Kenneth Shaw
Papers
10
Total Citations
178
H-Index
5
About
Kenneth Shaw is a robotics researcher whose work sits at the intersection of dexterous manipulation, robot learning, and accessible hardware design. He is perhaps best known for developing the **LEAP Hand**, a low-cost, anthropomorphic robotic hand that can be assembled in under four hours for approximately $2,000 USD — a landmark contribution that has democratized dexterous robotics research and garnered 83 citations since its 2023 release. His follow-up, LEAP Hand V2, extends this work with a hybrid rigid-soft design that more faithfully replicates human hand capabilities. Shaw has also pioneered methods for teaching robots dexterous skills by learning directly from human demonstrations, particularly through internet videos. His "Robotic Telekinesis" system (57 citations) enables real-time robot hand control using only a single RGB camera, while VideoDex and related work leverage large-scale YouTube data to guide robotic learning without requiring costly real-world data collection. Together, these contributions address a fundamental bottleneck in robotics: acquiring rich manipulation experience safely and efficiently. More recently, Shaw has explored open-world mobile manipulation and fine-tuning policies for deformable objects, broadening the scope of where capable robot hands can operate. His body of work reflects a consistent vision — making dexterous robotics more practical, scalable, and accessible for the broader research community.
Research Focus
Key Achievements
Top Papers
- 1LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning83 citations · 2023
- 2
- 3Learning dexterity from human hand motion in internet videos12 citations · 2024
- 4VideoDex: Learning Dexterity from Internet Videos7 citations · 2022
- 5
- 6Adaptive Mobile Manipulation for Articulated Objects In the Open World5 citations · 2024
- 7Designing Anthropomorphic Soft Hands Through Interaction4 citations · 2023
- 8
- 9DEFT: Dexterous Fine-Tuning for Real-World Hand Policies2 citations · 2023
- 10Demonstrating Learning from Humans on Open-Source Dexterous Robot Hands1 citations · 2024