Kyohei Unuma

About

Kyohei Unuma is a robotics researcher whose work focuses on advancing autonomous navigation for mobile robots, particularly through deep learning-based motion planning. His key research areas include end-to-end motion planning, multi-task learning, and sensor-driven navigation using 2D LiDAR. Unuma’s major contribution lies in developing deep neural network (DNN) architectures, such as multilayer perceptrons (MLPs), that enable robots to move toward destinations while avoiding obstacles in real time. His most cited paper, "End-to-End Motion Planners Through Multi-Task Learning for Mobile Robots with 2D LiDAR" (2023, 5 citations), demonstrates how multi-task learning can improve the efficiency and robustness of motion planning by simultaneously handling multiple navigation objectives. This work is notable for its practical approach to integrating LiDAR data directly into neural network planners, reducing the need for handcrafted features. Though early in his career, Unuma’s research has already contributed to the growing field of learning-based robotics, offering scalable solutions for autonomous systems. His work is particularly relevant for students and researchers interested in deep learning applications for real-world robot navigation.

Research Focus

Key Achievements

Top Papers

1. 1
   End-to-End Motion Planners Through Multi-Task Learning for Mobile Robots with 2D LiDAR

   5 citations · 2023

Key Collaborators

Contact & Links