehicle and a theoretical coordinate on the normal to the plane of the vehicle,

the theoretical coordinate on the normal to the plane of the vehicle is defined as an average of the coordinates on the normal to the plane of the vehicle of the points of the cloud of points acquired by the LIDAR sensor contained within the section, and

the other theoretical coordinates are defined as the coordinates of a point on an ideal circle inscribed within the plane of the road centered on the vehicle.

3 . The method as claimed in claim 1 , wherein, for each sector, a Gaussian filter is applied to results of the determination of the standard deviation in order to reduce impact of irregularities.

4 . The method as claimed in claim 3 , wherein the Gaussian filter has a size 3 kernel and a standard deviation of 5.

5 . The method as claimed in claim 1 , wherein

a direction of movement of the vehicle running forward is defined as corresponding to an angle 0 of the angle of the beam in the plane of the vehicle, and

four sectors are defined in the plane of the vehicle,

a first sector comprising the LIDAR data for which an angle in the plane of the vehicle extends from the angle 0 to an angle π/2, and in which the LIDAR data are scanned from the angle 0 to the angle π/2 in the plane of the vehicle,

a second sector comprising the LIDAR data for which the angle in the plane of the vehicle extending from the angle π/2 to an angle π, and in which the LIDAR data are scanned from the angle π to the angle π/2 in the plane of the vehicle,

a third sector comprising the LIDAR data for which the angle in the plane of the vehicle extends from the angle π to an angle 3π/2 and in which the LIDAR data are scanned from the angle π to the angle 3π/2 in the plane of the vehicle, and

a fourth sector comprising the LIDAR data for which the angle in the plane of the vehicle extends from the angle 3π/2 to the angle 0, and in which the LIDAR data are scanned in the plane of the vehicle from the angle 0 to the angle 3π/2 in the plane of the vehicle.

6 . The method as claimed claim 1 , wherein the steps relating to each sector are performed via distinct processing circuitry.

7 . The method as claimed in claim 1 , wherein, for each angle of the beam with respect to the plane of the vehicle, the method determines that a LIDAR datum belonging to the road corresponds to a marking on a ground, when a reflected light intensity perceived by the LIDAR sensor is lower than a predetermined threshold.

8 . The method as claimed in claim 1 , wherein the motor vehicle is an autonomous vehicle.

9 . The method as claimed in claim 1 , further comprising:

determining four sectors in the plane of the vehicle, each sector being associated with a direction of scanning the sector, wherein

a direction of movement of the vehicle running forward is defined as corresponding to an angle 0 of the angle of the beam in the plane of the vehicle,

the four sectors include:

a first sector comprising the LIDAR data for which an angle in the plane of the vehicle extends from the angle 0 to an angle π/2, and in which the LIDAR data are scanned from the angle 0 to the angle π/2 in the plane of the vehicle,

a second sector comprising the LIDAR data for which the angle in the plane of the vehicle extending from the angle π/2 to an angle π, and in which the LIDAR data are scanned from the angle π to the angle π/2 in the plane of the vehicle,

a third sector comprising the LIDAR data for which the angle in the plane of the vehicle extends from the angle π to an angle 3π/2 and in which the LIDAR data are scanned from the angle π to the angle 3π/2 in the plane of the vehicle, and

a fourth sector comprising the LIDAR data for which the angle in the plane of the vehicle extends from the angle 3π/2 to the angle 0, and in which the LIDAR data are scanned in the plane of the vehicle from the angle 0 to the angle 3π/2 in the plane of the vehicle, and

the first sector, the second sector, the third sector, and the fourth sector surround the vehicle.

10 . The method as claimed in claim 9 , further comprising:

scanning, for each of the first sector, the second sector, the third sector, and the fourth sector, the LIDAR data in the scanning direction;

determining whether each LIDAR datum belongs to the road; and

interrupting the scanning of the LIDAR data in response to determining that a LIDAR datum does not belong to the road, the method determining that the LIDAR data of the sector that have not been scanned do not belong to the road.