Belief Change Maximisation for Hydrothermal Vent Hunting Using Occupancy Grids

The problem of where a mobile robot should go to efficiently build a map of its surroundings is frequently addressed using entropy reduction techniques. However, in exploration problems where the goal is to find an object or objects of interest, such techniques can be a useful heuristic but are optimising the wrong quantity. An example of such a problem is an autonomous underwater vehicle (AUV) searching the sea floor for hydrothermal vents. The state of the art in these problems is information lookahead in the action-observation space which is computationally expensive. We present an original belief-maximisation algorithm for this problem, and use a simulation of the AUV problem to show that our method outperforms straightforward entropy reduction and runs much faster than information lookahead while approaching it in terms of performance. We further introduce a heuristic using an orienteering-problem (OP) solver, which improves the performance of both our belief-maximisation algorithm and information lookahead.