Bingqing Chen
Papers
1
Total Citations
4
H-Index
1
About
Bingqing Chen is a leading researcher at the intersection of robotics, simulation, and causal machine learning, with a core focus on bridging the sim-to-real gap. Her most-cited work, "What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery" (2023), introduces a groundbreaking framework that uses differentiable causal discovery to identify and correct discrepancies between simulated and real-world dynamics. By treating modeling errors as causal structure learning problems, Chen’s approach enables robots to autonomously diagnose why policies fail in deployment—a paradigm shift from traditional domain randomization or system identification. Though early in its trajectory (4 citations), this paper has already influenced how roboticists think about interpretable sim-to-real transfer. Chen’s broader contributions span reinforcement learning, differentiable programming, and causal inference, where she advocates for transparent, data-efficient methods that expose the "why" behind policy failures. Her work is particularly notable for its practical rigor: she designs algorithms that not only improve robot performance but also provide engineers with actionable insights into model flaws. As a rising voice in robotics, Chen is shaping a future where simulation-trained agents can reliably and explainably adapt to the messy realities of the physical world.
Research Focus
Key Achievements
Top Papers
- 1