Kenta Miyazaki
Papers
3
Total Citations
17
H-Index
2
About
Kenta Miyazaki is a robotics researcher focused on advancing multi-robot coordination, particularly in the domain of cooperative transportation. His work addresses a critical challenge in industrial automation: enabling multiple robots to collaboratively transport large or awkward objects through dynamic environments. Miyazaki’s primary contributions lie in applying and refining deep reinforcement learning algorithms to solve the complex problem of formation path learning. His most influential work, "Formation path learning for cooperative transportation of multiple robots using MADDPG" (2021, 12 citations), pioneered the use of Multi-Agent Deep Deterministic Policy Gradient to allow robots to autonomously learn cooperative transport strategies. He has since extended this research through experimental validation in "Experiment of Cooperative Transportation using Multi-Robots by Multi-agent Deep Deterministic Policy Gradient" (2022, 3 citations) and explored faster learning mechanisms with "On Fast Learning of Cooperative Transport by Multi-robots using DeepDyna-Q" (2022, 2 citations). While his citation counts are modest, reflecting the emerging nature of this specialized field, Miyazaki’s work represents an important step toward practical, scalable multi-robot systems for factories and construction sites, bridging the gap between theoretical reinforcement learning and real-world industrial deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3