Optimal Placement for a Limited-Support Binary Sensor

We present an optimal strategy for placement of a binary sensor based on maximizing the mutual information between the distribution of possible target locations, the sensor footprint, and probability of sensor errors. The result replaces the direct computation of information gradients by a sensor coverage criterion, which can greatly reduce computation. Contributions include closed-form expressions for the optimal sensor placement and a proposed control algorithm for a mobile sensor. The approach is validated with multiple experiments using a quadrotor UAV conducting a search task.