Online Replanning in Belief Space for Partially Observable Task and Motion Problems
This addresses the challenge of autonomous robot operation in uncertain, real-world settings like kitchens, but it appears incremental as it builds on existing planning methods with modifications for efficiency and progress retention.
The paper tackles the problem of enabling robots to perform multi-step manipulation tasks in partially observable environments by updating their belief about the world and replanning actions online. It presents a system that efficiently solves such problems in simulation and a real-world kitchen, though no concrete numbers are provided.
To solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object out of the way to examine the space behind it. Upon receiving a new observation, the robot must update its belief about the world and compute a new plan of action. In this work, we present an online planning and execution system for robots faced with these challenges. We perform deterministic cost-sensitive planning in the space of hybrid belief states to select likely-to-succeed observation actions and continuous control actions. After execution and observation, we replan using our new state estimate. We initially enforce that planner reuses the structure of the unexecuted tail of the last plan. This both improves planning efficiency and ensures that the overall policy does not undo its progress towards achieving the goal. Our approach is able to efficiently solve partially observable problems both in simulation and in a real-world kitchen.