Vision-based Manipulation of Deformable and Rigid Objects Using Subspace Projections of 2D Contours
This work addresses the challenge of robotic manipulation in unstructured environments where object properties are unknown, offering a practical solution for applications in manufacturing or healthcare, though it appears incremental as it builds on existing subspace projection techniques.
The paper tackles the problem of vision-based manipulation of both deformable and rigid objects by proposing a unified framework that automatically learns visual features and interaction matrices from image contours, enabling robots to manipulate objects without prior knowledge of their material properties. The method was validated through numerical simulations and experiments, showing adaptive online extraction with minimal initialization data.
This paper proposes a unified vision-based manipulation framework using image contours of deformable/rigid objects. Instead of using human-defined cues, the robot automatically learns the features from processed vision data. Our method simultaneously generates -- from the same data -- both, visual features and the interaction matrix that relates them to the robot control inputs. Extraction of the feature vector and control commands is done online and adaptively, with little data for initialization. The method allows the robot to manipulate an object without knowing whether it is rigid or deformable. To validate our approach, we conduct numerical simulations and experiments with both deformable and rigid objects.