🤖 AI Summary
Enabling dexterous, human-in-the-loop robotic grasping for users with disabilities requires simultaneous adaptation to dynamic user intent and diverse object geometries. Method: We propose GraspGF—a hand-object-intent-conditioned grasp gradient field—and a history-dependent residual policy framework. This is the first work to introduce score-based generative modeling into assistive grasping, decoupling pose generation (“how to grasp”) from temporal control (“when and how fast to grasp”). Our approach integrates score-matching gradient field modeling, conditional diffusion priors, a residual network encoding trajectory history, and sim-to-real transfer training. Contribution/Results: Evaluated on multi-object, multi-intent scenarios, GraspGF significantly outperforms state-of-the-art methods. Real-world experiments demonstrate strong intent awareness and real-time responsiveness. The code and demonstration videos are publicly available.
📝 Abstract
The use of anthropomorphic robotic hands for assisting individuals in situations where human hands may be unavailable or unsuitable has gained significant importance. In this paper, we propose a novel task called human-assisting dexterous grasping that aims to train a policy for controlling a robotic hand's fingers to assist users in grasping objects. Unlike conventional dexterous grasping, this task presents a more complex challenge as the policy needs to adapt to diverse user intentions, in addition to the object's geometry. We address this challenge by proposing an approach consisting of two sub-modules: a hand-object-conditional grasping primitive called Grasping Gradient Field~(GraspGF), and a history-conditional residual policy. GraspGF learns `how' to grasp by estimating the gradient from a success grasping example set, while the residual policy determines `when' and at what speed the grasping action should be executed based on the trajectory history. Experimental results demonstrate the superiority of our proposed method compared to baselines, highlighting the user-awareness and practicality in real-world applications. The codes and demonstrations can be viewed at"https://sites.google.com/view/graspgf".
