Sensor placement to reduce blind spots

A system for imaging a scene in front of a vehicle, the system comprising:

• A plurality of LiDAR sensors;
• an object detection circuit communicatively coupled to the LiDAR sensors and comprising a processor and a memory, the memory comprising a plurality of instructions, which when executed by the processor cause the object detection circuit to perform the operations comprising:
• receiving a first point cloud from a first LiDAR sensor mounted at a first location behind a vehicle grille, the first point cloud representing the scene in front of the vehicle, wherein as a result of the grille the scene represented by the first point cloud data is partially occluded with a first pattern of occlusion;
• receiving a second point cloud from a second LiDAR sensor mounted at a second location behind the vehicle grille, wherein as a result of the grille, the scene represented by the second point cloud data is partially occluded with a second pattern of occlusion;
• combining the first and second point clouds to generate a composite point cloud data set, wherein the first location of the first LiDAR sensor is located relative to the second location of the second LiDAR sensor such that when a point cloud data for the first optical sensor and the second optical sensor are combined, the first pattern of occlusion is at least partially compensated for, and further wherein the first location of the first LiDAR sensor is located relative to the second location of the second LiDAR sensor such an overlap of the first pattern of occlusion with the second pattern of occlusion is reduced or minimized;
• and
• processing the combined point cloud data set.

A method for determining placement of a plurality of LiDAR sensors behind a grille of a vehicle, the method comprising:

• receiving a data file describing a pattern of features of the grille of the vehicle;
• determining a placement of a first LiDAR sensor of the plurality of LiDAR sensors behind the grille of the vehicle;
• modeling operation of the first LiDAR sensor behind the grille of the vehicle to determine a pattern of occlusions of the first LiDAR sensor caused by the pattern of features of the grille, the modeling based on the data file describing the pattern of features of the grille of the vehicle;
• based on a field-of-view of the plurality of LiDAR sensors and parameters of the pattern of features of the grille, determining a placement of the second LiDAR sensor of the plurality of LiDAR sensors behind the grille of the vehicle such that when a point cloud data for the first optical LiDAR sensor and the second optical LiDAR sensor are combined, the first pattern of occlusion of the first LiDAR sensor that is caused by the pattern of features of the grille is at least partially compensated in the combined data by data captured from the second LiDAR sensor.