Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning

2026-07-07

AI Summary

Service robots operating in open-world environments often struggle with unexpected situations due to incomplete environmental knowledge and inherent uncertainties. This work proposes a hypothesis-driven planning framework that tightly integrates uncertainty-aware model expansion with task planning for the first time. The approach leverages foundation models to generate hypotheses about states and transitions, concurrently executes tasks and validates these hypotheses through automated planning, and iteratively updates the robot’s knowledge base based on execution feedback. Experimental results demonstrate that the proposed method significantly enhances both the robot’s capability for autonomous knowledge acquisition and its task success rate in both simulated and real-world environments.

Abstract

We consider an open-world planning setting in which service robots must operate in unknown environments with incomplete knowledge of objects and actions. Traditional closed-world approaches with pre-programmed knowledge bases fail when robots encounter unexpected situations and tasks, posing a fundamental challenge for autonomous knowledge expansion in human environments. In this work, we propose an open-world planning framework that enables robots to automatically generate, verify, and update hypotheses about their abstract world models. Our key insight is to explicitly maintain uncertainty-aware knowledge expansion and integrate hypothesis verification into goal-reaching planning. The framework leverages foundation models to generate initial hypotheses over states and transitions, and applies automated planning to produce action sequences that jointly address hypothesis verification and task execution. Through iterative execution and refinement, the robot expands its knowledge by incorporating verification feedback from the foundation models when hypotheses prove incorrect. Extensive experiments in simulated and real-world environments demonstrate that our framework enables autonomous knowledge expansion and effective operation in open-world settings. These results indicate that integrating uncertainty-aware model expansion from robot foundation models with planning advances the practical deployment of household service robots.

Problem

• open-world planning
• knowledge expansion
• uncertainty
• service robots
• autonomous reasoning

Innovation

• open-world planning
• hypothesis-driven model expansion
• uncertainty-aware knowledge
• foundation models
• autonomous knowledge expansion