Historical Memory-Based Database Management System for Effective ADAS Configuration in Autonomous and Connected Vehicles

The ability to store data is crucial for an autonomous vehicle system. Memorizing traffic signs, including their locations, can be easier than trying to read and understand them on the fly. Using the vehicle's location and other vehicle data, decisions can be made faster when using existing memory data. This study outlines a technique that utilizes an environmental structure database as a tool for decision-making in diverse vehicle scenarios. By collectively learning and storing vehicle location, historical data, and past actions, this paper results in a way to predict the environmental structure in advance and use the necessary control signals to optimize vehicle operation. In a connected vehicle system, there can be many reasons and factors to be considered in various events such as vehicle speed, parking location, speed changes, speed bumps, braking, etc. These are stored in a separate database, and the accuracy of the results is increased by comparing the actual data at that time with the information in that database to draw specific conclusions. The following parameters such as safety, adaptability, scalability, cybersecurity, user experience, maintenance and energy optimization are to be reviewed in this article for finding out the implementation challenges and software configuration for effective ADAS functions.