Tomotake Sasaki
Papers
3
Total Citations
19
H-Index
2
About
Tomotake Sasaki is a researcher at the forefront of safe and efficient autonomous systems, with key contributions spanning safe reinforcement learning, supervisory control theory, and data-efficient machine learning. His most impactful work, "Efficient Safe Control via Deep Reinforcement Learning and Supervisory Control – Case Study on Multi-Robot Warehouse Automation" (2022, 15 citations), pioneers a hybrid framework that integrates deep reinforcement learning with formal supervisory control theory to guarantee safety in multi-robot systems while overcoming the computational bottlenecks of traditional correct-by-construction methods. This work addresses a critical challenge in safety-critical cyber-physical systems, offering a scalable path toward provably safe autonomy. Sasaki has also advanced practical machine learning through "Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm" (2021, 2 citations), which reduces human annotation burden by leveraging robotic automation for weak labeling. His recent "Safe Exploration Method for Reinforcement Learning Under Existence of Disturbance" (2023, 2 citations) further extends safety guarantees to real-world environments with external perturbations. With a research portfolio that bridges formal methods, robotics, and reinforcement learning, Sasaki is shaping the future of trustworthy autonomous systems, making his work essential reading for researchers tackling safety and efficiency in multi-agent and robotic applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3