VIRAL：大规模视觉仿真到现实用于双足机器人类地交互
VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation
AI总结：
VIRAL通过大规模仿真训练并零样本部署，实现双足机器人在现实中的自主移动- manipulation能力，无需现实微调。
摘要：
双足机器人在现实世界中的部署面临缺乏自主移动- manipulation技能的瓶颈。我们引入了VIRAL，一种视觉仿真到现实框架，该框架在仿真中完全学习双足机器人的移动- manipulation技能，并在零样本情况下部署到真实硬件。VIRAL采用教师-学生设计：一个特权强化学习教师，在完整状态上运行，利用delta动作空间和参考状态初始化学习长周期的移动- manipulation。然后通过大规模仿真和瓷砖渲染，将基于视觉的学生策略从教师中进行知识蒸馏。我们发现计算规模至关重要：将仿真扩展到数十块GPU（最高64块）使教师和学生训练变得可靠，而低计算量的环境往往失败。为了弥合仿真到现实的差距，VIRAL结合了大规模视觉领域随机化，涵盖光照、材料、相机参数、图像质量和传感器延迟，并与现实到仿真的灵活手和相机对齐。在Unitree G1双足机器人上部署后，基于RGB的策略可连续进行移动- manipulation多达54次循环，无需任何现实世界微调即可泛化到多样的空间和外观变化，并接近专家级遥控操作性能。广泛的消融实验解剖了使基于RGB的双足移动- manipulation在实践中可行的关键设计选择。
英文摘要：
A key barrier to the real-world deployment of humanoid robots is the lack of autonomous loco-manipulation skills. We introduce VIRAL, a visual sim-to-real framework that learns humanoid loco-manipulation entirely in simulation and deploys it zero-shot to real hardware. VIRAL follows a teacher-student design: a privileged RL teacher, operating on full state, learns long-horizon loco-manipulation using a delta action space and reference state initialization. A vision-based student policy is then distilled from the teacher via large-scale simulation with tiled rendering, trained with a mixture of online DAgger and behavior cloning. We find that compute scale is critical: scaling simulation to tens of GPUs (up to 64) makes both teacher and student training reliable, while low-compute regimes often fail. To bridge the sim-to-real gap, VIRAL combines large-scale visual domain randomization over lighting, materials, camera parameters, image quality, and sensor delays--with real-to-sim alignment of the dexterous hands and cameras. Deployed on a Unitree G1 humanoid, the resulting RGB-based policy performs continuous loco-manipulation for up to 54 cycles, generalizing to diverse spatial and appearance variations without any real-world fine-tuning, and approaching expert-level teleoperation performance. Extensive ablations dissect the key design choices required to make RGB-based humanoid loco-manipulation work in practice.
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。
