Do Earth-Trained Humanoid Controllers Walk on the Moon? Gravity, Terrain, and Soil Transfer
作者: Guillem Casadesus Vila, Sri Aditya Deevi, Grace X. Gao
分类: cs.RO
发布日期: 2026-10-21
备注: 11 pages, 4 figures, 5 tables. Supplementary material (13 pages) included as an ancillary file
💡 一句话要点
提出一种新方法以解决人形机器人在月球行走的适应性问题
🎯 匹配领域: 支柱一:机器人控制 (Robot Control)
关键词: 人形机器人 月球行走 运动控制 重力适应 地形适应 模拟训练 机器人技术 太空探索
📋 核心要点
- 现有的学习型运动控制方法主要在地球重力下进行,缺乏对月球环境的适应性研究,导致人形机器人在月球行走的能力不足。
- 本文提出了一种新的训练方法,通过在不同重力和地形条件下训练策略,探索人形机器人在月球环境中的适应性。
- 实验结果显示,经过粗糙训练的策略在月球和地球的生存率显著提高,验证了所提方法的有效性和适用性。
📝 摘要(中文)
月球的重力、地形和土壤特性与地球截然不同。现有的学习型运动控制主要集中在地球重力下的刚性地面和颗粒地形,缺乏对人形机器人在月球环境下的适应性研究。本文在模拟的Unitree G1机器人上训练了12种策略,探索了重力、地形几何和接触模型的变化,并进行了地球到月球的微调和重力随机化。实验结果表明,地球训练的策略在月球平坦刚性地面上的生存率为0.64至0.75,而月球训练的策略在地球上无法站立。通过粗糙训练,生存率在地球和月球上都有显著提升。本文的研究为未来人形机器人在月球的应用提供了重要的理论基础和实验数据。
🔬 方法详解
问题定义:本文旨在解决人形机器人在月球环境下的行走适应性问题,现有方法未能有效应对月球的低重力和复杂地形。
核心思路:通过在模拟环境中训练多种策略,结合重力、地形几何和接触模型的变化,探索地球到月球的适应性转移。
技术框架:研究采用了Unitree G1机器人进行模拟训练,训练过程中包括12种不同策略的生成,重力随机化和地球到月球的微调。实验分为在刚性地面和3D RFT条件下进行测试。
关键创新:本研究的创新在于首次系统性地探讨了人形机器人在月球环境下的运动控制,揭示了重力转移的非对称性及其对生存率的影响。
关键设计:训练过程中采用了多种接触模型和地形类型,设置了不同的重力条件,优化了策略的生存率,并在实验中对比了不同训练策略的效果。
🖼️ 关键图片
📊 实验亮点
实验结果显示,地球训练的策略在月球平坦刚性地面上的生存率为0.64至0.75,而经过粗糙训练的策略在地球和月球的生存率分别提升至0.98和0.99,显示出显著的适应性提升。
🎯 应用场景
该研究为未来人形机器人在月球及其他低重力环境中的应用提供了理论支持,具有重要的实际价值。其结果可为太空探索、月球基地建设以及其他行星探测任务中的机器人技术发展提供参考。
📄 摘要(原文)
The Moon changes gravity, terrain, and soil at once. Learned locomotion has studied reduced gravity on rigid ground and granular terrain mostly at Earth gravity, but not humanoids under both, generalist-controller transfer, or the Earth cost of lunar adaptation. On a simulated Unitree G1, we train 12 policies with one recipe, varying gravity, terrain geometry, and ground contact (rigid or three-dimensional resistive force theory, 3D RFT), and including Earth-to-Moon fine-tuning and gravity randomization. We test them at both gravities on rigid ground and 3D RFT, and at their training gravity on three held-out soil models. We also test the frozen SONIC, a released generalist humanoid controller, at both gravities on rigid ground only. Gravity transfer is asymmetric. Earth-trained policies keep 0.64 to 0.75 survival at the Moon on flat rigid ground, Moon-trained and fine-tuned policies cannot stand at Earth, and SONIC survives at most 0.10 at the Moon. Rough training lifts combined-tile survival from 0.53 to 0.98 at Earth and 0.80 to 0.99 at the Moon. In 3D RFT, soil training helps on Earth sand, on tiles and for rough-trained policies also on flat sand. On the stiffer lunar soil it helps only flat-trained Earth policies at Earth and changes the survival of Moon-trained policies by at most a few hundredths. In the sampled rollouts of the held-out soil models, Moon-trained policies keep most of their rigid-ground progress on lunar regolith at the low G1 foot pressure, with per-seed progress ratios of 0.84 to 1.39 apart from one seed with a short rigid reference. A gravity-randomized policy trained on rough 3D RFT terrain has a seed-mean survival of at least 0.84 at Earth and 0.96 at the Moon on every key test cell up to 20 degrees. Lunar results are simulation predictions conditional on the contact model and soil stiffness.