外观
论文arXiv 2609.234831 个月前
STRIDER：面向人形机器人的支持迈步的多步态分层3D移动操作框架
原文链接：STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots（arXiv 2609.23483 · 发布日期：2026-09-20）
STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots
STRIDER面向人形移动操作中足点调控与全身操作融合问题，以分层多步态与LD-PPO蒸馏方法在仿真和TianGong Omni真机验证。
核心要点
- 连续速度控制难精确调控单个落足，专用落足跟踪又难集成全身操作。
- 框架融合地形感知3D迈步逻辑、AMP自然行走和上身笛卡尔控制。
- LD-PPO结合在线强化学习、DAgger动作重构和教师条件潜变量对齐。
- 仿真与TianGong Omni真机显示，LD-PPO落足和姿态跟踪精度更高。
验证范围与局限：验证范围为仿真和TianGong Omni人形机器人真机上的多步态移动操作、落足与末端跟踪。
英文摘要 (Abstract)
Humanoid loco-manipulation faces two prominent limitations: controllers using continuous velocity commands cannot precisely regulate individual footholds, while specialized foothold-tracking modules are difficult to integrate with whole-body manipulation. Furthermore, standard action-based imitation distillation primarily transfers expert actions, without explicitly encouraging a shared representation of heterogeneous skills. This paper introduces STRIDER, a hierarchical multi-gait framework to bridge these gaps. The framework integrates terrain-aware 3D stepping logic, Adversarial Motion Priors (AMP)-based natural walking, and Cartesian upper-body control: its stepping expert selects feasible footholds in the stance-foot frame and generates clearance-aware swing trajectories. To fuse distinct walking and stepping experts into one executable student policy, we propose Latent Distillation Proximal Policy Optimization (LD-PPO), a distillation algorithm augmented with teacher-conditioned latent alignment. By jointly optimizing on-policy reinforcement learning, DAgger-based action reconstruction, and latent alignment, LD-PPO transfers expert actions while encouraging a shared skill representation across heterogeneous modes. Simulation and real-robot evaluations on the TianGong Omni humanoid show that LD-PPO outperforms vanilla distillation-PPO in foothold-tracking and posture-tracking accuracy. Deployed on hardware, STRIDER realizes multi-gait loco-manipulation with accurate foothold and end-effector tracking.
作者：Yuanzhuo Li, Wen Zhao, Zhe Yong, Xiang Meng, Gang Han, Hengle Ren, Xiaoyang Zheng, Zhen Wang, Yijie Guo
来源
本页事实对应的公开页面，以原文为准。