Study on localization for rescue robots based on NDT scan matching

Study on localization for rescue robots based on NDT scan matching

This paper studied the localization problem for a rescue robot based on laser scan matching and extended Kalman filtering (EKF). Scan matching method based on normal distribution transform (NDT) can avoid hard feature extraction problem by estimation of the probability distribution of laser scan dat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jinliang Li, Jihua Bao, Yan Yu
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Feature extraction
Gaussian distribution
Kinematics
Laser modes
Laser theory
Navigation
Normal distribution transform
Probability distribution
Rescue robots
Robot localization
Robot sensing systems
Robotics and automation
Scan matching
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper studied the localization problem for a rescue robot based on laser scan matching and extended Kalman filtering (EKF). Scan matching method based on normal distribution transform (NDT) can avoid hard feature extraction problem by estimation of the probability distribution of laser scan data and localization can be achieved using correlation of the NDT. Based on NDT scan matching, the NDT-EKF algorithm has been proposed, which realizes fast and precise localization in rescue environment by fusing odometery data and scan matching together. The NDT-EKF algorithm has been extensively tested and experimental results show its effectiveness and robustness.
DOI:10.1109/ICINFA.2010.5512205