Papers
2
Total Citations
91
H-Index
2
About
Motoya Ohnishi is a leading researcher at the intersection of safe reinforcement learning, adaptive control, and robotics. His work is distinguished by a focus on guaranteeing safety during learning, particularly for systems with uncertain or changing dynamics. Ohnishi’s most impactful contribution is the development of barrier-certified adaptive reinforcement learning, a framework that integrates model learning with barrier certificates to ensure safe exploration and operation. This approach, demonstrated in applications like brushbot navigation, has garnered 78 citations and is foundational for deploying learning-based controllers in real-world, safety-critical environments. He has also advanced constraint learning for control tasks with limited-duration barrier functions, addressing how to maintain safety guarantees when constraints are only active for finite time horizons. Ohnishi’s work is notable for its rigorous theoretical grounding combined with practical validation, making him a key figure in the push toward trustworthy autonomous systems. His research empowers robots to learn and adapt without compromising safety, a crucial step for their integration into human-centric settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2