Bao Chen

Papers

Total Citations

H-Index

About

Bao Chen investigates the intersection of large language models and robotics, with a particular focus on scalable simulation for generalist robot training. Their most cited work, "GenSim: Generating Robotic Simulation Tasks via Large Language Models" (2023, 8 citations), addresses a critical bottleneck in robotics: the prohibitive cost of collecting real-world interaction data. By leveraging LLMs to automatically generate diverse, structured simulation tasks, Chen’s approach moves beyond simple scene-level variation—such as randomizing object poses—to create semantically meaningful task curricula. This innovation enables more efficient and generalizable policy learning without requiring expensive human annotation or physical robot time. In parallel, Chen has contributed to clinical robotics through a comparative study of robot-assisted versus traditional freehand pedicle screw fixation for thoracolumbar fractures (2023, 4 citations), providing rigorous 1-year follow-up evidence on surgical accuracy and efficacy. This dual expertise—bridging AI-driven simulation and real-world surgical robotics—positions Chen as a researcher who not only advances foundational methods in robot learning but also validates their translational impact. Their work is particularly relevant for students and researchers seeking to understand how generative AI can lower the data barrier in embodied AI.