Antonio Pistillo
Papers
5
Total Citations
104
H-Index
4
About
Antonio Pistillo is a robotics researcher whose work sits at the intersection of robot learning, human-robot interaction, and motion control. His research has made meaningful contributions to the field of imitation learning and skill transfer, particularly through the use of probabilistic models and dynamical systems to encode complex task constraints. His most influential work explores how explicit-duration Hidden Markov Models can capture both temporal and spatial structure in robot movements, enabling robots to learn and reproduce tasks demonstrated through kinesthetic teaching — a technique where a human physically guides the robot through a motion. This foundational research has accumulated over 80 citations, reflecting its significant uptake in the robotics learning community. Pistillo has also advanced methods for safe bilateral physical interaction between humans and robot manipulators, proposing weighted combinations of flow fields to enable intuitive and secure collaboration. Beyond industrial applications, he has demonstrated creative versatility by applying haptic robotic interfaces to musical expression, exploring the robot as a bidirectional tangible instrument. His body of work reveals a researcher committed to making robots not only capable learners but also safe, responsive, and even artistically expressive collaborators — pushing the boundaries of how humans and machines can meaningfully interact.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5