Skip to content

论文arXiv 2604.1934411 天前

稀疏门控MoE架构赋能四足机器人视觉敏捷运动控制 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Quadruped Agile Locomotion: Sparsely Gated Mixture of Experts with Visual Input(arXiv 2604.19344)

核心内容 ​

针对四足机器人敏捷运动控制中传统密集MLP网络容量受限问题,研究提出将LLM领域的稀疏门控混合专家(MoE)架构迁移至视觉导航任务。实验表明,在严格控制推理时激活参数量的前提下,MoE策略相比标准MLP训练奖励提升8%,且优于同等总参数量的MLP模型,证实了稀疏激活机制在机器人运动控制中的有效性。

该技术路线通过仅激活部分专家网络参数,在不增加实时推理算力的前提下显著扩展了策略网络容量,解决了视觉输入下高维状态空间与端侧算力约束的矛盾。研究已在Unitree Go2四足机器人上完成真机部署与验证,证明了从大语言模型借鉴稀疏化架构以增强具身智能体运动泛化能力的工程可行性。

关键看点 ​

  • 架构迁移:将稀疏门控MoE引入四足视觉运动控制,解决密集MLP在复杂地形下网络容量瓶颈
  • 性能增益:推理激活参数量对齐时MoE训练奖励较标准MLP提升8%,优于同总参数量密集模型
  • 真机验证:在Unitree Go2平台完成实机部署,验证稀疏架构在真实物理环境中的敏捷运动能力
  • 算力效率:利用稀疏激活机制扩展策略容量,保持低推理开销同时提升视觉运动策略上限

工程与产业观察 ​

该工作验证了LLM稀疏化架构向具身控制迁移的有效性,为端侧部署高容量视觉运动策略提供了新范式。对于算法工程师而言,MoE可在不升级边缘计算硬件的前提下突破MLP性能天花板;对产业界则意味着现有四足本体可通过纯软件架构升级获得更强非结构化地形适应能力,降低了对高算力芯片的刚性依赖。

英文摘要 (Abstract) ​

Agile locomotion is important for quadruped robots in the real world. Recent approaches have demonstrated impressive capabilities including dynamic climbing and jumping but typically rely on sequential multilayer perceptron (MLP) architectures with densely activated layers. In contrast, sparsely gated mixture-of-experts (MoE) architectures have become popular in the large language model (LLM) domain as a tool to improving scalability and performance by activating only a subset of parameters at inference. In this work, we investigate the application of such architectures to vision-based robotic locomotion. We compare policies based on standard MLPs and MoE architectures under a controlled setting where the number of active parameters at inference time is matched. Experimental results show an 8% increase in reward during training comparing the MoE to a standard MLP and even show benefits comparing to MLPs with equivalent total parameters. Experimental results on a real Unitree Go2 quadruped robot demonstrate performance in the real world. These results highlight that sparsely gated MoE architectures may pose advantages in tasks where network capacity is important and that borrowing techniques from the fast-moving LLM space and applying them to locomotion is a promising direction.

作者:Michael Ziegltrum, Jianhao Jiao, Tianhu Peng, Chengxu Zhou, Dimitrios Kanoulas

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2604.19344:Quadruped Agile Locomotion: Sparsely Gated Mixture of Experts with Visual Input ↗访问 2026-11-11