Adaptive Bi-Level Multi-Robot Task Allocation and Learning under Uncertainty with Temporal Logic Constraints

This work addresses the problem of multi-robot coordination under unknown robot transition models, ensuring that tasks specified by Time Window Temporal Logic are satisfied with user-defined probability thresholds. We present a bi-level framework that integrates (i) high-level task allocation, where tasks are assigned based on the robots’ estimated task completion probabilities and expected rewards, and (ii) low-level distributed policy learning and execution, where robots independently optimize auxiliary rewards while fulfilling their assigned tasks. To handle uncertainty in robot dynamics, our approach leverages data collected during task execution to iteratively refine the expected task completion probabilities and rewards, enabling adaptive task allocation without explicit robot transition models. We theoretically validate the proposed algorithm by showing that it ensures tasks are completed at the desired probability thresholds with high confidence. Finally, we demonstrate the efficacy of our framework through comprehensive simulations.

Authors

• Xiaoshan Lin
• Roberto Tron Boston University

Keywords

• Multi-Robot Systems
• Task Allocation
• Temporal Logic
• Reinforcement Learning