Tomoyoshi Takebayashi

Fujitsu (Japan)

Papers

2

Total Citations

24

H-Index

2

About

Tomoyoshi Takebayashi is a leading researcher in robotic manipulation and computer vision, with a focus on enabling intelligent, adaptive object picking systems. His work addresses critical challenges in industrial automation, particularly the high cost and impracticality of retraining deep learning models when product shapes change. Takebayashi pioneered online self-supervised learning for grasping, developing methods that allow robots to autonomously collect and learn from training data during operation—a breakthrough that reduces reliance on pre-labeled datasets. His 2020 paper on this topic, which has garnered 16 citations, introduced a metric learning approach to detect optimum grasping positions without complete ground truth, solving a fundamental limitation of self-supervised systems. Expanding on this, he proposed a multi-task learning framework that simultaneously handles grasping-position detection and few-shot classification, achieving robust performance with minimal labeled images—a critical advance for factories where objects frequently change. This work, with 8 citations, demonstrates his ability to bridge perception and action in robotics. Takebayashi’s research directly impacts real-world automation by making picking robots more flexible, cost-effective, and easier to deploy, positioning him as a key innovator in the intersection of deep learning and industrial robotics.

Research Focus

Key Achievements

2
H-Index
2
Papers
24
Total Citations
12
Avg Citations/Paper
🏆 Most Cited Paper
Online Self-Supervised Learning for Object Picking: Detecting Optimum Grasping Position using a Metric Learning Approach
16 citations · 2020
📈 Most Prolific Year: 2020 (2 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Fujitsu (Japan)

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago