A Framework for Learning and Reusing Robotic Skills

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hertel, Brendan, Tran, Nhu, Elkoudi, Meriem, Azadeh, Reza
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929402802077696
author Hertel, Brendan
Tran, Nhu
Elkoudi, Meriem
Azadeh, Reza
author_facet Hertel, Brendan
Tran, Nhu
Elkoudi, Meriem
Azadeh, Reza
contents In this paper, we present our work in progress towards creating a library of motion primitives. This library facilitates easier and more intuitive learning and reusing of robotic skills. Users can teach robots complex skills through Learning from Demonstration, which is automatically segmented into primitives and stored in clusters of similar skills. We propose a novel multimodal segmentation method as well as a novel trajectory clustering method. Then, when needed for reuse, we transform primitives into new environments using trajectory editing. We present simulated results for our framework with demonstrations taken on real-world robots.
format Preprint
id arxiv_https___arxiv_org_abs_2404_18383
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Framework for Learning and Reusing Robotic Skills
Hertel, Brendan
Tran, Nhu
Elkoudi, Meriem
Azadeh, Reza
Robotics
In this paper, we present our work in progress towards creating a library of motion primitives. This library facilitates easier and more intuitive learning and reusing of robotic skills. Users can teach robots complex skills through Learning from Demonstration, which is automatically segmented into primitives and stored in clusters of similar skills. We propose a novel multimodal segmentation method as well as a novel trajectory clustering method. Then, when needed for reuse, we transform primitives into new environments using trajectory editing. We present simulated results for our framework with demonstrations taken on real-world robots.
title A Framework for Learning and Reusing Robotic Skills
topic Robotics
url https://arxiv.org/abs/2404.18383