Tanishq Duhan

Papers

Total Citations

H-Index

About

Tanishq Duhan is an emerging researcher specializing in multi-agent pathfinding (MAPF) and scalable robot coordination, with a focus on bridging classical optimization techniques and modern machine learning approaches. His work addresses one of robotics' most pressing challenges: enabling large teams of agents to navigate complex environments efficiently and without collision — a problem central to warehouse automation, logistics, and transportation systems. Duhan's most recognized contribution, "ALPHA: Attention-based Long-horizon Pathfinding in Highly-structured Areas" (2024, 12 citations), introduces attention mechanisms to improve long-horizon planning in structured environments, advancing the capabilities of learning-based MAPF solvers. His subsequent work on scalable imitation learning for Lifelong MAPF demonstrates ambitions of unprecedented scale, addressing systems involving up to ten thousand robots simultaneously. Additionally, his research on LNS2+RL creatively combines reinforcement learning with Large Neighborhood Search, exemplifying his commitment to hybrid methodologies that leverage the strengths of both classical and learned approaches. With a cumulative citation count growing steadily across recent publications, Duhan represents a promising voice in autonomous multi-robot systems research, consistently pushing the boundaries of what scalable, intelligent coordination can achieve in real-world deployment scenarios.