Energy Efficient Sampling For Last-Mile Delivery Systems

A computer-implemented method is presented for determining sampling rate for at least one of a camera and a receiver of a global navigation satellite system deployed in an autonomous vehicle. A Kalman filter is used for predicting a local sampling rate for the camera and a global sampling rate for the receiver in the global navigation satellite system. The method includes: retrieving length of the lane being traversed by the autonomous vehicle from a graph, where nodes of the graph represent intersection in a road network and edges of the graph represent paths in the road network; measuring speed of the autonomous vehicle as it traverses the lane; estimating the local sampling rate and the global sampling rate using the measured speed and the Kalman filter; and capturing, by the camera, images in accordance with the local sampling rate estimated by the Kalman filter.