Multi radar object detection

A system comprising:

• at least one programmable processor;
• and
• a non-transitory machine-readable medium storing instructions that, when executed by the at least one programmable processor, cause the at least one programmable processor to perform operations comprising:
• receiving one or more signals reflected by one or more second objects, the signals being received by one or more radar sensors positioned on one or more first objects;
• generating, based on the one or more received signals, one or more representations, one or more portions of the generated representations corresponding to the one or more received signals, wherein the one or more representations include one or more point clouds, wherein the one or more portions of the representations include one or more points in the one or more point clouds;
• filtering the one or more point clouds to remove one or more points corresponding to one or more noise signals in the one or more received signals;
• wherein the one or more point clouds comprise one or more cross potential point clouds generated by combining one or more point clouds generated using signals received by each radar sensor of the one or more radar sensors, wherein generation of the one or more cross potential point clouds further comprises:
• clustering at least a portion of the one or more point clouds based on a number of points corresponding to at least a portion of the one or more received signals received from one or more scattering regions of a second object in the one or more second objects, and generating one or more clustered point clouds;
• determining, based at least on a confidence metric, that a first cluster representative of the second object corresponds to a second cluster representative of the second object, wherein the first cluster is in a first clustered point cloud associated with a first radar sensor and the second cluster is in a second clustered point cloud associated with a second radar sensor, wherein the confidence metric is indicative of the first clustered point cloud and the second clustered point cloud corresponding to the second object;
• combining, based on the determining, at least the first clustered point cloud and the second clustered point cloud to generate the one or more cross potential point clouds, wherein the confidence metric is included in the one or more cross potential point clouds;
• generating, using the one or more cross potential point clouds, one or more virtual enclosures encompassing the one or more second objects;
• and
• detecting, using the generated one or more virtual enclosures, a presence of the one or more second objects.