提出MSTA机制，让四足机器人在传感器缺失时仍能稳定行走
Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion
- 用掩码注意力直接处理传感器与时间信息
- 即使缺失大量传感器数据也能准确感知状态
- 适合部署在真实机器人上，支持多种传感器组合
随着四足机器人研究的深入，能够适应不同机器人型号和传感器输入的通用策略变得尤为重要。尽管已有方法解决形态差异问题，但基于学习的策略在处理不同本体感受信息组合时仍面临挑战。本文提出基于Transformer的掩码感官-时间注意力（MSTA）机制，通过直接在传感器层面施加注意力，增强对感官-时间信息的理解，并可作为集成未知信息的基础。MSTA在大量传感器数据缺失的情况下仍能有效理解自身状态，且具备足够灵活性，可在物理系统上部署，即使面对长输入序列也表现良好。
原文摘要 · Abstract (English)
With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensor inputs becomes highly beneficial. Although several methods have been proposed to address different morphologies, it remains a challenge for learning-based policies to manage various combinations of proprioceptive information. This paper presents Masked Sensory-Temporal Attention (MSTA), a novel transformer-based mechanism with masking for quadruped locomotion. It employs direct sensor-level attention to enhance the sensory-temporal understanding and handle different combinations of sensor data, serving as a foundation for incorporating unseen information. MSTA can effectively understand its states even with a large portion of missing information, and is flexible enough to be deployed on physical systems despite the long input sequence.
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。