Simulation and Deployment Tools

Abstract

This chapter surveys the simulation environments and deployment workflows used throughout the book. It begins by examining the role of simulation in the development and evaluation of learning-based control systems. The chapter then compares two primary implementation environments used in the projects presented in the book: MATLAB/Simulink and Python. Their respective strengths, workflows, and typical use cases are discussed to show how each environment supports modeling, controller development, and experimentation. The chapter also summarizes the supporting software stack used across the implementations, including key libraries and software tools. Finally, the chapter reviews hardware platforms used for development and deployment, with particular attention to embedded AI systems such as NVIDIA Jetson devices. Together, these topics provide a practical overview of the tools, software environments, and computing platforms used to build and test the intelligent control systems presented in the book. The chapter concludes with a Smart Parking AI project that demonstrates a hybrid perception-and-decision pipeline running on Jetson hardware, combining YOLOv8 object detection with a rule-based decision layer for parking lot monitoring.