Bairan Xiang

Papers

Total Citations

H-Index

About

Bairan Xiang is an emerging researcher at the intersection of multi-agent systems, deep reinforcement learning, and autonomous robotics. His work primarily addresses the fundamental challenges of scalability and coordination in complex, real-world environments — problems that sit at the heart of modern robotics and artificial intelligence. Xiang's most significant contribution is SCRIMP (Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding), which has garnered over 49 citations since its 2023 publication. This work advances the Multi-Agent Path Finding (MAPF) field by developing communication strategies that allow agents to coordinate collision-free navigation at scale — a critical breakthrough as the research community increasingly turns to Multi-Agent Reinforcement Learning (MARL) over traditional, computationally expensive planning algorithms. Complementing this, his 2024 work on deep reinforcement learning for large-scale robot exploration (30 citations) demonstrates his breadth across single-agent autonomous systems, proposing a reactive DRL-based planner capable of navigating vast, unknown 2D environments using LiDAR sensing. Together, these contributions position Xiang as a promising voice in scalable autonomous navigation, with growing influence among robotics and AI researchers tackling real-world deployment challenges.