Papers
7
Total Citations
38
H-Index
3
About
Tomohiro Motoda is a robotics researcher focused on advancing autonomous manipulation in cluttered, real-world environments—particularly logistics warehouses. His core research areas include bimanual manipulation, motion planning under uncertainty, and object extraction from dense piles. Motoda’s major contributions center on developing planners that enable robots to safely retrieve or replenish objects from randomly stacked shelves without causing collapses, a critical challenge in warehouse automation. His work on the “Bimanual Shelf Picking Planner Based on Collapse Prediction” (15 citations) and “Shelf Replenishment Based on Object Arrangement Detection and Collapse Prediction” (10 citations) introduced novel methods for predicting support relations and coordinating dual-arm actions. He further advanced the field with multi-step extraction planning and learning-based approaches, such as using Transformers for bimanual coordination. Motoda’s research has practical impact, addressing real-world occlusion and stability issues, and his recent integration of CLIP and SAM for precise object masking demonstrates a commitment to leveraging state-of-the-art AI for robotic manipulation. With a growing citation record and publications from 2020 to 2025, Motoda is establishing himself as a promising contributor to intelligent, dexterous robotics.
Research Focus
Key Achievements
Top Papers
- 1Bimanual Shelf Picking Planner Based on Collapse Prediction15 citations · 2021
- 2
- 3
- 4
- 5Motion Planning to Retrieve an Object from Random Pile3 citations · 2022
- 6Probabilistic Action/Observation Planning for Playing Yamakuzushi2 citations · 2020
- 7