操作与视觉语言模型

OpenVLA系列工作

OpenVLA teaser

OpenVLA: An Open-Source Vision-Language-Action Model

arXiv 论文链接

具身操作VLA foundation model

OpenVLA-OFT teaser

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

arXiv 论文链接

具身操作VLA foundation model

RDT teaser

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

arXiv 论文链接

双臂协同操作foundation model。

π系列工作

pi0 teaser

π0: A Vision-Language-Action Flow Model for General Robot Control

arXiv 论文链接

PI系列VLA关键工作

pi0.5 teaser

π0.5: a Vision-Language-Action Model with Open-World Generalization

arXiv 论文链接

PI系列VLA关键工作

TikTok GR系列工作

GR-1 teaser

UNLEASHING LARGE-SCALE VIDEO GENERATIVE PRE-TRAINING FOR VISUAL ROBOT MANIPULATION

arXiv 论文链接

字节跳动提出的基于大规模视频预训练模型

GR-2 teaser

GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

arXiv 论文链接

字节跳动提出的基于大规模视频预训练模型

GR-3 teaser

GR-3 Technical Report

arXiv 论文链接

字节跳动提出的基于大规模视频预训练模型

仿真平台和基准

RoboTwin teaser

RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins

arXiv 论文链接

最佳仿真平台。

RoboTwin2.0 teaser

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

arXiv 论文链接

最佳仿真平台升级版。

RoboCasa teaser

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

arXiv 论文链接

最佳仿真平台升级版。

RoboVerse teaser

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

arXiv 论文链接

仿真平台集成。

人形机器人运动/模仿学习

ASAP teaser

ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills

arXiv 论文链接

人形机器人对高敏捷人类行为的模仿学习。

TWIST Teaser

TWIST: Teleoperated Whole-Body Imitation System

arXiv 论文链接

人形机器人全身遥操作。