Kazuhi Murata
Papers
3
Total Citations
21
H-Index
3
About
Kazuhi Murata is a researcher advancing the field of multi-robot cooperative transportation, with a focus on enabling industrial applications through intelligent formation control and robust physical coordination. His primary research areas include multi-agent reinforcement learning, formation path planning, and error compensation in collaborative manipulation systems. Murata’s most significant contribution is the application of Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to train robots to autonomously learn cooperative transport behaviors, as demonstrated in his 2021 paper (12 citations), which addresses the complex challenge of formation changes during obstacle avoidance. He further enhanced system reliability with a 2023 study (6 citations) introducing a Model Error Compensator for robots equipped with suction cups, mitigating misalignment during object transfer. His experimental validation in 2022 (3 citations) provided critical real-world evidence for the feasibility of these approaches. While his citation counts are currently modest, Murata’s work directly tackles the gap between theoretical multi-robot systems and practical industrial deployment, making his research foundational for future factory and construction site automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3