Junpeng Gao

Papers

Total Citations

H-Index

About

Junpeng Gao is a rising researcher at the forefront of soft robotics, dedicated to bridging the critical gap between simulation and real-world performance. His primary research areas include soft robot modeling, simulation-to-reality (sim-to-real) transfer, and data-driven physics learning. Gao’s most significant contribution is his pioneering work on learned residual physics, which directly tackles the computational expense and inaccuracy inherent in modeling soft robots. By developing a framework that augments traditional simulation with a learned correction term, his research dramatically improves the fidelity of virtual models, enabling more reliable control and design of these flexible machines. This work, detailed in his highly cited 2024 paper, has already garnered over 20 citations, signaling its immediate impact on the field. Gao’s approach offers a practical pathway to deploy soft robots in the real world without exhaustive manual tuning, a long-standing challenge in robotics. His achievements mark him as a key innovator, making complex soft robotic systems more accessible and robust for applications ranging from medical devices to exploration.