Functional Eigen-Grasping Using Approach Heatmaps
🤖 AI Summary
This work addresses the challenge of autonomously positioning the palm of multi-fingered robotic hands to accurately contact functional components (e.g., buttons, triggers) during everyday tool manipulation—without human demonstration. We propose a novel functional grasping framework that jointly optimizes palm pose and functional contact via a heatmap-based guidance mechanism, uniquely integrating directional manipulability analysis with a dual-energy function (penalizing both suboptimal palm placement and poor functional-component contact). The resulting heatmaps drive low-dimensional eigengrasp control to achieve stable, task-oriented grasps. The framework is hand-agnostic, supporting both anthropomorphic (Shadow) and non-anthropomorphic (Barrett) hands, and automatically identifies optimal functional workspaces. Experiments demonstrate successful generalization across diverse tools—including spray bottles, power drills, and remote controls—significantly improving cross-hand morphology and cross-tool heterogeneity adaptability. This establishes a new paradigm for general-purpose functional manipulation.
Application Category
📝 Abstract
This work presents a framework for a robot with a multi-fingered hand to freely utilize daily tools, including functional parts like buttons and triggers. An approach heatmap is generated by selecting a functional finger, indicating optimal palm positions on the object's surface that enable the functional finger to contact the tool's functional part. Once the palm position is identified through the heatmap, achieving the functional grasp becomes a straightforward process where the fingers stably grasp the object with low-dimensional inputs using the eigengrasp. As our approach does not need human demonstrations, it can easily adapt to various sizes and designs, extending its applicability to different objects. In our approach, we use directional manipulability to obtain the approach heatmap. In addition, we add two kinds of energy functions, i.e., palm energy and functional energy functions, to realize the eigengrasp. Using this method, each robotic gripper can autonomously identify its optimal workspace for functional grasping, extending its applicability to non-anthropomorphic robotic hands. We show that several daily tools like spray, drill, and remotes can be efficiently used by not only an anthropomorphic Shadow hand but also a non-anthropomorphic Barrett hand.
Problem
Research questions and friction points this paper is trying to address.
Generate approach heatmaps for tool grasping
Enable functional grasping without human demonstrations
Adapt grasping to various tool sizes and designs
Innovation
Methods, ideas, or system contributions that make the work stand out.
Approach heatmaps for functional grasping
Eigengrasp with palm and functional energy
Directional manipulability for heatmap generation
🔎 Similar Papers
No similar papers found.
