Max Robotics — Global Service Robot Directory + US Certification

About

Masashi Okada is a leading researcher at the intersection of robot learning, control, and state representation, whose work is reshaping how robots acquire complex manipulation skills. His primary research areas include imitation learning, impedance control, and contact-rich manipulation, with a focus on enabling robots to operate safely and efficiently in real-world environments. Okada's major contributions include pioneering domain-adversarial and conditional state space models for imitation learning, which allow robots to learn abstract, domain-agnostic features from partially observable data—a critical advancement for generalizable robot control. His work on learning compliant stiffness through impedance control-aware task segmentation and multi-objective Bayesian optimization has set new standards for safe industrial robot operation, moving beyond traditional position control. Most recently, Okada introduced the Diffusion Contact Model (DCM), a novel approach using denoising diffusion to learn variable impedance control for contact-rich tasks like wiping, achieving state-of-the-art results in manipulation. With over 19 citations across his most-cited papers, Okada's research is gaining rapid recognition for its practical impact. His innovative integration of Bayesian optimization with prior knowledge and diffusion models marks him as a rising star in robot learning, with work that directly addresses the safety and adaptability challenges facing modern robotics.