Bayesian Learning of Occupancy Grids

Abstract

Occupancy grids encode for hot spots on a map that is represented by a two dimensional grid of disjoint cells. The problem is to recursively update the probability that each cell in the grid is occupied, based on a sequence of sensor measurements. In this paper, we provide a new Bayesian framework for generating these probabilities that does not assume statistical independence between the occupancy state of grid cells. This approach is made analytically tractable through the use of binary asymmetric channel models that capture the errors associated with observing the occupancy state of a grid cell. Binary valued measurement vectors are the output of a physical layer detector in an imaging, radar, sonar, or other sensory system. We compare the performance of the proposed framework to that of the classical formulation for occupancy grids. The results show that the proposed framework identifies occupancy grids with lower false alarm and miss rates, and requires fewer observations of the surrounding area to generate an accurate estimate of occupancy probabilities when compared to classical formulations.

Reinforcement Learning for UAV Autonomous Navigation, Mapping and Target Detection

“…The goal of the UAV is to infer the map of the environment by searching the maximum of the belief given the history of measurements (maximum a-posteriori probability (MAP) estimator), i.e., [35], [36]…”