GRoQ-LoCO：基于离线数据集的通用且与机器人无关的四足运动控制
GRoQ-LoCO: Generalist and Robot-agnostic Quadruped Locomotion Control using Offline Datasets
AI总结：
提出GRoQ-LoCO，一个基于注意力且与机器人无关的框架，利用离线数据集在多个四足机器人上训练通用运动策略，实现零样本跨机器人迁移，并已在Unitree Go1和Stoch 5上验证。
摘要：
近期在大规模离线训练方面的进展展示了通用策略学习在复杂机器人任务中的潜力。然而，由于连续动力学以及跨多样地形和机器人形态的实时适应需求，将这些原则应用于腿式运动仍面临挑战。在本工作中，我们提出了GRoQ-LoCO，一个可扩展的、基于注意力的框架，仅依赖离线数据集，即可在多个四足机器人和地形上学习单一的通用运动策略。我们的方法利用从多个四足机器人收集的两种不同运动行为的专家演示——楼梯穿越（非周期步态）和平面地形穿越（周期步态）——来训练一个能够实现行为融合的通用模型。关键在于，我们的框架仅使用来自所有机器人的本体感觉数据，不包含任何特定于机器人的编码。该策略可直接部署在Intel i7 NUC上，无需测试时优化即可产生低延迟控制输出。我们的大量实验证明了在高度多样的四足机器人和地形上的零样本迁移，包括在Unitree Go1（一款商用12kg机器人）上的硬件部署。值得注意的是，我们评估了具有挑战性的跨机器人训练设置，其中不同的运动技能在机器人间不均匀分布，但在测试时观察到平面行走和楼梯穿越行为均成功迁移到所有机器人。我们还展示了在Stoch 5（一款70kg四足机器人）上无需微调即可在平面和户外地形上初步行走。这些结果证明了离线、数据驱动的学习在多样化四足形态和行为中泛化运动的潜力。
英文摘要：
Recent advancements in large-scale offline training have demonstrated the potential of generalist policy learning for complex robotic tasks. However, applying these principles to legged locomotion remains a challenge due to continuous dynamics and the need for real-time adaptation across diverse terrains and robot morphologies. In this work, we propose GRoQ-LoCO, a scalable, attention-based framework that learns a single generalist locomotion policy across multiple quadruped robots and terrains, relying solely on offline datasets. Our approach leverages expert demonstrations from two distinct locomotion behaviors - stair traversal (non-periodic gaits) and flat terrain traversal (periodic gaits) - collected across multiple quadruped robots, to train a generalist model that enables behavior fusion. Crucially, our framework operates solely on proprioceptive data from all robots without incorporating any robot-specific encodings. The policy is directly deployable on an Intel i7 nuc, producing low-latency control outputs without any test-time optimization. Our extensive experiments demonstrate zero-shot transfer across highly diverse quadruped robots and terrains, including hardware deployment on the Unitree Go1, a commercially available 12kg robot. Notably, we evaluate challenging cross-robot training setups where different locomotion skills are unevenly distributed across robots, yet observe successful transfer of both flat walking and stair traversal behaviors to all robots at test time. We also show preliminary walking on Stoch 5, a 70kg quadruped, on flat and outdoor terrains without requiring any fine tuning. These results demonstrate the potential of offline, data-driven learning to generalize locomotion across diverse quadruped morphologies and behaviors.
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。
