# A Modular Approach to the Embodiment of Hand Motions from Human Demonstrations

arXiv: https://arxiv.org/abs/2203.02778 · HTML: https://mlsanity.com/paper/2203.02778/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2022.

## Built on by (most cited first, 1 of 1)

- [Signs of Language: Embodied Sign Language Fingerspelling Acquisition from Demonstrations for Human-Robot Interaction](https://mlsanity.com/paper/2209.05135/) (2022)

## Abstract (arXiv)

Manipulating objects with robotic hands is a complicated task. Not only the fingers of the hand, but also the pose of the robot's end effector need to be coordinated. Using human demonstrations of movements is an intuitive and data-efficient way of guiding the robot's behavior. We propose a modular framework with an automatic embodiment mapping to transfer recorded human hand motions to robotic systems. In this work, we use motion capture to record human motion. We evaluate our approach on eight challenging tasks, in which a robotic hand needs to grasp and manipulate either deformable or small and fragile objects. We test a subset of trajectories in simulation and on a real robot and the overall success rates are aligned.