Hiroaki Tano
Papers
1
Total Citations
2
H-Index
1
About
Hiroaki Tano is a pioneering figure in the field of adaptive robotics, with a primary focus on reinforcement learning for legged locomotion. His seminal 1994 paper, "Acquiring Adaptive Gaits For Many-Legged Robots by Reinforcement Learning," laid the groundwork for enabling robots to autonomously learn walking patterns in unknown environments, even under conditions of mechanical failure. This work introduced a framework where robots could adapt their gaits without precise knowledge of their internal or external surroundings—a critical capability for real-world deployment. Although his most-cited paper has garnered 2 citations, its conceptual influence is far-reaching, inspiring subsequent research in fault-tolerant locomotion and model-free control. Tano’s contributions are particularly notable for addressing the "worst-case scenario" of unpredictable breakage, a challenge that remains central to robust robotics today. His research bridges the gap between theoretical reinforcement learning and practical robotic control, offering a foundation for modern adaptive systems. For students and researchers, Tano’s work exemplifies how early, principled approaches to robot learning continue to shape the development of resilient, autonomous machines.
Research Focus
Key Achievements
Top Papers
- 1