Autonomous Vehicle in Industrial Logistics Application: Case Study

Autonomous Vehicle in Industrial Logistics Application: Case Study

Julius Fusic S. (Thiagarajar College of Engineering, India), Kanagaraj G. (Thiagarajar College of Engineering, India) and Hariharan K. (Thiagarajar College of Engineering, India)
DOI: 10.4018/978-1-5225-9078-1.ch008
OnDemand PDF Download:
No Current Special Offers


Rapid technological advances have revolutionized the industrial sector. In the global market, it is necessary to consider the new paradigm of Industry 4.0 that presents a lot of features in the industrial logistics application. It has been seen through literature that innovation management practices enable companies to compete within the autonomous and connected vehicle market and is considered as an emerging and competitive differentiator towards the growth of the product and that of meeting customer demands within the changing markets. The first case study explores the integration of GPS and GLONASS signals in AGV for localization and navigation of customer destination and materials in the indoor and outdoor environment. The second case study implemented in obstacle environment that recognized the obstacle in front of the robot and also identified the dimension of the obstacle size, length, width, circumference, height, and distance from a robot. The strength and disadvantages of the system are discussed in the logistical application and future outlines are provided.
Chapter Preview


Manufacturing companies are subject to permanently changing environments. The factories have to be continuously adapted to stay sustainable and competitive in the global market. Especially the smart driven logistic system facing huge problem relating to data processing and analyzing mechanism in navigation and control of the system. While the introduction of IIOT in logistic systems encounter solution for Automated Guided vehicle problems like planning path to reach destination, localize the material and localize the vehicle itself, navigate the customer location/ navigate the vehicle by the customer and sender itself, identifying the obstacle in the tracked path, recognize the obstacle and materials to pick and place operation with low budget by Mac et al., (2016). The laser and camera-based image processing-based vehicle positioning and obstacle avoid methodology were frequently followed (S. Lee & S. Lee 2013). For example, the PAN robot in advance where the laser mapping technology synchronized with stereo camera-based vision sensor to handle autonomous trouble-free loading and unloading in modern factory warehouses in European countries. Zhang, (2018) pointed that the sensor data must be handle carefully and stored in repository in secured manner, by deploying fog computing cyber security system in industry 4.0. Thus, the data driven model based on data processing and analyzing data in a more secure manner to avoid the error-free system. These vehicles encounter problems like unable to predict alternate path when it identifies obstacles, when it deviates from a predefined path, the navigation and localization of vehicle are complicated.

Key Terms in this Chapter

Mobile Kinematics: The process of understanding mobile motion based on operation of wheel constrains along with mechanical system behavior. The used mobile robots in case studies are two wheeled robot with generalized kinematics equation as, e_R=R(Ø)e_I, where e_R - Motion in local reference frame, R (Ø) – Orthogonal rotational matrix and e_I – Motion in the global reference frame.

AGV: Automated or autonomous guided vehicle is defined as vehicle or robot guided automatically in the pre-planned path without any human operation. These vehicles automatically navigate, plan obstacle free path to reach destination using artificial intelligence.

Morphology Technique: The morphology technique is conversion of images into small structural elements and classifies the structural element based on binary values positioned at all places in image to identify the expected image pixel by comparing with neighborhood pixel values. This technique is used to identify the obstacle in pre-defined path.

GNSS: The global navigation satellite system which receives position of the system using Receiver device to collect latitude and longitude data from satellites like GPS, GLONASS, Galileo, IRNSS, and so on. These data are used to predict automatic vehicle navigation, pedestrian navigation system, and tracking system in many applications.

Line of Sight: The line of sight (LoS) communication is defined as a type of propagation system where the transmitter and receiver which propagate and receive signal will be in view with each other without any obstacle block the signal. That improves the gain of signal whereas the NLoS (Non -line of sight) is a range in which physical interference across the signal propagate between transmitter and receiver.

Map-Based Approach: The navigation system of mobile robot in which the environment details are given in the form of graph and grid models. Using that models the system identify where the robot or AGV are located in the environment. In vision navigation early stages, the knowledge of environment is represent in 2D projection normally called occupancy map.

Complete Chapter List

Search this Book: