Generalist Robot Manipulation beyond Action Labeled Data

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Spiridonov, Alexander, Zaech, Jan-Nico, Nikolov, Nikolay, Van Gool, Luc, Paudel, Danda Pani
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915511257792512
author Spiridonov, Alexander
Zaech, Jan-Nico
Nikolov, Nikolay
Van Gool, Luc
Paudel, Danda Pani
author_facet Spiridonov, Alexander
Zaech, Jan-Nico
Nikolov, Nikolay
Van Gool, Luc
Paudel, Danda Pani
contents Recent advances in generalist robot manipulation leverage pre-trained Vision-Language Models (VLMs) and large-scale robot demonstrations to tackle diverse tasks in a zero-shot manner. A key challenge remains: scaling high-quality, action-labeled robot demonstration data, which existing methods rely on for robustness and generalization. To address this, we propose a method that benefits from videos without action labels - featuring humans and/or robots in action - enhancing open-vocabulary performance and enabling data-efficient learning of new tasks. Our method extracts dense, dynamic 3D point clouds at the hand or gripper location and uses a proposed 3D dynamics predictor for self-supervision. This predictor is then tuned to an action predictor using a smaller labeled dataset for action alignment. We show that our method not only learns from unlabeled human and robot demonstrations - improving downstream generalist robot policies - but also enables robots to learn new tasks without action labels (i.e., out-of-action generalization) in both real-world and simulated settings.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19958
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalist Robot Manipulation beyond Action Labeled Data
Spiridonov, Alexander
Zaech, Jan-Nico
Nikolov, Nikolay
Van Gool, Luc
Paudel, Danda Pani
Robotics
Recent advances in generalist robot manipulation leverage pre-trained Vision-Language Models (VLMs) and large-scale robot demonstrations to tackle diverse tasks in a zero-shot manner. A key challenge remains: scaling high-quality, action-labeled robot demonstration data, which existing methods rely on for robustness and generalization. To address this, we propose a method that benefits from videos without action labels - featuring humans and/or robots in action - enhancing open-vocabulary performance and enabling data-efficient learning of new tasks. Our method extracts dense, dynamic 3D point clouds at the hand or gripper location and uses a proposed 3D dynamics predictor for self-supervision. This predictor is then tuned to an action predictor using a smaller labeled dataset for action alignment. We show that our method not only learns from unlabeled human and robot demonstrations - improving downstream generalist robot policies - but also enables robots to learn new tasks without action labels (i.e., out-of-action generalization) in both real-world and simulated settings.
title Generalist Robot Manipulation beyond Action Labeled Data
topic Robotics
url https://arxiv.org/abs/2509.19958