Model-Based Systems Engineering to Design An Onboard Surround Vision System for Cooperative Automated Vehicles

• Published in: 2021 2nd International Informatics and Software Engineering Conference (IISEC) pp. 1 - 6
• Main Authors: Kemsaram, Narsimlu, Das, Anweshan, Dubbelman, Gijs
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.12.2021
• Subjects: Codes; Computational modeling; Cooperative automated vehicle; deep neural networks; Design methodology; Machine vision; model-based systems engineering; Navigation; Software algorithms; Software design; surround vision system; system modeling language; unified modeling language
• DOI: 10.1109/IISEC54230.2021.9672396

Cooperative automated vehicles have various electronic control units with multiple sensors running complex software algorithms to perceive and navigate their environment. Hence, there is a need to use advanced software engineering design methodology to reduce the software complexity and increase modularity. In this paper, we applied the SysCARS model-based systems engineering methodology to design an onboard surround vision system with a SysML modeling language using the IBM Rational Rhapsody modeling tool. The modeling methodology is described through various phases and steps with a modeling language to overcome the challenges. The modeling tool takes the information from the design model of the system and generates a skeletal code. The algorithm is written for each generated skeletal code, compiled with a C++ compiler on the host Desktop PC (Ubuntu 16.04 LTS), and deployed on the target Nvidia Drive PX2 embedded hardware platform. The designed solution fulfills the requirements of the onboard surround vision system.