Mamoru Miura
Papers
2
Total Citations
35
H-Index
2
About
Mamoru Miura is a researcher specializing in the intersection of reinforcement learning and robotic motion planning, with a particular focus on trajectory optimization for dynamical systems operating under real-world constraints. His most recognized contribution, "Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning" (2019), addresses a fundamental challenge in modern robotics: the difficulty of generating smooth, dynamically feasible trajectories when a system's underlying dynamics are not fully known. By proposing a reinforcement learning-based algorithm capable of handling constrained dynamical systems without requiring explicit model knowledge, Miura's work opens practical pathways for deploying autonomous robots in complex, uncertain environments. This contribution has garnered 35 citations across its publications, reflecting meaningful engagement from the robotics and control communities. His research sits at a critical frontier where data-driven machine learning methods meet the rigorous demands of physical system constraints, an area of growing importance as robotics applications expand into unstructured real-world settings. For students and researchers working on autonomous systems, model-free control, or motion planning, Miura's work offers a valuable methodological foundation bridging theoretical optimization with practical robotic deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2