David A. W. Barton
Papers
6
Total Citations
55
H-Index
4
About
David A. W. Barton is a leading researcher at the intersection of robotics, tactile sensing, and reinforcement learning. His primary research areas include tactile perception, non-prehensile manipulation, and data-efficient learning for robotic systems. Barton’s major contributions center on enabling robots to interact with dynamic, unstructured environments through advanced tactile sensing. He pioneered methods for shear-invariant sliding contact perception and developed sim-to-real deep reinforcement learning frameworks for tactile pushing, bridging the gap between simulation and physical robot control. His work on online learning with Gaussian Process Latent models has significantly improved data efficiency for tactile contour following, reducing the need for large training datasets. With over 55 citations across his most-cited papers, including 18 for his 2023 work on tactile pushing, Barton’s research has been recognized for its practical impact on robotic manipulation. Notable achievements include his 2019 paper on shear-invariant contact perception and his 2024 work on tactile control for dynamic object tracking, which addresses real-world challenges of moving objects. Barton’s innovative approaches to tactile sensing and learning continue to shape the future of dexterous robotic manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Shear-invariant Sliding Contact Perception with a Soft Tactile Sensor10 citations · 2019
- 4Equilibrium Configurations for a Territorial Model8 citations · 2009
- 5Tactile control for object tracking and dynamic contour following3 citations · 2024
- 6