一个能自适应控制多种机器人的通用运动模型，无需了解具体结构。
LocoFormer: Generalist Locomotion via Long-context Adaptation
- 用大规模强化学习训练，通过程序化生成机器人和极端随机化提升泛化能力。
- 扩展上下文长度至跨回合，实现测试时形态与动态变化的自适应调整。
- 可在摔倒后跨回合学习优化，适合需要通用性的机器人研发人员。
现代运动控制器需为特定机器人手动调参。我们提出 LocoFormer，一种通用的全形态运动模型，可控制此前未见的腿式与轮式机器人，甚至无需精确掌握其运动学信息。LocoFormer 能在测试时适应形态与动力学的变化。研究发现两个关键设计促成适应：首先，在大量程序生成的机器人上进行大规模强化学习，并采用激进的领域随机化；其次，与以往仅依赖短上下文的策略不同，将上下文扩展至跨越回合边界。我们使用同一模型部署于多种机器人，即使面对重量变化和电机故障等大扰动，仍表现出鲁棒控制。在极端情况下，出现跨回合的涌现适应——早期回合中的跌倒促使模型在后续回合中改进控制策略。我们认为这一简单但通用的训练范式，未来可用于训练其他机器人技能的基础模型。视频见 generalist-locomotion.github.io。
原文摘要 · Abstract (English)
Modern locomotion controllers are manually tuned for specific embodiments. We present LocoFormer, a generalist omni-bodied locomotion model that can control previously unseen legged and wheeled robots, even without precise knowledge of their kinematics. LocoFormer is able to adapt to changes in morphology and dynamics at test time. We find that two key choices enable adaptation. First, we train massive scale RL on procedurally generated robots with aggressive domain randomization. Second, in contrast to previous policies that are myopic with short context lengths, we extend context by orders of magnitude to span episode boundaries. We deploy the same LocoFormer to varied robots and show robust control even with large disturbances such as weight change and motor failures. In extreme scenarios, we see emergent adaptation across episodes, LocoFormer learns from falls in early episodes to improve control strategies in later ones. We believe that this simple, yet general recipe can be used to train foundation models for other robotic skills in the future. Videos at generalist-locomotion.github.io.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。