Early Lane Change Prediction for Mixed Traffic with V2X Communication

Lane change prediction is essential for ensuring road safety and effective decision-making in autonomous vehicles (AVs). AVs will probably take several decades to penetrate new vehicle sales. As AVs and human-driven vehicles (HDVs) will coexist in traffic for the long term, AVs must understand the lane change intentions of surrounding HDVs. Lane changing is a critical manoeuvre that can cause a crash if it is performed late or if incorrect lane adjustments are made. Therefore, forecasting surrounding vehicles’ lane change intentions in advance is essential to ensure safe driving in mixed traffic environments having both AVs and HDVs. The unpredictability of human driving behavior presents challenges for timely and accurate lane change predictions, leading to the risk of collisions. This study proposes an architecture combining deep learning for high accuracy and an edge-driven approach for low latency. In this study, we introduce an artificial intelligencebased early lane change prediction scheme with a decentralized Vehicle-to-Everything (V2X) framework using microservices and edge computing. Our objective is to forecast lane changes 3 seconds in advance with high accuracy and low latency for improving real-time AV safety. Our initial system employs a Long Short-Term Memory (LSTM) model to predict HDV lane change events in an emulated highway scenario.