arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.03332cs.RO
收藏

四足运动传感器泛化的掩蔽感官-时间注意力

Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion

NVIDIA AI Technology Centre (NVAITC)(英伟达人工智能技术中心(NVAITC));College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Coventry University(考文垂大学)

Dikai Liu, Tianwei Zhang, Jianxiong Yin, Simon See

AI总结:

本文提出掩蔽感官-时间注意力(MSTA),通过传感器级注意力与掩蔽机制增强四足机器人对不同本体感觉信息组合的泛化能力,并可在长输入序列下部署于物理系统。

摘要:

随着对四足机器人的关注日益增加,一种能够处理不同机器人模型和传感器输入的通用策略变得极具价值。尽管已有多种方法用于应对不同的形态结构,但对于基于学习的策略而言,管理各种本体感觉信息的组合仍然是一个挑战。本文提出了掩蔽感官-时间注意力(MSTA),这是一种新颖的基于Transformer并带有掩蔽机制的四足运动方法。它采用直接的传感器级注意力来增强感官-时间理解,并处理不同的传感器数据组合,为纳入未见信息奠定基础。即使缺失大量信息,MSTA也能有效理解自身状态,并且尽管输入序列较长,仍具有足够的灵活性以部署在物理系统上。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑