Research

Paper

AI LLM March 04, 2026

IROSA: Interactive Robot Skill Adaptation using Natural Language

Authors

Markus Knauer, Samuel Bustamante, Thomas Eiband, Alin Albu-Schäffer, Freek Stulp, João Silvério

Abstract

Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has received limited attention, particularly for industrial deployment. We present a novel framework that enables open-vocabulary skill adaptation through a tool-based architecture, maintaining a protective abstraction layer between the language model and robot hardware. Our approach leverages pre-trained LLMs to select and parameterize specific tools for adapting robot skills without requiring fine-tuning or direct model-to-robot interaction. We demonstrate the framework on a 7-DoF torque-controlled robot performing an industrial bearing ring insertion task, showing successful skill adaptation through natural language commands for speed adjustment, trajectory correction, and obstacle avoidance while maintaining safety, transparency, and interpretability.

Metadata

arXiv ID: 2603.03897
Provider: ARXIV
Primary Category: cs.RO
Published: 2026-03-04
Fetched: 2026-03-05 06:06

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03897v1</id>\n    <title>IROSA: Interactive Robot Skill Adaptation using Natural Language</title>\n    <updated>2026-03-04T09:54:09Z</updated>\n    <link href='https://arxiv.org/abs/2603.03897v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03897v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has received limited attention, particularly for industrial deployment. We present a novel framework that enables open-vocabulary skill adaptation through a tool-based architecture, maintaining a protective abstraction layer between the language model and robot hardware. Our approach leverages pre-trained LLMs to select and parameterize specific tools for adapting robot skills without requiring fine-tuning or direct model-to-robot interaction. We demonstrate the framework on a 7-DoF torque-controlled robot performing an industrial bearing ring insertion task, showing successful skill adaptation through natural language commands for speed adjustment, trajectory correction, and obstacle avoidance while maintaining safety, transparency, and interpretability.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-04T09:54:09Z</published>\n    <arxiv:comment>Accepted IEEE Robotics and Automation Letters (RA-L) journal, 8 pages, 5 figures, 3 tables, 1 listing</arxiv:comment>\n    <arxiv:primary_category term='cs.RO'/>\n    <author>\n      <name>Markus Knauer</name>\n    </author>\n    <author>\n      <name>Samuel Bustamante</name>\n    </author>\n    <author>\n      <name>Thomas Eiband</name>\n    </author>\n    <author>\n      <name>Alin Albu-Schäffer</name>\n    </author>\n    <author>\n      <name>Freek Stulp</name>\n    </author>\n    <author>\n      <name>João Silvério</name>\n    </author>\n  </entry>"
}