Task-Directed Exploration in Continuous POMDPs for Robotic Manipulation of Articulated Objects

TL;DR

This paper introduces STRUG, an online POMDP solver designed for long-horizon planning in uncertain, partially observable environments, demonstrated on robotic manipulation tasks with improved performance over existing methods.

Contribution

The paper presents STRUG, a novel online POMDP solver that effectively manages task-relevant and irrelevant uncertainties in long-horizon planning for robotic manipulation.

Findings

STRUG outperforms existing POMDP solvers on several tasks.

Demonstrated effectiveness on robotic manipulation of articulated objects.

Utilizes neural perception frontend for model distribution construction.

Abstract

Representing and reasoning about uncertainty is crucial for autonomous agents acting in partially observable environments with noisy sensors. Partially observable Markov decision processes (POMDPs) serve as a general framework for representing problems in which uncertainty is an important factor. Online sample-based POMDP methods have emerged as efficient approaches to solving large POMDPs and have been shown to extend to continuous domains. However, these solutions struggle to find long-horizon plans in problems with significant uncertainty. Exploration heuristics can help guide planning, but many real-world settings contain significant task-irrelevant uncertainty that might distract from the task objective. In this paper, we propose STRUG, an online POMDP solver capable of handling domains that require long-horizon planning with significant task-relevant and task-irrelevant uncertainty. We demonstrate our solution on several temporally extended versions of toy POMDP problems as well as robotic manipulation of articulated objects using a neural perception frontend to construct a distribution of possible models. Our results show that STRUG outperforms the current sample-based online POMDP solvers on several tasks.