Keisuke Yoneda
Papers
5
Total Citations
26
H-Index
3
About
Keisuke Yoneda is a robotics and artificial intelligence researcher whose work spans multi-agent systems, autonomous robot coordination, and evolutionary computation. His most influential contributions center on developing autonomous learning frameworks for coordinated robotic tasks, particularly in the domain of continuous cleaning — a challenging real-world application requiring multiple robots to collaboratively cover large areas without explicit communication. His 2013 paper on autonomous target decision strategies, garnering 11 citations, established foundational methods for decentralized coordination, while his 2015 follow-up refined these approaches through shallow coordination techniques, demonstrating the robustness and adaptability of learned strategies. Beyond multi-robot cleaning tasks, Yoneda has explored the acquisition of adaptive behaviors in modular robots using evolutionary computation, contributing to the understanding of how complex locomotive behaviors can emerge from simple, locally communicating modules. His more recent work addresses practical deployment challenges, specifically mitigating efficiency losses caused by planned agent suspensions in cooperative patrol problems — a critical consideration for real-world multi-agent systems. Collectively, Yoneda's research advances the field of intelligent autonomous systems, with particular emphasis on making robot coordination practical, scalable, and resilient in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5