2023 ASEE Annual Conference & Exposition

There have been major advances in autonomous vehicles through recent years. Features such as adaptive cruise control, emergency braking, lane assistance, and automatic parking have become standard in most new vehicles. There exist cars nearing level 5 autonomy, where the vehicle can operate without a driver and under any condition. As self-driving technology cements itself in our society, this package turns a normally trivial task into a display of modern technology. Developing a car with these capabilities requires computer vision and a variety of sensors to recognize its surroundings and navigate obstacles.
Due to their size and scope, Radio Controlled (RC) cars are a great way for prospective engineers to learn real-world technical skills. The low cost and shorter turnaround time allows for rapid development and testing, which can effectively teach many of the same principles as real cars. Autonomous driving is the most ideal way to test a custom RC car’s mechanical integrity to avoid human driving bias. Current self-driving RC car modules require hours of setup configurations and course-specific training before driving autonomously. Even after training, most modules do not provide the capability to avoid obstacles or traverse non-standard terrain. An ideal self-driving module must be capable of being downloaded and installed onto an RC car regardless of dimensions. Since this project’s audience is typically mechanical engineering students with little computer science and electrical engineering experience, having controls and driving data be easily accessible in a website would prove to be extremely beneficial. Hence, we developed the Modular Package for Autonomous Driving (MPAD). This project will demonstrate how techniques in computer vision and sensors are used to create a truly modular package. MPAD allows Mechanical Engineering students to test their work in a complete system without requiring a coding or electrical design background.
MPAD began with an axiomatic design of the project, to lay out the steps for design and guarantee an efficient final product. The development boards used were the Raspberry Pi 4 8GB and Elegoo Mega 2560. The sensors are connected to the Elegoo, which then connects to the Raspberry Pi. The sensor package uses a Raspberry Pi camera for lane recognition and seven ultrasonic sensors for obstacle avoidance. Along with the ultrasonic sensors, the final sensor package includes an inertial measurement unit (IMU), two temperature sensors, a hall-effect sensor, and a battery sensing circuit. All the sensors went through rigorous accuracy testing. The package is specifically designed to be easily transferable from one RC car to another. The self-driving software uses computer vision to navigate a course without any prior training. The angles of the wheels are calculated using the coordinates of the pixels in the camera input along with the readings from the ultrasonic sensors. Testing revealed that autonomous driving was able to do U-turns as well as perform better at high speeds. While driving alone is visually interesting, engineers need something concrete, which is data. Data collected by sensors in the car can be seen on a web portal in real time. Through customizable sensor graphs and camera views, the car can be highly configured and tested. If the students choose not to touch the program, they can rest assured knowing the web controller will quickly and reliably connect them to their car across any number of devices.
MPAD was implemented in an introductory engineering design course at XYZ University. Eight teams of mechanical engineering students each received documentation in the form of two guides to create their own version of MPAD. While there were challenges and learnings, the integration was successful, and the students were able to fully utilize MPADs capabilities with their own RC car design. The paper will discuss the implementation, testing details, and future work for a self-driving modular package.