EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Odometric Model Performance Based on LSTM Networks

Bibiana Fariña iD, Daniel Acosta, Jonay Toledo, Leopoldo Acosta iD

Sensors · 2023

DOI: 10.3390/s23020961 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Bibiana Fariña und 3 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and System Department, Universidad de La Laguna, 38200 San Cristobal de La Laguna, Spain. Hauptthemen laut MEDLINE: Algorithms, Wheelchairs. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a localization system for an autonomous wheelchair that includes several sensors, such as odometers, LIDARs, and an IMU. It focuses on improving the odometric localization accuracy using an LSTM neural network. Improved odometry will improve the result of the localization algorithm, obtaining a more accurate pose. The localization system is composed by a neural network designed to estimate the current pose using the odometric encoder information as input. The training is carried out by analyzing multiple random paths and defining the velodyne sensor data as training ground truth. During wheelchair navigation, the localization system retrains the network in real time to adjust any change or systematic error that occurs with respect to the initial conditions. Furthermore, another network manages to avoid certain random errors by using the relationship between the power consumed by the motors and the actual wheel speeds. The experimental results show several examples that demonstrate the ability to self-correct against variations over time, and to detect non-systematic errors in different situations using this relation. The final robot localization is improved with the designed odometric model compared to the classic robot localization based on sensor fusion using a static covariance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsWheelchairsNeural Networks, Computer

Stichwörter der Autor:innen

long short-term memorymobile robotodometryself-localizationsensor fusion

Autor:innen und Institutionen

  • Computer Science and System Department, Universidad de La Laguna, 38200 San Cristobal de La Laguna, Spain.

ORCID-Profile: Bibiana Fariña, Leopoldo Acosta

Zitieren

APA

Fariña, B., Acosta, D., Toledo, J., & Acosta, L. (2023). Improving Odometric Model Performance Based on LSTM Networks. Sensors. https://doi.org/10.3390/s23020961

Vancouver

Fariña B, Acosta D, Toledo J, Acosta L. Improving Odometric Model Performance Based on LSTM Networks. Sensors. 2023. doi:10.3390/s23020961

BibTeX
@article{Faria2023,
  author = {Fariña, Bibiana and Acosta, Daniel and Toledo, Jonay and Acosta, Leopoldo},
  title = {Improving Odometric Model Performance Based on LSTM Networks},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23020961}
}
Kostenlos starten →