Occupancy Grids: A Stochastic Spatial Representation for Active Robot Perception

In this paper we provide an overview of a new framework for robot perception, real-world modelling, and navigation that uses a stochastic tesselated representation of spatial in­ formation called the Occupancy Grid. The Occupancy Grid is a multi-dimensional randomfield model that maintains probabilistic estimates of the occupancy state of each cell in a spatia/lattice. Bayesian estimation mechanisms employ­ ing stochastic sensor models allow incremental updating of the Occupancy Grid using multi-view, multi-sensor data, composition of multiple maps, decision-making. and in­ corporation of robot and sensor position uncertainty. We present the underlying stochastic formulation of the Oc­ cupancy Grid framework, and discuss its application to a variety of robotic tasks. These include range-based mapping, multi-sensor integration, path-planning and ob­ stacle avoidance, handling of robot position uncertainty, incorporation of pre-compiled maps, recovery of geometric representations, and other related problems. The exper­ imental results show that the Occupancy Grid approach generates dense world models, is robust under sensor uncertainty and errors, and allows explicit handling of uncertainty. It supports the development of robust and agile sensor interpretation methods, incremental discovery procedures, and composition of information from multiple sources. Furthermore, the results illustrate that robotic tasks can be addressed through operations performed di­ rectly on the Occupancy Grid, and that these operations have strong parallels to operations performed in the image processing domain.