Tianze Yang

Papers

Total Citations

H-Index

About

Tianze Yang is a leading researcher in multi-agent pathfinding (MAPF) and reinforcement learning for robotics, with a focus on scalable, learning-based solutions for complex logistics and transportation systems. Their most-cited work, "ALPHA: Attention-based Long-horizon Pathfinding in Highly-structured Areas" (2024, 12 citations), introduces a novel attention-based neural architecture that enables agents to coordinate collision-free paths in dense, structured environments over long time horizons. This work addresses a critical bottleneck in MAPF—scaling to large teams in real-world settings like warehouse automation and autonomous fleets—by leveraging transformer-style attention mechanisms to capture agent interactions efficiently. Yang’s contributions bridge the gap between classical planning and modern deep learning, offering both theoretical advances in decentralized coordination and practical algorithms that outperform traditional methods. Their research has been recognized for its potential to transform logistics operations, and they continue to push the boundaries of learning-based planning, making them a rising voice in the intersection of AI, robotics, and operations research.