Yuya Unno

Papers

Total Citations

236

H-Index

About

Yuya Unno’s research sits at the intersection of robotics, natural language processing, and human-in-the-loop machine learning, with a focus on making robots more intuitive and responsive to human communication. His most influential work, “Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions” (2018, 175 citations), tackles the formidable challenge of enabling robots to comprehend and act upon free-form, unconstrained spoken commands—overcoming obstacles like linguistic ambiguity and complex sentence structures that plague real-world human-robot interaction. This work has become a cornerstone for researchers aiming to bridge the gap between natural language understanding and robotic manipulation. Unno also made significant strides in reinforcement learning with his paper “DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback” (2018, 48 citations), which addresses the critical exploration problem in RL by integrating human feedback to accelerate learning—a practical breakthrough for robotics applications where trial-and-error is costly. Through these contributions, Unno has advanced the vision of robots that can learn from and collaborate with humans seamlessly, earning recognition for pushing the boundaries of interactive AI systems.