A Relative Positioning Development for an Autonomous Mobile Robot with a Linear Regression Technique

• Daniel Teso-Fz-Betoño ^[1] ; Ekaitz Zulueta ^[1] ; Ander Sánchez-Chica ^[1] ; Unai Fernandez-Gamiz ^[1] ; Irantzu Uriarte ^[1] ; Jose Manuel Lopez-Guede ^[1]
  1. [1] Universidad del País Vasco/Euskal Herriko Unibertsitatea

     Universidad del País Vasco/Euskal Herriko Unibertsitatea

     Leioa, España

     
• Localización: 15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020): Burgos, Spain ; September 2020 / coord. por Álvaro Herrero Cosío, Carlos Cambra Baseca, Daniel Urda Muñoz, Javier Sedano Franco, Héctor Quintián Pardo, Emilio Santiago Corchado Rodríguez, 2021, ISBN 978-3-030-57802-2, págs. 627-635
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Autonomous Mobile Robots (AMR) need a positioning function to move into unknown areas. These kinds of vehicles do not use a magnetic tape to guide into warehouses. Therefore, AMR use two different alternative techniques to solve the localization problem. First one is based on absolute positioning, and second one is established on relative localization. The absolute localization uses Simultaneous Localization and Mapping algorithms, in order to obtain a global position. However, the relative localization is based on odometry techniques.With the intention of developing a navigation system for an industrial mobile robot, which is being programmed in a structured text language, a relative localization is done utilizing LiDAR data acquisition. This novel concept analyzes two LiDAR datasets from different periods to calculate the AMRmovement, by implementing Point matching and Linear Regression (LR) techniques. To understand the differences between conventional Iterative Closest Point (ICP) and LR a comparison is performed.