DeformGrasp: A Human-Guided and Synthetic Data Framework for Learning-Based Deformable Object Grasping Using Anthropomorphic Robot Hands
An imitation learning framework for developing a model-free behavioral cloning (BC) policy that generates grasp strategies for three-dimensional deformable objects and results demonstrate that contact-driven augmentation and BC can support ARH grasping of three-dimensional deformable objects despite an initial small-nu...