Recommendation of Adaptive Safe Speed Limit for different driver Profiles using Deep Learning

Personalization and driver profiling have emerged as popular topics within the Advanced Driver Assistance Systems domain. Several features, like seat position adjustment and route selection deliver a customized experience for everyone. The systems often profile the driver and their preferences using Machine Learning algorithms to anticipate the needs of the driver. Within this field, personalization of speed limits is not explored to the fullest. Currently, speed limits are the same for all drivers, irrespective of their driving style. Even when the speed limits are designed to address adverse weather conditions, they do not consider the driver’s capabilities. Thus, we propose a novel idea to recommend a safe speed limit based on the driving style and the surrounding environmental conditions. The architecture consists of Long Short-Term Memory based neural networks that capture the driver’s traits based on risks of the environment. The system identifies if a driver is uncomfortable in the current road segment using vehicle data like vehicle speed, acceleration, steering. We use map data to fetch the speed limits and online weather API to get the weather information of the route. The front camera is used to classify the traffic density of the scene as either No Traffic, Medium Traffic or Heavy Traffic using Convolutional Neural Networks. These are used to derive the risk in the environment, which is classified into Low, Medium, and High Risk. The driver is evaluated based on the risk factor and a speed limit lower than the standard applicable value from traffic signs and/ or map data is recommended. The system derives a reduced speed limit, considering traffic signs, average speed in the road section for the closest matching weather and lighting conditions, and driver profile. Our system presents a distinct advantage by personalizing the speed limit based on the driver’s capability in a specific environment to ensure a safe and comfortable ride.