SafeHumanoid: VLM-RAG-driven Control of Upper Body Impedance for Humanoid Robot

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mahmoud, Yara, Sam, Jeffrin, Khang, Nguyen, Fernando, Marcelino, Tokmurziyev, Issatay, Cabrera, Miguel Altamirano, Khan, Muhammad Haris, Lykov, Artem, Tsetserukou, Dzmitry
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918222635204608
author Mahmoud, Yara
Sam, Jeffrin
Khang, Nguyen
Fernando, Marcelino
Tokmurziyev, Issatay
Cabrera, Miguel Altamirano
Khan, Muhammad Haris
Lykov, Artem
Tsetserukou, Dzmitry
author_facet Mahmoud, Yara
Sam, Jeffrin
Khang, Nguyen
Fernando, Marcelino
Tokmurziyev, Issatay
Cabrera, Miguel Altamirano
Khan, Muhammad Haris
Lykov, Artem
Tsetserukou, Dzmitry
contents Safe and trustworthy Human Robot Interaction (HRI) requires robots not only to complete tasks but also to regulate impedance and speed according to scene context and human proximity. We present SafeHumanoid, an egocentric vision pipeline that links Vision Language Models (VLMs) with Retrieval-Augmented Generation (RAG) to schedule impedance and velocity parameters for a humanoid robot. Egocentric frames are processed by a structured VLM prompt, embedded and matched against a curated database of validated scenarios, and mapped to joint-level impedance commands via inverse kinematics. We evaluate the system on tabletop manipulation tasks with and without human presence, including wiping, object handovers, and liquid pouring. The results show that the pipeline adapts stiffness, damping, and speed profiles in a context-aware manner, maintaining task success while improving safety. Although current inference latency (up to 1.4 s) limits responsiveness in highly dynamic settings, SafeHumanoid demonstrates that semantic grounding of impedance control is a viable path toward safer, standard-compliant humanoid collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2511_23300
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SafeHumanoid: VLM-RAG-driven Control of Upper Body Impedance for Humanoid Robot
Mahmoud, Yara
Sam, Jeffrin
Khang, Nguyen
Fernando, Marcelino
Tokmurziyev, Issatay
Cabrera, Miguel Altamirano
Khan, Muhammad Haris
Lykov, Artem
Tsetserukou, Dzmitry
Robotics
Safe and trustworthy Human Robot Interaction (HRI) requires robots not only to complete tasks but also to regulate impedance and speed according to scene context and human proximity. We present SafeHumanoid, an egocentric vision pipeline that links Vision Language Models (VLMs) with Retrieval-Augmented Generation (RAG) to schedule impedance and velocity parameters for a humanoid robot. Egocentric frames are processed by a structured VLM prompt, embedded and matched against a curated database of validated scenarios, and mapped to joint-level impedance commands via inverse kinematics. We evaluate the system on tabletop manipulation tasks with and without human presence, including wiping, object handovers, and liquid pouring. The results show that the pipeline adapts stiffness, damping, and speed profiles in a context-aware manner, maintaining task success while improving safety. Although current inference latency (up to 1.4 s) limits responsiveness in highly dynamic settings, SafeHumanoid demonstrates that semantic grounding of impedance control is a viable path toward safer, standard-compliant humanoid collaboration.
title SafeHumanoid: VLM-RAG-driven Control of Upper Body Impedance for Humanoid Robot
topic Robotics
url https://arxiv.org/abs/2511.23300