With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensory inputs will be 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 model with masking for quadruped locomotion. It employs direct sensor-level attention to enhance sensory-temporal understanding and handle different combinations of sensor data, serving as a foundation for incorporating unseen information. This model can effectively understand its states even with a large portion of missing information, and is flexible enough to be deployed on a physical system despite the long input sequence.

翻译：随着四足机器人研究日益受到关注，能够处理不同机器人模型与传感输入的泛化策略将具有重要价值。尽管已有多种方法被提出以应对不同的形态结构，但基于学习的策略如何管理多种本体感知信息的组合仍具挑战。本文提出掩码感知-时序注意力模型，这是一种基于Transformer架构、采用掩码机制的新型四足运动控制模型。该模型通过直接传感器级注意力机制增强感知-时序理解能力，处理不同传感器数据的组合，为融入未知信息提供基础框架。即使在大比例信息缺失的情况下，该模型仍能有效理解自身状态，且其长输入序列的特性不影响其在实体系统中的灵活部署。