Akihito Ogawa
Papers
9
Total Citations
154
H-Index
6
About
Akihito Ogawa is a leading robotics researcher specializing in intelligent grasping, bin-picking, and depalletizing automation for logistics and warehouse environments. His work addresses critical challenges in robotic manipulation, particularly the handling of textureless, planar-faced objects and densely packed parcels. Ogawa’s major contributions include developing depth image-based deep learning systems for grasp planning, which eliminate the need for costly human-labeled datasets by leveraging physical simulators. He has also pioneered novel end-effector designs, such as suction pad units with bellows pneumatic actuators and hybrid gripper systems that combine suction and pinching, enabling robust picking of diverse objects. His research on mobile picking robots with wide reach areas and elastic joint mechanisms for cardboard box depalletizing further demonstrates his focus on practical, high-speed automation. With over 150 citations across his most influential papers, Ogawa’s work has significantly advanced the throughput and reliability of vision-guided robotic systems. Notable achievements include the development of a compact depalletizing robot capable of handling complicated stacks and a probabilistic active filtering method for object search in clutter. His recent hybrid-AI grasp planning system, integrating rule-based and deep neural network methods, continues to push the boundaries of efficient, real-world robotic picking.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Mobile Picking-Robot having wide reach area for shelves7 citations · 2019
- 7Probabilistic Active Filtering for Object Search in Clutter6 citations · 2019
- 8
- 9