H-Zero让机器人在不同体型间快速迁移，少样本训练即可稳定行走。
H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer
- 在多种人形机器人上预训练通用运动策略
- 新机器人无需重训，能保持81%的完整行走时长
- 仅需30分钟微调，即可适配未知人形或双足机器人
人形机器人快速发展，但其控制器通常针对特定设计定制，需大量调参。为此，我们提出H-Zero跨人形运动预训练方案，通过有限数量的人形机器人预训练，学习可泛化的人形基础策略。实验证明，该策略可在未见机器人上实现零样本与少样本迁移，模拟环境中对未知人形机器人保持最高81%的完整运行时长；仅用30分钟微调，即可成功迁移到未见过的人形机器人和直立四足机器人。
原文摘要 · Abstract (English)
The rapid advancement of humanoid robotics has intensified the need for robust and adaptable controllers to enable stable and efficient locomotion across diverse platforms. However, developing such controllers remains a significant challenge because existing solutions are tailored to specific robot designs, requiring extensive tuning of reward functions, physical parameters, and training hyperparameters for each embodiment. To address this challenge, we introduce H-Zero, a cross-humanoid locomotion pretraining pipeline that learns a generalizable humanoid base policy. We show that pretraining on a limited set of embodiments enables zero-shot and few-shot transfer to novel humanoid robots with minimal fine-tuning. Evaluations show that the pretrained policy maintains up to 81% of the full episode duration on unseen robots in simulation while enabling few-shot transfer to unseen humanoids and upright quadrupeds within 30 minutes of fine-tuning.
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。