Alessio Caporali
Papers
14
Total Citations
200
H-Index
7
About
Alessio Caporali is a robotics researcher whose work centers on one of automation's most persistent challenges: enabling robotic systems to perceive and manipulate Deformable Linear Objects (DLOs) such as wires, cables, ropes, and hoses. His research sits at the intersection of computer vision, deep learning, and robotic manipulation, with a particular focus on bridging the gap between laboratory robotics and real-world industrial environments. Caporali's most influential contributions include the development of Ariadne+, a deep learning framework for wire instance segmentation that has garnered 46 citations, and RT-DLO, a real-time segmentation system with 33 citations, both of which address the fundamental perception barriers that have historically limited robotic handling of flexible objects. His work on online model parameter estimation for DLO manipulation (32 citations) further demonstrates his drive to make robotic systems adaptive and practically deployable. Beyond perception, Caporali has advanced 3D shape estimation from multi-view 2D imagery, weakly supervised dataset generation, and shared autonomy teleoperation frameworks, collectively accumulating over 190 citations. His research also extends into human-robot interfaces, including sEMG-based prosthetic hand control. Taken together, his body of work represents a comprehensive and growing contribution toward making flexible object manipulation a tractable problem for modern robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2RT-DLO: Real-Time Deformable Linear Objects Instance Segmentation33 citations · 2023
- 3
- 4
- 5
- 63D DLO Shape Detection and Grasp Planning from Multiple 2D Views12 citations · 2021
- 7
- 8
- 9
- 10Cable Detection and Manipulation for DLO-in-Hole Assembly Tasks4 citations · 2022