本帖最后由 豆腐机器人 于 2026-2-26 16:05 编辑
一、遥操作与数据收集 (Teleoperation & Data Collection)
| TWIST Teleoperated Whole-Body Imitation System
| (CoRL 2025)
|✅ 开源`github.com/YanjieZe/TWIST` | 全身遥操作系统,实现全身协调控制 |
| TWIST2 Scalable, Portable, and Holistic Humanoid Data Collection System
| (Nov 2025)
| ✅ 开源`yanjieze.com/TWIST2` | 便携式无MoCap数据采集系统,15分钟收集100条演示 |
---
二、运动重定向 (Motion Retargeting)
| GMR General Motion Retargeting
| (Oct 2025)
| ✅ 开源`github.com/YanjieZe/GMR` | 通用运动重定向,支持16个人形机器人平台 |
| OmniRetarget Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation
| (Sep 2025)
| ✅ 开源 `github.com/amazon-far/holosoma` | 亚马逊发布,保持交互逻辑的重定向,宇树春晚蹬墙后空翻即用此工作流 |
---
三、运动跟踪与控制 (Motion Tracking & Control)
| DeepMimic Example-Guided Deep Reinforcement Learning
| 2018 (ACM TOG)
| ✅ 开源<br>(MimicKit) | 开创性工作,首次实现强化学习驱动的动画角色动作模仿 |
| AMP Adversarial Motion Priors
| 2021 (SIGGRAPH)
| ✅ 开源<br>(MimicKit) | 对抗运动先验,无需显式动作选择即可生成多样化行为 |
| BeyondMimic From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
| 2025 (Aug 2025)
| ✅ 开源`github.com/HybridRobotics/whole_body_tracking` | 宇树G1侧手翻,当前主流代码框架 |
| Robust and Generalized Humanoid Motion Tracking
| 2025-2026 |
| ❓代码未公开 | 鲁棒通用的人形机器人运动跟踪 |
---
四、交互技能学习 (Interaction Skills)
| HumanX Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
| 2025-2026
| ✅ 开源`github.com/humanx-robotics` | 宇树G1接抛篮球、三步上篮、踢足球、拳击格挡等 |
---
五、感知跑酷与特殊技能 (Perceptive Parkour & Special Skills)
| DribbleBot Dynamic Legged Manipulation in the Wild
| 2023 (ICRA 2023)
| ✅ 开源 `GitHub - Improbable-AI/dribblebot: Code release accompanying DribbleBot: Dynamic Legged Manipulation in the Wild` | MIT工作,四足机器人野外运球 |
| Robot Parkour Learning
| 2023 (CoRL 2023)
| ✅ 开源`GitHub - ZiwenZhuang/parkour: [CoRL 2023] Robot Parkour Learning` | 四足机器人跑酷,攀爬、跳跃、匍匐 |
| DrEureka Language Model Guided Sim-to-Real Transfer
| 2024 (RSS 2024)
| ✅ 开源 GitHub - eureka-research/DrEureka: Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024) | NVIDIA工作,机器狗瑜伽球上行走 |
| Hiking in the Wild A Scalable Perceptive Parkour Framework for Humanoids
| 2025
| ✅ 开源 GitHub - 项目-instinct/InstinctLab | 人形机器人野外感知跑酷框架 |
| Perceptive Humanoid Parkour (PHP) Chaining Dynamic Human Skills via Motion Matching
| 2026 (Feb 2026) | ❓代码未公开 Perceptive Humanoid Parkour | 运动匹配链接动态人形技能,宇树G1攀爬1.25m障碍 |
---
时间线汇总 (Timeline)
- 2018 ─── 深度模仿学习起步 (DeepMimic)
- │
- 2021 ─── 对抗运动先验 (AMP)
- │
- 2023 ─── 四足机器人野外技能突破 (DribbleBot + Parkour)
- │
- 2024 ─── LLM引导仿真到现实迁移 (DrEureka)
- │
- 2025 ─── 人形机器人爆发年:
- ├── 8月: BeyondMimic (宇树G1侧手翻)
- ├── 9月: OmniRetarget (宇树春晚技术栈核心)
- ├── 10月: GMR (通用重定向)
- └── 11月: TWIST系列 (全身遥操作与数据采集)
- │
- 2026 ─── 动态人形跑酷 (PHP, 代码未公开)
复制代码
关键结论
1. 开源情况:除 Hiking in the Wild 和 Robust and Generalized Humanoid Motion Tracking、PHP 外,其余项目均有开源实现
2. 宇树春晚技术栈:主要基于 OmniRetarget (重定向) + BeyondMimic (控制) + HumanX (交互)
3. 最新进展:TWIST2 (2025.11) 和 PHP (2026.02) 代表了当前人形机器人遥操作和跑酷的最新成果
|