Papers
3
Total Citations
59
H-Index
3
About
Kaige Tan is a robotics researcher whose work sits at the intersection of soft robotics, bio-inspired locomotion, and machine learning. His primary research focuses on developing and optimizing gaits for soft quadruped robots—machines built from compliant, tendon-driven actuators rather than traditional rigid components. Tan’s most impactful contribution, "Synthesizing the optimal gait of a quadruped robot with soft actuators using deep reinforcement learning" (2022, 45 citations), demonstrates how reinforcement learning can automatically generate efficient, adaptive locomotion patterns for these flexible systems. He further advanced this line of inquiry with "Optimal gait design for a soft quadruped robot via multi-fidelity Bayesian optimization" (2024), introducing a data-efficient, online learning approach that combines inverse kinematics with central pattern generators. Beyond soft robotics, Tan has contributed to democratizing robotics research through open-source hardware and software platforms, as seen in his 2016 work on accessible tools for AI and robotics applications. His work is notable for bridging the gap between theoretical optimization methods and practical, real-world robot control, making him a key figure in the growing field of soft robotic locomotion.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3