GigaBrain-0.5M*: 基于世界模型强化学习的VLA
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
AI总结：
GigaBrain-0.5M*通过基于世界模型的强化学习提升VLA模型的跨任务适应能力，实现复杂操作任务的可靠执行。
摘要：
直接从当前观察预测多步动作块的视觉-语言-动作（VLA）模型面临固有的限制，因为场景理解受限且未来预测能力较弱。相比之下，基于网络级视频语料预训练的视频世界模型具有强大的时空推理能力和准确的未来预测能力，使其成为增强VLA学习的自然基础。因此，我们提出了GigaBrain-0.5M*，一种通过基于世界模型的强化学习训练的VLA模型。该模型基于GigaBrain-0.5，其在超过10000小时的机器人操作数据上进行预训练，其中间版本目前在国际RoboChallenge基准测试中排名第一。GigaBrain-0.5M*进一步通过RAMP（基于世界模型的强化学习策略）整合世界模型强化学习，以实现稳健的跨任务适应。实证结果表明，RAMP在挑战性任务如Laundry Folding、Box Packing和Espresso Preparation上相比RECAP基线实现了显著的性能提升，大约提高了30%。关键的是，GigaBrain-0.5M*表现出可靠的长周期执行能力，能够一致地完成复杂操作任务，且在我们的项目页面上通过现实世界部署视频验证其可靠性。
英文摘要：
Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and weak future anticipation capabilities. In contrast, video world models pre-trained on web-scale video corpora exhibit robust spatiotemporal reasoning and accurate future prediction, making them a natural foundation for enhancing VLA learning. Therefore, we propose \textit{GigaBrain-0.5M*}, a VLA model trained via world model-based reinforcement learning. Built upon \textit{GigaBrain-0.5}, which is pre-trained on over 10,000 hours of robotic manipulation data, whose intermediate version currently ranks first on the international RoboChallenge benchmark. \textit{GigaBrain-0.5M*} further integrates world model-based reinforcement learning via \textit{RAMP} (Reinforcement leArning via world Model-conditioned Policy) to enable robust cross-task adaptation. Empirical results demonstrate that \textit{RAMP} achieves substantial performance gains over the RECAP baseline, yielding improvements of approximately 30\% on challenging tasks including \texttt{Laundry Folding}, \texttt{Box Packing}, and \texttt{Espresso Preparation}. Critically, \textit{GigaBrain-0.5M$^*$} exhibits reliable long-horizon execution, consistently accomplishing complex manipulation tasks without failure as validated by real-world deployment videos on our \href{https://gigabrain05m.github.io}{project page}.
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。
