Mingyu Cai

Papers

Total Citations

H-Index

About

Mingyu Cai is an emerging researcher specializing in safe robot learning, motion planning, and formal methods for autonomous systems. His work sits at the critical intersection of control theory, reinforcement learning, and robotics, addressing one of the field's most pressing challenges: enabling robots to operate safely in uncertain, real-world environments. Among his notable contributions, Cai has advanced the integration of temporal logic specifications into reinforcement learning frameworks, developing methods that ensure safe exploration while maintaining effective exploitation for robotic systems with unknown models and measurement uncertainties. His 2021 work on safety-critical learning with temporal logic specifications has garnered 4 citations, reflecting growing interest in principled safety guarantees for learning-based control. His more recent work introduces LQR-CBF-RRT*, an innovative motion planning algorithm that elegantly combines Control Barrier Functions with Linear Quadratic Regulators within a sampling-based planning framework. This approach generates trajectories that are simultaneously safe and optimal, earning 3 citations since its 2023 publication. Though still building his citation profile, Cai's research addresses foundational problems in autonomous robotics, and his interdisciplinary approach bridging formal verification, optimal control, and machine learning positions him as a promising voice in the safe autonomy research community.