Ryota Yoshimura
Papers
2
Total Citations
6
H-Index
2
About
Ryota Yoshimura is a researcher specializing in mobile robotics, with a particular focus on advancing state estimation and localization techniques. His work sits at the intersection of probabilistic filtering and reinforcement learning, aiming to make robots more autonomous and reliable in real-world environments. Yoshimura’s major contributions include the development of a novel reinforcement-learning-based method for designing particle filter models, which traditionally require manual tuning by users. This approach, detailed in his 2022 paper, automates the design process, improving performance in nonlinear and non-Gaussian systems. He also introduced the concept of a "highlighted map," a new kind of environmental representation that uses reinforcement learning to identify and emphasize unique landmarks in monotonous settings. This innovation, presented in his 2020 work, enables robots to use these landmarks as reliable cues for localization, significantly enhancing navigation accuracy. While his most-cited papers each hold 3 citations, reflecting an emerging career, the originality and practical relevance of his ideas signal strong potential for future impact. Yoshimura’s work is particularly valuable for students and researchers interested in adaptive robotics, sensor fusion, and learning-based perception systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2