Claudia Cuttano
Papers
1
Total Citations
6
H-Index
1
About
Claudia Cuttano investigates the intersection of computer vision, robotics, and cognitive science, with a particular focus on visual affordance reasoning. Her work explores how intelligent systems can understand object functionality beyond simple recognition—identifying which parts of an object enable specific actions, such as grasping a handle or peeling a banana. In her highly cited 2024 paper, "What does CLIP know about peeling a banana?" (6 citations), Cuttano demonstrates how large vision-language models can be leveraged to segment object parts based on the actions they afford, bridging the gap between human-like intuitive tool use and robotic manipulation. This research is foundational for developing robots that can interact with objects in dynamic, unstructured environments, moving beyond rigid pre-programmed behaviors. By grounding affordance learning in multimodal models, Cuttano’s work has significant implications for assistive robotics, autonomous systems, and human-robot interaction. Her contributions are shaping a new generation of machines that not only see objects but understand their potential for action.
Research Focus
Key Achievements
Top Papers
- 1What does CLIP know about peeling a banana?6 citations · 2024