Robotic Cleaning Through Dirt Rearrangement Planning with Learned Transition Models

We address the problem of enabling a manipulator to move arbitrary amounts and configurations of dirt on a surface to a goal region using a cleaning tool. We represent this problem as heuristic search with a set of primitive dirt-oriented tool actions. We present dirt and action representations that allow efficient learning and prediction of future dirt states, given the current dirt state and applied action. We also present a method for sampling promising actions based on a clustering of dirt states and heuristics for planning. We demonstrate the effectiveness of our approach on challenging cleaning tasks through implementations on PR2 and Fetch robots.