C Hirayama

Papers

Total Citations

H-Index

About

C. Hirayama is a robotics researcher whose work focuses on the intersection of safe control, learning from demonstration, and scalable autonomy. Their key research areas include dynamic obstacle avoidance, reinforcement learning, and control theory, with a particular emphasis on developing methods that bridge the gap between theoretical guarantees and practical deployment. Hirayama’s most impactful contribution is the introduction of "Sequential Neural Barriers" (2023, 13 citations), a novel framework that uses learned barrier functions to enable scalable, real-time navigation around multiple dynamic obstacles—a critical challenge for autonomous systems operating in crowded environments. This work addresses the exponential complexity of traditional planning methods by leveraging data-driven models. Additionally, Hirayama has advanced the field of Learning from Observations (LfO) with their work on "Learning Stabilization Control from Observations" (2023, 4 citations), which proposes learning Lyapunov-like proxy models to derive stabilizing controllers without explicit reward engineering. This approach simplifies the deployment of reinforcement learning in robotics by using only state-based expert trajectories. Hirayama’s research is notable for its focus on combining theoretical safety guarantees with practical, scalable algorithms, making their work highly relevant for students and researchers interested in safe autonomous navigation and learning-based control.