GR-2：一种面向机器人操作的、具备网络规模知识的生成式视频-语言-动作模型
GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
AI总结：
该研究提出通用机器人操作智能体GR-2，经3800万视频、500亿token预训练及机器人轨迹微调，在100余任务上平均成功率97.7%，对新场景泛化性优异且性能随模型规模提升。
摘要：
我们提出了GR-2，这是一款性能领先的通用智能体，可实现多功能、具备泛化性的机器人操作任务。GR-2首先在海量互联网视频上进行预训练，以捕捉世界的动态规律。这一涉及3800万个视频片段、超500亿token的大规模预训练，让GR-2在后续的策略学习阶段，能够在各类机器人任务与环境中实现泛化。之后，我们利用机器人轨迹对GR-2进行微调，使其同时适配视频生成与动作预测任务。该模型展现出出色的多任务学习能力，在100余项任务上的平均成功率达97.7%。此外，GR-2在全新的、未见过的场景中也表现出优异的泛化性，包括全新背景、环境、物体与任务。值得注意的是，GR-2的性能随模型规模有效提升，凸显了其持续发展与应用的潜力。项目页面：https://gr2-manipulation.github.io
英文摘要：
We present GR-2, a state-of-the-art generalist robot agent for versatile and generalizable robot manipulation. GR-2 is first pre-trained on a vast number of Internet videos to capture the dynamics of the world. This large-scale pre-training, involving 38 million video clips and over 50 billion tokens, equips GR-2 with the ability to generalize across a wide range of robotic tasks and environments during subsequent policy learning. Following this, GR-2 is fine-tuned for both video generation and action prediction using robot trajectories. It exhibits impressive multi-task learning capabilities, achieving an average success rate of 97.7% across more than 100 tasks. Moreover, GR-2 demonstrates exceptional generalization to new, previously unseen scenarios, including novel backgrounds, environments, objects, and tasks. Notably, GR-2 scales effectively with model size, underscoring its potential for continued growth and application. Project page: \url{https://gr2-manipulation.github.io}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
