Riccardo Zanella
Papers
10
Total Citations
246
H-Index
7
About
Riccardo Zanella is a robotics researcher whose work centers on the perception and manipulation of deformable linear objects (DLOs), robotic vision, tactile sensing, and deep learning-based control systems. His research addresses one of the field's most persistent challenges: enabling robotic systems to reliably handle flexible, cable-like objects in complex real-world environments. Zanella's most influential contribution, "Integration of Robotic Vision and Tactile Sensing for Wire-Terminal Insertion Tasks" (2018, 93 citations), demonstrated a practical manipulation system combining cameras and custom tactile sensors for automating electrical wire insertion—a task critical to industrial assembly. Building on this foundation, he developed Ariadne+, a deep learning framework for wire instance segmentation (2022, 46 citations), and RT-DLO, a real-time segmentation system for deformable linear objects (2023, 33 citations), collectively advancing robotic perception of notoriously difficult-to-model objects. His more recent work explores online model parameter estimation for DLO manipulation (2024, 32 citations) and passivity-based reinforcement learning (2024), reflecting a broadening toward robust, adaptive control strategies. With contributions spanning tactile feedback systems, graph neural networks, and industrial deployment of deep learning, Zanella's cumulative impact—exceeding 240 citations—marks him as a significant emerging voice in robot manipulation research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3RT-DLO: Real-Time Deformable Linear Objects Instance Segmentation33 citations · 2023
- 4
- 5DLO-in-Hole for Assembly Tasks with Tactile Feedback and LSTM Networks13 citations · 2019
- 6Automatized Switchgear Wiring: An Outline of the WIRES Experiment Results12 citations · 2019
- 7Learning passive policies with virtual energy tanks in robotics7 citations · 2024
- 8
- 9
- 10