<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In this paper a fast method based on laser triangulation for the estimation of the pose of a mobile robot is presented. The system is made of a camera and a laser source, placed on the front side of a robot, the Smoov ASRV, which is an autonomous vehicle able to carry, store and retrieve pallets in a smart warehouse constituted by metallic shelves. Therefore, the movements of the robot are constrained into allowed paths made of rails, arranged with several apertures that allow the robot change of direction. The processing of the acquired images is directly done on board by means of a low-cost single-board computer, namely the Raspberry Pi. This last is able to extract the information about the distance and the heading of the robot with respect to the rail boundary by analyzing the laser line lying in the camera plane; then, the extracted information expressed in the 3D reference system are sent via User Datagram Protocol to the control system of the vehicle. Results show how the information given by the proposed vision system are provided in a more efficient way with respect to the inductive sensors and the classic odometry, which fail when the robot crosses the structural rail apertures or its wheels suffer from unavoidable slippage.</p>
</abstract>

In this paper a fast method based on laser triangulation for the estimation of the pose of a mobile robot is presented. The system is made of a camera and a laser source, placed on the front side of a robot, the Smoov ASRV, which is an autonomous vehicle able to carry, store and retrieve pallets in a smart warehouse constituted by metallic shelves. Therefore, the movements of the robot are constrained into allowed paths made of rails, arranged with several apertures that allow the robot change of direction. The processing of the acquired images is directly done on board by means of a low-cost single-board computer, namely the Raspberry Pi. This last is able to extract the information about the distance and the heading of the robot with respect to the rail boundary by analyzing the laser line lying in the camera plane; then, the extracted information expressed in the 3D reference system are sent via User Datagram Protocol to the control system of the vehicle. Results show how the information given by the proposed vision system are provided in a more efficient way with respect to the inductive sensors and the classic odometry, which fail when the robot crosses the structural rail apertures or its wheels suffer from unavoidable slippage.

Laser Profilometry Aiding Smart Vehicle Control

International Journal on Smart Sensing and Intelligent Systems

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Laser Profilometry Aiding Smart Vehicle Control"}

In this paper a fast method based on laser triangulation for the estimation of the pose of a mobile robot is presented. The system is made of a camera and a...

Laser Profilometry Aiding Smart Vehicle Control

Pubblicato online: 15 feb 2020

Pagine: 1 - 6

DOI: https://doi.org/10.21307/ijssis-2019-055

Parole chiave
Computer Vision, Visual Odometry, Laser Profilometry, Smart Warehouse, Indoor Robot Navigation, Automated Storage Retrieval Vehicle

© 2019 Cosimo Patruno et al., published by Sciendo.

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Laser Profilometry Aiding Smart Vehicle Control

Pubblicato online: 15 feb 2020

Pagine: 1 - 6

DOI: https://doi.org/10.21307/ijssis-2019-055

Parole chiaveComputer Vision, Visual Odometry, Laser Profilometry, Smart Warehouse, Indoor Robot Navigation, Automated Storage Retrieval Vehicle

© 2019 Cosimo Patruno et al., published by Sciendo.

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Parole chiave
Computer Vision, Visual Odometry, Laser Profilometry, Smart Warehouse, Indoor Robot Navigation, Automated Storage Retrieval Vehicle