Ryunosuke UCHIDA
Papers
1
Total Citations
1
H-Index
1
About
Ryunosuke Uchida is a robotics researcher whose work centers on reinforcement learning (RL) for autonomous mobile systems, with a particular focus on multi-objective behavior and real-world robot control. His most cited study, "An Experimental Study for Tracking Ability of Deep Q-Network under the Multi-Objective Behaviour using a Mobile Robot with LiDAR" (2021), investigates how Deep Q-Networks (DQN) can be adapted to handle competing objectives in dynamic environments—a critical challenge for deploying RL in physical robots. By integrating LiDAR-based perception with Q-learning, Uchida addresses the scalability limitations of traditional Q-tables, which require vast memory for grid-based updates. His work bridges the gap between simulated RL and practical robotic navigation, demonstrating how DQNs can track multiple goals simultaneously without performance degradation. While his citation count remains modest, his contributions are foundational for researchers exploring multi-objective RL in robotics, particularly for autonomous vehicles and service robots. Uchida’s experimental approach, combining real-world LiDAR data with neural network adaptability, offers a replicable framework for advancing RL’s transition from theory to tangible robotic applications.
Research Focus
Key Achievements
Top Papers
- 1