Entropy-based environment exploration and kochastic optimal control
Marco Baglietto, Massimo Paolucci, Luca Scardovi, R. Zoppoli · 2004
This paper deals with the problem of mapping an unknown environment by a team of autonomous decision makers. A discrete grid map of the environment is considered in which each cell is labeled as free or not free, depending on the presence of an obstacle. The decision makers can communicate with one another. A preliminary study of the problem in the framework of stochastic optimal control is presented. The tradeoff between the exploration cost and the information gain (exploiting the concept of entropy) is addressed. Numerical results show the effectiveness of the approach.