Shu Hosokawa
Papers
5
Total Citations
25
H-Index
3
About
Shu Hosokawa’s research lies at the intersection of multi-robot systems, game theory, and reinforcement learning, with a focus on enabling autonomous agents to make intelligent, coordinated decisions in dynamic environments. His work on multi-robot coordination using game-theoretic equilibrium switching has been particularly influential, cited 7 times for its novel approach to target tracking—a classic multi-agent problem where robots must independently decide actions to achieve a shared objective. Hosokawa also advanced reinforcement learning by developing reward allocation methods that accelerate learning in stabilizing control tasks, such as the T-inverted pendulum, reducing the time required for real-world robot applications. His integration of particle swarm optimization with path planning, as seen in his StRRT-based approach for RoboCup soccer, demonstrates a practical commitment to improving robot performance in competitive settings. With a total of 25 citations across his most-cited works, Hosokawa’s contributions offer valuable insights for researchers tackling the challenges of multi-agent coordination and efficient learning in robotics.
Research Focus
Key Achievements
Top Papers
- 1StRRT-based path planning with PSO-tuned parameters for RoboCup soccer7 citations · 2014
- 2
- 3
- 4
- 5