Jonathan Thomas Platt
Published: 2022
Total Pages: 0
Get eBook
Several highly anticipated technologies including self-driving cars, delivery robots, and interplanetary rovers are predicated on continued advances in autonomous navigation research. One of the most significant challenges being faced in the development of autonomous navigation systems is that training and testing them is time consuming, costly, and potentially dangerous. A common way to address these concerns without significantly impeding development is to use a computer simulated environment. Currently, several dedicated simulation suites exist, but they are limited in terms of environment size, visual quality, and feature sets. As a result, many researchers have begun to consider repurposing game engines as simulators to take advantage of their greater flexibility, scalability, and graphical fidelity.This thesis investigates a robotics simulation suite based on the Unity3D game engine and ROS robotics middleware, collectively referred to as ROS-Unity3D, and compares it to the popular ROS-Gazebo robotics simulation suite. They are compared in terms of their architecture, environment creation process, resource usage, and accuracy while simulating an autonomous ground robot in real-time. Overall, ROS-Unity3D is found to be a viable alternative to ROS-Gazebo with support for many of the same file types and a powerful scripting interface for creating custom functionality like sensors. Test results indicate that ROS-Unity3D scales better to larger environments, has higher shadow quality, and is more capable of real-time LiDAR simulation than ROS-Gazebo. As for its advantages over ROS-Unity3D, ROS-Gazebo has a more streamlined interface between ROS and Gazebo, has more existing sensor plugins, and is more computer resource efficient for simulating small environments.