Glen Chou
Papers
2
Total Citations
36
H-Index
2
About
Glen Chou is a robotics and AI researcher whose work sits at the intersection of formal methods, natural language processing, and safe motion planning for robotic systems. His research addresses two critical challenges in modern robotics: making robots understandable and programmable by non-experts, and ensuring they operate safely in uncertain real-world environments. Chou's most visible contribution, "Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification" (2023, 31 citations), tackles the fundamental problem of bridging human communication and machine-interpretable task definitions. By developing methods to translate natural language commands into Linear Temporal Logic (LTL), he enables everyday users to specify complex robot behaviors without formal programming expertise — a significant step toward democratizing robotics. Complementing this, his work on statistical safety guarantees for feedback motion planning addresses how robots with unknown, nonlinear stochastic dynamics can still be trusted to operate reliably. By jointly learning dynamics models and providing provable runtime safety and goal-reachability guarantees from data alone, Chou advances the frontier of trustworthy autonomous systems. His research reflects a cohesive vision: robots that are both accessible to humans and rigorously safe — a combination essential for real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2