Takumi Sakamoto

Papers

Total Citations

H-Index

About

Takumi Sakamoto is a robotics researcher whose work centers on intelligent motion planning for industrial manipulation, with a particular focus on efficiency and real-time performance. His major contributions lie in developing novel algorithms that allow robots to reason about and execute complex pick-and-place tasks more intelligently. In his highly cited 2021 paper, "Efficient Picking by Considering Simultaneous Two-Object Grasping" (11 citations), Sakamoto introduced a groundbreaking motion planning algorithm that enables robots to grasp two objects at once. The core of this work is a sophisticated cost function that dynamically selects between single-object, simultaneous two-object, or sequential grasping policies, optimizing for both distance and friction constraints. This approach dramatically improves throughput in bin-picking scenarios. His earlier 2020 work, "Real-time Planning Robotic Palletizing Tasks using Reusable Roadmaps" (8 citations), tackles the repetitive nature of palletizing by proposing reusable Probabilistic Roadmap methods. This innovation allows robots to leverage previously computed paths for similar pick-and-place iterations, achieving real-time planning speeds essential for industrial deployment. Sakamoto’s research bridges the gap between theoretical motion planning and practical, high-speed industrial automation, making him a notable figure in efficient robotic manipulation.