Weiheng Dai

Papers

Total Citations

H-Index

About

Weiheng Dai is an emerging researcher specializing in multi-robot systems, reinforcement learning, and autonomous coordination. His work addresses some of the most pressing challenges in robotics: enabling teams of heterogeneous agents to efficiently collaborate on complex, spatially distributed tasks in dynamic environments. Dai's most influential contribution, "Heterogeneous Multi-robot Task Allocation and Scheduling via Reinforcement Learning" (2025, 24 citations), tackles the intricate problem of assigning robots with differing capabilities to tasks requiring synchronized agent presence — a scenario common in construction, search-and-rescue, and logistics. His follow-up work on dynamic coalition formation (2024, 9 citations) extends this framework to large-scale deployments, where agents must intelligently coordinate trajectories and form coalitions on the fly, reflecting real-world operational complexity. More recently, Dai has ventured into multi-agent pathfinding with SIGMA (2025), a novel sheaf-informed geometric approach that advances decentralized learning for collision-free navigation in obstacle-rich environments — a critical capability for large-scale logistics applications. With over 35 citations across a concise but high-impact publication record, Dai is rapidly establishing himself as a thoughtful contributor to the intersection of reinforcement learning and multi-robot intelligence.