Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Dikai, Zhang, Tianwei, Yin, Jianxiong, See, Simon
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913731770843136
author Liu, Dikai
Zhang, Tianwei
Yin, Jianxiong
See, Simon
author_facet Liu, Dikai
Zhang, Tianwei
Yin, Jianxiong
See, Simon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03332
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion
Liu, Dikai
Zhang, Tianwei
Yin, Jianxiong
See, Simon
Robotics
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.
title Masked Sensory-Temporal Attention for Sensor Generalization in Quadruped Locomotion
topic Robotics
url https://arxiv.org/abs/2409.03332