Hiroto Iino
Papers
2
Total Citations
9
H-Index
2
About
Hiroto Iino is a rising roboticist whose work bridges machine learning, human-robot interaction, and autonomous navigation. His research focuses on two core challenges: enabling robots to plan collision-free paths with high-level optimization criteria, and enhancing human operators' sense of agency during teleoperation. In his most-cited work (2023, 7 citations), Iino pioneered a learning-based approach using Conditional Generative Adversarial Networks (cGANs) to map a robot's joint space into a latent space that inherently excludes collision-prone configurations, conditioned on obstacle maps. This allows for efficient, multi-trajectory generation that satisfies arbitrary optimization goals—a significant step toward flexible, real-time motion planning. More recently (2024, 2 citations), he addressed the critical issue of time-varying delays in teleoperation by developing a recurrent neural network (RNN)-based visual guidance system. This work demonstrably boosts the operator's sense of agency—the feeling of directly controlling the robot—which is vital for embodiment and task performance in remote operations. Iino's contributions are particularly notable for integrating generative AI with practical robotics constraints, offering new pathways for both autonomous and human-guided systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2