Multi-LED Classification as Pretext For Robot Heading Estimation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Carlotti, Nicholas, Nava, Mirko, Giusti, Alessandro
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913535381995520
author Carlotti, Nicholas
Nava, Mirko
Giusti, Alessandro
author_facet Carlotti, Nicholas
Nava, Mirko
Giusti, Alessandro
contents We propose a self-supervised approach for visual robot detection and heading estimation by learning to estimate the states (OFF or ON) of four independent robot-mounted LEDs. Experimental results show a median image-space position error of 14 px and relative heading MAE of 17 degrees, versus a supervised upperbound scoring 10 px and 8 degrees, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04536
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-LED Classification as Pretext For Robot Heading Estimation
Carlotti, Nicholas
Nava, Mirko
Giusti, Alessandro
Robotics
We propose a self-supervised approach for visual robot detection and heading estimation by learning to estimate the states (OFF or ON) of four independent robot-mounted LEDs. Experimental results show a median image-space position error of 14 px and relative heading MAE of 17 degrees, versus a supervised upperbound scoring 10 px and 8 degrees, respectively.
title Multi-LED Classification as Pretext For Robot Heading Estimation
topic Robotics
url https://arxiv.org/abs/2410.04536