Rina Akabane
Papers
2
Total Citations
22
H-Index
2
About
Rina Akabane is a researcher at the forefront of human-robot interaction, specializing in pedestrian trajectory prediction for human-following mobile robots. Her work addresses a critical challenge in service robotics: enabling robots to navigate safely and accurately in human-populated environments like homes and offices. Akabane’s major contribution lies in applying transfer learning and pre-trained machine learning models to predict pedestrian movement, significantly improving the tracking accuracy of mobile robots. Her 2021 paper, “Pedestrian Trajectory Prediction Based on Transfer Learning for Human-Following Mobile Robots,” has garnered 16 citations, while her foundational 2020 study, “Pedestrian Trajectory Prediction Using Pre-trained Machine Learning Model for Human-Following Mobile Robot,” has 6 citations. Notably, Akabane leverages open datasets for training, making her methods accessible and reproducible. Her work is pivotal for advancing autonomous service robots that can seamlessly coexist with humans, enhancing safety and efficiency in shared spaces. For students and researchers, Akabane’s research offers a practical gateway into the intersection of machine learning, robotics, and real-world human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2