Simulator for Teaching Robotics, ROS and Autonomous Driving in a Competitive Mindset

Simulator for Teaching Robotics, ROS and Autonomous Driving in a Competitive Mindset

Valter Costa (University of Porto, Portugal), Rosaldo J.F. Rossetti (University of Porto, Portugal) and Armando Sousa (University of Porto, Portugal)
Copyright: © 2019 |Pages: 15
DOI: 10.4018/978-1-5225-8060-7.ch033

Abstract

Interest in robotics field as a teaching tool to promote the STEM areas has grown in the past years. The search for solutions to promote robotics is a major challenge and the use of real robots always increases costs. An alternative is the use of a simulator. The construction of a simulator related with the Portuguese Autonomous Driving Competition using Gazebo as 3D simulator and ROS as a middleware connection to promote, attract, and enthusiasm university students to the mobile robotics challenges is presented. It is intended to take advantage of a competitive mindset to overcome some obstacles that appear to students when designing a real system. The proposed simulator focuses on the autonomous driving competition task, such as semaphore recognition, localization, and motion control. An evaluation of the simulator is also performed, leading to an absolute error of 5.11% and a relative error of 2.76% on best case scenarios relating to the odometry tests, an accuracy of 99.37% regarding to the semaphore recognition tests, and an average error of 1.8 pixels for the FOV tests performed.
Chapter Preview
Top

Literature Review

In order to properly prepare the contestants for a successful participation, some authors have presented strategies to teach and enthusiasm students into the robotics area using hardware based platforms. A major point to support this solution is the integration of Robotics classes’ exercises with real-world problems, with the output of the working project interacting directly with a real setup, thus motivating students (Cardeira & da Costa, 2005; Lenskiy, Junho, Dongyun, & Junsu, 2014). To reduce complexity, they can be based on off-the-shelf components. By skipping the complications of hardware development, which students in their first graduate years do not have, development in autonomous driving robotics is much more accessible (Cardeira & da Costa, 2005). They can also permit online development, making possible to create online classes, giving greater accessibility to the platform (Lenskiy et al., 2014). Usage of this manner of platform as a learning tool can prove to be costly and potentially difficult to distribute between potential students. Being a physical solution, it is prone to malfunctions, thus requiring maintenance and it is harder to share, unlike software. Unless it is a modular setup, the robots will be tailored to specific tasks, limiting their usage in different scenarios (Yusof & Hassan, 2012). Another disadvantage of using real platforms is the associated monetary cost, being sometimes inaccessible to fund. A solution to this problem is the creation of almost inexpensive platforms to introduce the same robotic tasks: a possible substitution is the use of 3D printed models to replace parts such as the wheels or the chassis (Gonçalves, Silva, Costa, & Sousa, 2015); the printed circuit board that hosts the electronic components can be designed to also serve as the robots’ structure (Valente, Salgado, & Boaventura-Cunha, 2014). Although these solutions are much less expensive, they always have an associated monetary cost. A workaround is the use of a simulator or a hybrid solution – simulator and a real platform – thus minimizing aforementioned costs.

Complete Chapter List

Search this Book:
Reset