Development of Deep Learning Autonomous Car Using Raspberry Pi


  • Koon Ling Lee University Tun Hussein Onn
  • Hong Yin Lam University Tun Hussein Onn Malaysia


Autonomous vehicle, Autonomous car, Numpy, Machines Learning, image classified


An autonomous vehicle is a vehicle that senses its environment and operates without human intervention. The accident cases in Malaysia are grow rapidly every years. According to police statistics, there have the fatal accident cases happened in 2020 compare to 197 cases in 2019. This problem can be solved by an autonomous car, where such car technology can send us from place to place to increase with certain level of safety on the traffic. An autonomous car involves the extraction of surrounding information whereby such information is analysed by using the neural network. With a good environment situation, the collected information can be easily changed to Numpy array to allow the model to easily train the data. Machines learning algorithm requires the record the database of the user control for decision making and prediction. A major concern of such a driving method is to avoid the accident, which system can calculate the situation of the road and made the right decision to avoid the accident on the road. This work focus on the implementation of practical autonomous car based on few aspects such as the distance between obstacle and the view by the raspberry pi and also the image classified, which the image classifier is used to detect the sign board on the road. This project consists two main section, namely the auto mode and the manual mode respectively. In manual mode, the autonomous car is control by the user to collected the data, all the data will used in the auto mode. This work is demo on all kind of real-world road situation. Thus, using this prototype, it can contribute to the society for reduce the accident on the road.




How to Cite

Lee, K. L., & Lam, H. Y. . (2021). Development of Deep Learning Autonomous Car Using Raspberry Pi. Progress in Engineering Application and Technology, 2(1), 534–548. Retrieved from