Hierarchical Object-Oriented POMDP Planning for Object Rearrangement

TL;DR

This paper introduces a hierarchical, object-oriented POMDP planning framework for multi-object rearrangement in complex, partially observable multi-room environments, supported by a new benchmark dataset and demonstrating robust performance.

Contribution

It presents a novel hierarchical object-oriented POMDP approach and a comprehensive MultiRoomR benchmark for challenging multi-object rearrangement tasks.

Findings

Effective handling of complex multi-room scenarios

Robust performance with imperfect perception

Outperforms existing benchmarks

Abstract

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.