Melding LLMs and Temporal Logics for Reliable Multi-robot Task Planning in Complex Scenarios

Abstract

Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating the operator's intent into coordinated swarm actions and helping determine when validation or intervention is required during execution. In long-horizon missions under dynamic scenarios, however, reliable task planning becomes difficult to maintain: emerging events and changing conditions demand continual adaptation, and sustained operator oversight imposes substantial cognitive burden. Existing LLM-based planning tools can support plan generation, yet they remain susceptible to invalid task orderings and infeasible robot actions, resulting in frequent manual adjustment.

Here we introduce a neuro-symbolic framework for long-horizon human-swarm collaboration that tightly melds verifiable task planning with context-grounded LLM reasoning. We formalize mission goals and operational rules as temporal logic formulas and admissible task orderings as task automata. Conditioned on these formal constraints and live perceptual context, LLMs generate executable subtask sequences that satisfy mission rules and remain grounded in the current scene. An uncertainty-aware scheduler then assigns subtasks across the heterogeneous swarm to maximise parallelism while remaining resilient to disruptions. An event-triggered interaction protocol further limits operator involvement to sparse, high-level confirmation and guidance. Deployment on a heterogeneous robotic fleet yields similar results while remaining robust to hardware-specific actuation and communication uncertainties. Simulation and experiment results show that our method, compared to state-of-the-art baselines, significantly improves task success rates and greatly reduces operator interventions and lowers physiological stress.

Speaker

Prof. Zhongkui Li received the BSc degree in Space Engineering from the National University of Defense Technology, China, in 2005, and his PhD degree in Dynamical Systems and Control from Peking University, China, in 2010. Since 2013, he has been with the Peking University, China, where he is currently a Full Professor with the School of Advanced Manufacturing and Robotics. His current research interests include cooperative control and planning of multi-agent systems.

Prof. Li was the recipient of the China National Science Funds for Distinguished Young Scientists in 2024, the State Natural Science Award of China in 2015, the Natural Science Award of the Ministry of Education of China in 2022 and 2011, and the National Excellent Doctoral Thesis Award of China in 2012. His coauthored papers received the IET Control Theory & Applications Premium Award in 2013 and the Best Paper Award of Journal of Systems Science & Complexity in 2012. He serves/has served as an Associate Editor of IEEE Transactions on Automatic Control, International Journal of Robust and Nonlinear Control, and several other journals.