paper-with-me

Papers

Generalist Robot Manipulation beyond Action Labeled Data

2025-09-24 · Alexander Spiridonov, Jan-Nico Zaech, Nikolay Nikolov, Luc Van Gool, Danda Pani Paudel arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.19958

Code (0)

등록된 구현이 없습니다.

Tasks

Robot ManipulationPoint Clouds

Similar Papers 제목 키워드 기반

JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignment

2026-08-06 · JoyAI-RA Team arxiv

Robot data is scarce, so generalist policies need to learn from heterogeneous sources, including human egocentric video, simulation, and real robots, which differ in supervision and embodiment, with action labels missing…

Robot Manipulation

Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding

2025-01-08 · Joshua Jones, Oier Mees, Carmelo Sferrazza, Kyle Stachowicz 외

Interacting with the world is a multi-sensory experience: achieving effective general-purpose interaction requires making use of all available modalities -- including vision, touch, and audio -- to fill in gaps from part…

Robot ManipulationText GenerationVision-Language-Action

Octo: An Open-Source Generalist Robot Policy

2024-05-20 · Octo Model Team, Dibya Ghosh, Homer Walke, Karl Pertsch 외

Large policies pretrained on diverse robot datasets have the potential to transform robotic learning: instead of training new policies from scratch, such generalist robot policies may be finetuned with only a little in-d…

Robot Manipulation

GR-Dexter Technical Report

2025-12-30 · Ruoshi Wen, Guangzeng Chen, Zhongren Cui, Min Du 외 arxiv

Vision-language-action (VLA) models have enabled language-conditioned, long-horizon robot manipulation, but most existing systems are limited to grippers. Scaling VLA policies to bimanual robots with high degree-of-freed…

Robot Manipulation

RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning

2024-12-13 · Charles Xu, Qiyang Li, Jianlan Luo, Sergey Levine

Recent advances in robotic foundation models have enabled the development of generalist policies that can adapt to diverse tasks. While these models show impressive flexibility, their performance heavily depends on the q…

reinforcement-learningReinforcement Learning