Chao Yan

Nanjing University of Aeronautics and Astronautics, National University of Defense Technology, Southeast University

Papers

Total Citations

H-Index

About

Chao Yan is a robotics and autonomous systems researcher whose work sits at the intersection of deep reinforcement learning, multi-robot coordination, and simultaneous localization and mapping (SLAM). His most recognized contribution, "Deep Reinforcement Learning With Multicritic TD3 for Decentralized Multirobot Path Planning" (2024, 22 citations), tackles one of the field's persistent challenges — enabling robots to navigate complex environments without relying on centralized communication, a critical bottleneck in real-world deployments. By extending the Twin Delayed Deep Deterministic Policy Gradient (TD3) framework with a multicritic architecture, Yan advances scalable, decentralized planning strategies with significant practical implications. His work on formation control for robotic fish (2023, 21 citations) further demonstrates his ability to bridge biological inspiration and end-to-end learning, incorporating non-expert imitation to reduce the burden of hand-crafted reward design. Additionally, his development of D-VINS (2023) addresses the fragility of visual-inertial SLAM systems in dynamic scenes, integrating IMU priors and semantic constraints to improve robustness. Together, Yan's research consistently pushes autonomous robots toward greater adaptability, intelligence, and real-world reliability — making his contributions particularly valuable for students exploring mobile robotics, swarm systems, and embodied AI.