Dynamic sensor range detection for vehicle navigation
Sensor information and map information may be obtained. The sensor information may characterize positions of objects in an environment of a sensor. The map information may characterize a road configuration in an environment of a vehicle. A sensor range configuration for the vehicle may be determined based on the road configuration in the environment of the vehicle. A portion of the sensor information may be processed for vehicle navigation based on the sensor range configuration.
1. A system for dynamic range detection, the system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining sensor information, the sensor information defining a three-dimensional (3D) point cloud that characterizes positions of objects in an environment of a sensor;
obtaining map information, the map information characterizing road intersections and exits in an environment of a vehicle;
determining, based on the map information, that the vehicle is traveling along a planned route, wherein the planned route comprises making one or more planned maneuvers at one or more road intersections and exits that the vehicle has not reached yet;
determining a sensor range configuration based on the one or more planned maneuvers before the vehicle reaches the one or more road intersections and exits and a speed of the vehicle, the sensor range configuration including a region of interest, wherein the region of interest is a sub-region of the 3D point cloud, and the determining comprises:
determining the sub-region of the 3D point cloud that is either a spherical or a polygonal shape;
determining a point density for the sub-region that is lower than a point density of the 3D point cloud;
reducing the region of interest if the vehicle lowers its speed, and enlarging the region of interest if the vehicle increases its speed; and
processing the sub-region of the 3D point cloud with the determined point density.
2. A system for dynamic range detection, the system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining sensor information, the sensor information that defines a three-dimensional (3D) point cloud characterizing positions of objects in an environment of a sensor;
obtaining map information, the map information characterizing road intersections and exits in an environment of a vehicle;
determining, based on the map information, that the vehicle is traveling along a planned route, wherein the planned route comprises making one or more planned maneuvers at one or more road intersections and exits that the vehicle has not reached yet;
determining a sensor range configuration based on the one or more planned maneuvers before the vehicle reaches the one or more road intersections and exits and a speed of the vehicle, the sensor range configuration including a region of interest, wherein the region of interest is a sub-region of the 3D point cloud, and the determining comprises:
determining the sub-region of the 3D point cloud that is either a spherical or a polygonal shape;
determining a point density for the sub-region that is lower than a point density of the 3D point cloud;
reducing the region of interest if the vehicle lowers its speed, and enlarging the region of interest if the vehicle increases its speed; and
processing the sub-region of the 3D point cloud with the determined point density.
3. The system of claim 2 , wherein the sensor range configuration is defined in two-dimensions.
4. The system of claim 2 , wherein the sensor range configuration is defined in three-dimensions.
5. The system of claim 2 , wherein the sensor includes a LIDAR, and the three-dimensional (3D) point cloud characterizing the positions of the objects in the environment of the LIDAR.
6. The system of claim 2 , wherein the map information further characterizes another road configuration in the environment of the vehicle includes a physical arrangement of one or more roads in the environment of the vehicle, and the planned route further comprises planned maneuvers according to the other road configuration.
7. The system of claim 6 , wherein the physical arrangement of the one or more roads includes a curvature, a grade, an on-ramp, or a number of lanes of the one or more roads.
8. A method for dynamic range detection, the method comprising:
obtaining sensor information, the sensor information that defines a three-dimensional (3D) point cloud characterizing positions of objects in an environment of a sensor;
obtaining map information, the map information characterizing road intersections and exits in an environment of a vehicle;
determining, based on the map information, that the vehicle is traveling along a planned route, wherein the planned route comprises making one or more planned maneuvers at one or more road intersections and exits that the vehicle has not reached yet;
determining a sensor range configuration based on the one or more planned maneuvers before the vehicle reaches the one or more road intersections and exits and a speed of the vehicle, the sensor range configuration including a region of interest, wherein the region of interest is a sub-region of the 3D point cloud, and the determining comprises:
determining the sub-region of the 3D point cloud that is either a spherical or a polygonal shape;
determining a point density for the sub-region that is lower than a point density of the 3D point cloud;
reducing the region of interest if the vehicle lowers its speed, and enlarging the region of interest if the vehicle increases its speed; and
processing the sub-region of the 3D point cloud with the determined point density.
9. The method of claim 8 , wherein the sensor range configuration is defined in two-dimensions.
10. The method of claim 8 , wherein the sensor range configuration is defined in three-dimensions.
11. The method of claim 8 , wherein the sensor includes a LIDAR, and the three-dimensional (3D) point cloud characterizing the positions of the objects in the environment of the LIDAR.
12. The method of claim 8 , wherein the map information further characterizes another road configuration in the environment of the vehicle includes a physical arrangement of one or more roads in the environment of the vehicle, and the planned route further comprises planned maneuvers according to the other road configuration.
13. The method of claim 12 , wherein the physical arrangement of the one or more roads includes a curvature, a grade, an on-ramp, or a number of lanes of the one or more roads.