RoboTTT：机器人策略的上下文扩展
RoboTTT: Context Scaling for Robot Policies
- NVIDIA（英伟达公司）
- Stanford University（斯坦福大学）
- The University of Texas at Austin（德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究提出RoboTTT，将测试时训练集成到机器人基础模型，通过序列动作强制和截断反向传播扩展视觉运动上下文到8K时间步长，解锁新能力，提升多任务性能，证明上下文长度是机器人基础模型新扩展轴。
AI中文摘要：
近期的机器人基础模型在单步或短历史视觉运动上下文下运行。我们引入了测试时训练机器人策略（RoboTTT），这是一种机器人模型和训练方法，可将视觉运动上下文扩展到8K时间步长，比现有技术策略高出三个数量级，且不增加推理延迟。在此上下文长度下，解锁了新的机器人能力，如从人类视频演示中一次性上下文模仿、即时策略改进、对扰动的鲁棒性以及在多阶段、长视野任务上更强的性能。还首次观察到随着预训练上下文长度增加，闭环性能稳步提升。核心是将测试时训练集成到机器人基础模型中，通过序列动作强制和截断反向传播来扩展训练上下文长度。在具有挑战性的真实机器人操作任务中，RoboTTT比单步上下文基线的整体性能提高了87%，并完全完成了五分钟、十阶段的装配任务，而基线模型从未做到。用8K时间步长上下文训练的RoboTTT比用1K时间步长预训练的相同模型性能高出62%，表明上下文长度是机器人基础模型新的扩展轴。
英文摘要：
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference latency. At this context length, we unlock new robot capabilities: one-shot in-context imitation from human video demonstrations, on-the-fly policy improvement, robustness to perturbations, and stronger performance on multi-stage, long-horizon tasks. We also observe, for the first time, steady gains in closed-loop performance as pretraining context length scales. At its core, RoboTTT integrates Test-Time Training into robot foundation models such as Vision-Language-Action policies, yielding a sequence model whose recurrent state consists of fast weights, parameters updated by gradient descent during both training and inference, compressing histories into weight space and retrieving contextual information for long-context conditioning. To scale training context length, the recipe combines sequence action forcing with truncated backpropagation through time. On challenging real-robot manipulation tasks, RoboTTT improves overall performance by 87% over the single-step context baseline and fully completes a five-minute, ten-stage assembly task, which no baseline ever does. RoboTTT trained with 8K-timestep context outperforms the same model pretrained with 1K timesteps by 62%, suggesting context length as a new scaling axis for robot foundation models. Videos are available at https://research.nvidia.com/labs/gear/robottt/
