Target tracking during acceleration events

A vehicle, comprising:

• a radar sensing system;
• one or more vehicle actuators comprising at least one of steering, braking and propulsion actuators;
• and
• at least one processor in operable communication with the radar sensing system and the vehicle actuators, the at least one processor configured to execute program instructions, wherein the program instructions are configured to cause the at least one processor to:
• receive at least one Radar-Doppler, RD, map from the radar sensing system of the vehicle;
• detect relative acceleration of an object with respect to the vehicle based on the RD map and a neural network, and provide acceleration data based on the relative acceleration detecting, wherein the neural network is a deep neural network and comprises a convolutional neural network, fully connected layers and a logistic regression operation, wherein the deep neural network is trained to classify RD maps that have been captured when the vehicle is moving at a constant velocity and to classify RD maps that have been captured when the vehicle is accelerating;
• receive a current frame of detected object data from a sensing system of the vehicle;
• when the relative acceleration has not been detected, track the object based on the current frame of detected object data, a predictive motion model and a historical state of the object using a tracking algorithm and provide estimated object data based on the object tracking;
• when the relative acceleration has been detected, adapt the tracking algorithm to reduce the influence of at least one of the predictive motion model and the historical state of the object and track the object using the adapted tracking algorithm and provide adapted estimated object data based on the object tracking;
• and
• control the one or more vehicle actuators based on the adapted estimated object data or the estimated object data.