Multi-Robot Learning-Informed Task Planning Under Uncertainty

2026-03-20

AI Summary

This work addresses the challenge of enabling multi-robot teams to efficiently collaborate on long-horizon, complex tasks in partially observable environments. To this end, the authors propose a hybrid task planning framework that integrates learning-based uncertainty estimation with model-driven planning. By leveraging learned representations of environmental uncertainty and combining them with multi-stage task abstraction and model predictive control, the approach enables dynamic coordination and adaptive action allocation among robots. This study presents the first tightly coupled integration of learning-driven uncertainty modeling and long-horizon multi-robot planning, substantially enhancing collaborative decision-making capabilities. Experimental results demonstrate that the proposed method significantly outperforms baseline approaches in the ProcTHOR simulation environment and successfully validates efficient collaboration between two LoCoBot robots in real-world domestic settings.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We want a multi-robot team to complete complex tasks in minimum time where the locations of task-relevant objects are not known. Effective task completion requires reasoning over long horizons about the likely locations of task-relevant objects, how individual actions contribute to overall progress, and how to coordinate team efforts. Planning in this setting is extremely challenging: even when task-relevant information is partially known, coordinating which robot performs which action and when is difficult, and uncertainty introduces a multiplicity of possible outcomes for each action, which further complicates long-horizon decision-making and coordination. To address this, we propose a multi-robot planning abstraction that integrates learning to estimate uncertain aspects of the environment with model-based planning for long-horizon coordination. We demonstrate the efficient multi-stage task planning of our approach for 1, 2, and 3 robot teams over competitive baselines in large ProcTHOR household environments. Additionally, we demonstrate the effectiveness of our approach with a team of two LoCoBot mobile robots in real household settings.

Problem

• multi-robot
• task planning
• uncertainty
• coordination
• long-horizon decision-making

Innovation

• multi-robot planning
• learning-informed planning
• uncertainty handling
• long-horizon coordination
• task-relevant object localization