Multi-Keypoint Affordance Representation for Functional Dexterous Grasping

TL;DR

This paper introduces a novel multi-keypoint affordance representation for functional dexterous grasping, directly encoding task-specific grasp configurations to improve manipulation accuracy and generalization in robotic systems.

Contribution

It proposes Contact-guided Multi-Keypoint Affordance (CMKA) and Keypoint-based Grasp matrix Transformation (KGT), enabling precise, generalizable, and direct visual-to-manipulation mapping without manual keypoint annotations.

Findings

Enhanced affordance localization accuracy

Improved grasp consistency and robustness

Better generalization to unseen tools and tasks

Abstract

Functional dexterous grasping requires precise hand-object interaction, going beyond simple gripping. Existing affordance-based methods primarily predict coarse interaction regions and cannot directly constrain the grasping posture, leading to a disconnection between visual perception and manipulation. To address this issue, we propose a multi-keypoint affordance representation for functional dexterous grasping, which directly encodes task-driven grasp configurations by localizing functional contact points. Our method introduces Contact-guided Multi-Keypoint Affordance (CMKA), leveraging human grasping experience images for weak supervision combined with Large Vision Models for fine affordance feature extraction, achieving generalization while avoiding manual keypoint annotations. Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions. Experiments on public real-world FAH datasets, IsaacGym simulation, and challenging robotic tasks demonstrate that our method significantly improves affordance localization accuracy, grasp consistency, and generalization to unseen tools and tasks, bridging the gap between visual affordance learning and dexterous robotic manipulation. The source code and demo videos are publicly available at https://github.com/PopeyePxx/MKA.