Shu Ishida
Papers
2
Total Citations
10
H-Index
2
About
Shu Ishida is a roboticist and computer scientist whose research lies at the intersection of embodied AI, deep learning, and autonomous navigation. His work addresses a critical gap in robotics: how to enable agents to plan and navigate through complex, unseen 3D environments without relying on pre-mapped models or hazardous trial-and-error. In his highly cited 2022 paper, "Towards real-world navigation with deep differentiable planners" (6 citations), Ishida introduced a framework that trains neural networks to learn state transitions and rewards directly, significantly improving an agent’s ability to generalize to real-world deployment. Earlier, in "Robot Path Planning for Multiple Target Regions" (2019, 4 citations), he tackled the practical challenge of planning optimal routes through sequences of regions rather than simple point goals—a problem central to mobile robotics in dynamic settings. Though early in his career, Ishida’s contributions are already shaping how researchers think about safe, scalable navigation. His work is particularly notable for its focus on bridging simulation-trained models with real-world constraints, a key step toward truly autonomous systems in logistics, search-and-rescue, and service robotics.
Research Focus
Key Achievements
Top Papers
- 1Towards real-world navigation with deep differentiable planners6 citations · 2022
- 2Robot Path Planning for Multiple Target Regions4 citations · 2019