Learning environment properties in Partially Observable Monte Carlo Planning

We tackle the problem of learning state-variable relationships in Partially Observable Markov Decision Processes to improve planning performance on mobile robots. The proposed approach extends Partially Observable Monte Carlo Planning (POMCP) and represents state-variable relationships with Markov Random Fields. A ROS-based implementation of the approach is proposed and evaluated in rocksample, a standard benchmark for probabilistic planning under uncertainty. Experiments have been performed in simulation with Gazebo. Results show that the proposed approach allows to effectively learn state- variable probabilistic constraints on ROS-based robotic platforms and to use them in subsequent episodes to outperform standard POMCP