UMBRELLA: Uncertainty-aware Multi-robot Reactive Coordination under Dynamic Temporal Logic Tasks

2026-03-26

AI Summary

This work addresses the challenge of balancing environmental uncertainty and real-time responsiveness in multi-robot systems tasked with tracking dynamic moving targets under spatiotemporal constraints. The authors propose an online cooperative planning framework that integrates conformal prediction (CP) with linear temporal logic (LTL) specifications. By modeling target motion uncertainty via CP, they design a CP-guided Monte Carlo tree search (MCTS) algorithm coupled with an uncertainty-aware rollout policy, minimizing the conditional value-at-risk (CVaR) of the average makespan within a receding-horizon optimization scheme. This study presents the first application of CP to multi-robot planning and introduces a lightweight partially synchronized replanning mechanism that significantly enhances robustness and computational efficiency while guaranteeing LTL compliance. Extensive simulations and hardware experiments demonstrate a 23% reduction in average makespan and a 71% decrease in its variance compared to static baselines.

Technology Category

• Multiagent Systems: Multiagent Planning
• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Planning under Uncertainty

Application Category

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

Abstract

Multi-robot systems can be extremely efficient for accomplishing team-wise tasks by acting concurrently and collaboratively. However, most existing methods either assume static task features or simply replan when environmental changes occur. This paper addresses the challenging problem of coordinating multi-robot systems for collaborative tasks involving dynamic and moving targets. We explicitly model the uncertainty in target motion prediction via Conformal Prediction(CP), while respecting the spatial-temporal constraints specified by Linear Temporal Logic (LTL). The proposed framework (UMBRELLA) combines the Monte Carlo Tree Search (MCTS) over partial plans with uncertainty-aware rollouts, and introduces a CP-based metric to guide and accelerate the search. The objective is to minimize the Conditional Value at Risk (CVaR) of the average makespan. For tasks released online, a receding-horizon planning scheme dynamically adjusts the assignments based on updated task specifications and motion predictions. Spatial and temporal constraints among the tasks are always ensured, and only partial synchronization is required for the collaborative tasks during online execution. Extensive large-scale simulations and hardware experiments demonstrate substantial reductions in both the average makespan and its variance by 23% and 71%, compared with static baselines.

Problem

• multi-robot coordination
• dynamic tasks
• uncertainty
• temporal logic
• moving targets

Innovation

• Conformal Prediction
• Monte Carlo Tree Search
• Linear Temporal Logic
• Conditional Value at Risk
• Receding-horizon Planning