Papers
11
Total Citations
256
H-Index
7
About
Tianjian Chen is a pioneering researcher at the intersection of robotics, machine learning, and autonomous systems. His work spans three transformative domains: federated reinforcement learning for autonomous driving, intelligent prosthetic design, and hardware-software co-optimization for robotic manipulation. Chen’s most impactful contribution is his work on federated transfer reinforcement learning for autonomous driving (94 citations), which enables multiple vehicles to collaboratively learn driving policies while preserving data privacy—a critical advancement for scalable autonomous fleets. In biomechatronics, he designed an ankle-foot prosthesis emulator with active inversion-eversion control (40 citations), addressing a key gap in prosthetic balance and mobility. Chen has also broken new ground in robotic hand design, co-optimizing mechanical structure and control policies using deep reinforcement learning (23 citations), demonstrating that hardware itself can be treated as a learnable policy. His work on underactuated hand synergies (12 citations) provides a principled method for achieving dexterous grasping with minimal actuation. With over 250 total citations, Chen’s research uniquely bridges theoretical machine learning, practical hardware design, and human-centered robotics, making him a leading voice in creating intelligent, adaptive, and physically embodied AI systems.
Research Focus
Key Achievements
Top Papers
- 1Federated Transfer Reinforcement Learning for Autonomous Driving94 citations · 2022
- 2
- 3Federated Transfer Reinforcement Learning for Autonomous Driving39 citations · 2019
- 4
- 5Co-designing hardware and control for robot hands23 citations · 2021
- 6Underactuated Hand Design Using Mechanically Realizable Manifolds12 citations · 2018
- 7
- 8
- 9
- 10