Inverse radar sensor model and evidential grid mapping processors

A system comprising:

• processing circuitry;
• a non-transitory computer readable medium (CRM) storing executable code that, when executed by the processing circuitry, is configured to cause the system to:
• receive reflections indicating detections and generate data points representing the detections, in which each data point includes position and velocity information of a corresponding detection relative to a radar sensor of the system;
• receive, from the radar sensor, a set of the data points for time k;
• receive motion data for time k indicative of motion of the radar sensor at time k;
• generate object data for time k based on the set of the data points for time k and the motion data for time k, the object data representative of locations of the detections in a space, a radial velocity at each of the locations, and a signal-to-noise ratio (SNR) at each of the locations;
• and
• calculate, based on the object data for time k and a characteristic of the radar sensor, for each cell in a grid representing a field of view (FOV) of the radar sensor at time k, probabilities of the cell being in a free state indicating no detected object in the cell, a stationary state indicating a stationary detected object in the cell, and a dynamic state indicating a dynamic object detected in the cell.

A device comprising:

• motion sensing and processing circuitry configured to generate compensated motion data for a first time based on raw motion data and a set of motion indicators including a velocity indicator for the device calculated based on the raw motion data;
• and
• a radar sensor configured to receive reflections indicating detections and generate data points for the first time representing the detections, in which each data point includes position and velocity information of a corresponding detection relative to the radar sensor;
• a first circuit configured to generate object data for the first time based on the set of the data points for the first time and the compensated motion data for the first time;
• and
• a second circuit configured to calculate, based on the object data for the first time and a characteristic of the radar sensor, for each cell in a grid representing a field of view (FOV) of the radar sensor at the first time, probabilities of the cell being in a free state indicating no detected object in the cell, a stationary state indicating a stationary detected object in the cell, and a dynamic state indicating that a dynamic object is detected in the cell.