Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs

TL;DR

Tru-POMDP is a novel planning framework that integrates Large Language Models with POMDPs using a hierarchical Tree of Hypotheses to effectively handle uncertainty and ambiguity in home-service robot tasks.

Contribution

It introduces a hierarchical Tree of Hypotheses and an open-ended POMDP model that leverage LLMs for structured belief generation and efficient planning under uncertainty.

Findings

Outperforms state-of-the-art LLM-based planners in success rate and plan quality.

Demonstrates robustness to ambiguity and occlusion in complex tasks.

Achieves higher planning efficiency in diverse kitchen environments.

Abstract

Task planning under uncertainty is essential for home-service robots operating in the real world. Tasks involve ambiguous human instructions, hidden or unknown object locations, and open-vocabulary object types, leading to significant open-ended uncertainty and a boundlessly large planning space. To address these challenges, we propose Tru-POMDP, a planner that combines structured belief generation using Large Language Models (LLMs) with principled POMDP planning. Tru-POMDP introduces a hierarchical Tree of Hypotheses (TOH), which systematically queries an LLM to construct high-quality particle beliefs over possible world states and human goals. We further formulate an open-ended POMDP model that enables rigorous Bayesian belief tracking and efficient belief-space planning over these LLM-generated hypotheses. Experiments on complex object rearrangement tasks across diverse kitchen environments show that Tru-POMDP significantly outperforms state-of-the-art LLM-based and LLM-tree-search hybrid planners, achieving higher success rates with significantly better plans, stronger robustness to ambiguity and occlusion, and greater planning efficiency.