Hideki Okamoto

Toyota Motor Corporation (United States), Toyota Motor Corporation (Switzerland)

Papers

Total Citations

H-Index

About

Hideki Okamoto is an emerging robotics researcher whose work sits at the intersection of safe control theory, motion planning, and robot learning. His research focuses on developing rigorous frameworks that ensure safety and reliability in robotic systems operating under uncertainty — a challenge increasingly critical as robots move into real-world, safety-sensitive environments. Okamoto's most notable contribution is CBFkit, a Python/ROS toolbox introduced in 2024 that democratizes the design of control barrier functions (CBFs) for both deterministic and stochastic mobility systems, already accumulating citations that reflect its practical utility for the robotics community. Complementing this, his work on Model Predictive Path Integral methods integrated with CBFs advances the frontier of safe, probabilistic robot control. His 2025 paper on Neural Configuration Signed Distance Functions demonstrates a sophisticated approach to continuum robot shape modeling, enabling accurate, computationally efficient collision avoidance through learned kinematics representations. His contributions further extend to multi-robot coordination, with SMT-based dynamic task allocation methods addressing scalability challenges in autonomous systems. Though early in his career, Okamoto's diverse yet cohesive body of work — spanning toolbox development, neural geometry, and formal methods — positions him as a promising voice in safe and intelligent robotics research.