Hierarchical Object-Oriented POMDP Planning for Object Rearrangement
This addresses the problem of adaptability in object rearrangement for robotics, though it is incremental as it builds on existing POMDP methods.
The paper tackles multi-object rearrangement in partially observable, multi-room environments by introducing a Hierarchical Object-Oriented POMDP planning approach, achieving robust performance with 10-20 objects across 2-4 rooms and 10-30% initial visibility.
We present an online planning framework and a new benchmark dataset for solving multi-object rearrangement problems in partially observable, multi-room environments. Current object rearrangement solutions, primarily based on Reinforcement Learning or hand-coded planning methods, often lack adaptability to diverse challenges. To address this limitation, we introduce a novel Hierarchical Object-Oriented Partially Observed Markov Decision Process (HOO-POMDP) planning approach. This approach comprises of (a) an object-oriented POMDP planner generating sub-goals, (b) a set of low-level policies for sub-goal achievement, and (c) an abstraction system converting the continuous low-level world into a representation suitable for abstract planning. To enable rigorous evaluation of rearrangement challenges, we introduce MultiRoomR, a comprehensive benchmark featuring diverse multi-room environments with varying degrees of partial observability (10-30\% initial visibility), blocked paths, obstructed goals, and multiple objects (10-20) distributed across 2-4 rooms. Experiments demonstrate that our system effectively handles these complex scenarios while maintaining robust performance even with imperfect perception, achieving promising results across both existing benchmarks and our new MultiRoomR dataset.