Yu Kubota

Papers

Total Citations

H-Index

About

Yu Kubota is a researcher advancing the field of autonomous mobile robotics, with a focus on intelligent motion planning and obstacle avoidance. Their key research areas include deep learning-based navigation, mediated perception, and the integration of convolutional neural networks (CNNs) with long short-term memory (LSTM) architectures for dynamic environment handling. Kubota’s major contributions include developing a motion planner that combines CNNs with LSTM blocks through mediated perception, enabling mobile robots to effectively avoid both static and dynamic obstacles while navigating toward destinations. This work, published in 2024, has already garnered 7 citations, reflecting its timely relevance. Additionally, their 2023 paper on a mobile robot motion planner utilizing an obstacle state classifier, with 4 citations, further demonstrates their systematic approach to improving autonomous navigation. Kubota’s research is notable for addressing the critical challenge of real-time adaptation to moving obstacles, a key hurdle in practical robotics. Their work is valuable for students and researchers interested in deep learning for robotics, autonomous systems, and sensor-based navigation, offering a pathway toward safer and more efficient mobile robot operation in complex environments.