With the exponential increase in the number of vehicles and the slow pace of road infrastructure development, ensuring safety and maintaining speed while driving have become critical priorities in today's scenario. Stand-alone Automated vehicles, despite being cloud-connected facilities, seem not to have achieved exceptional safety and speed in the wake of traffic congestion. The situations like accidents, traffic congestion, etc., are waiting for further improvements. In this work, we propose to collect real-time data pertaining to the status of driving from predefined, authenticated vehicles. Appropriate control signals will be generated after processing at the cloud. Depending on the current status of many vehicles, the generated control signals will be sent back to all other authenticated vehicles for better maneuvering and decision-making. Meanwhile, each of the vehicles is also made capable of publishing the status of the road to every other vehicle in its range. Thus, helping the vehicle owners to make smarter and faster decisions, and thereby easing traffic. The On-Board Unit is developed with Seeed Studio XIAO ESP32C3, along with sensors to extract eight features from every vehicle. Wi-Fi and Bluetooth capabilities of microcontrollers are exploited for V2X and V2V communication. Machine Learning algorithms are used to train the models to categorize the road conditions precisely. It was observed that among Logistic regression, Naïve Bayes, KNN, SVM, and DT classification algorithms, DT, SVM, and NB are more suitable for this application, with a Classification accuracy of 90%, while others are at 88%. The accuracy of the classification of data collected from a low-cost, low-weight module is very promising compared to previous works. An added advantage is that the said module can be used by pedestrians and Segways.