Generalized Anthropomorphic Functional Grasping with Minimal Demonstrations
Wei Wei, Peng Wang, Sizhe Wang

TL;DR
This paper presents a novel grasp synthesis framework enabling anthropomorphic robots to perform human-like tool-use grasps with minimal demonstrations, validated through extensive simulation and real-world experiments.
Contribution
The authors introduce a six-step contact-based grasp synthesis algorithm and a neural network trained on 10K grasps, improving generalization and success in human-like grasping tasks.
Findings
Outperforms baseline methods in simulation
Achieves 79% success rate on real robots
Demonstrates robustness across object categories
Abstract
This article investigates the challenge of achieving functional tool-use grasping with high-DoF anthropomorphic hands, with the aim of enabling anthropomorphic hands to perform tasks that require human-like manipulation and tool-use. However, accomplishing human-like grasping in real robots present many challenges, including obtaining diverse functional grasps for a wide variety of objects, handling generalization ability for kinematically diverse robot hands and precisely completing object shapes from a single-view perception. To tackle these challenges, we propose a six-step grasp synthesis algorithm based on fine-grained contact modeling that generates physically plausible and human-like functional grasps for category-level objects with minimal human demonstrations. With the contact-based optimization and learned dense shape correspondence, the proposed algorithm is adaptable to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobot Manipulation and Learning · Hand Gesture Recognition Systems · Human Pose and Action Recognition
