Extensive Traffic Light Prediction under Real-World Conditions

Innovative driving assisting systems, such as Green Light Optimal Speed Advisory (GLOSA), efficient start-stop control or traffic light warning systems can contribute to reducing CO
₂
emissions and traffic accidents. These systems necessitate reliable estimations on future traffic light signals on a large scale. However, due to dynamic adjustment of traffic lights' signal phasing and timing, the provision of such information on a certain quality level is a difficult task. This paper deals with the challenges of an extensive prediction of complete urban areas' traffic light networks. We introduce a real-time prediction algorithm and back-end implementation that is able to generate signaling predictions based on historical Signal Phase and Timing information (SPaT) for adaptive traffic lights of an entire urban area. Our approach is able to meet the requirement of dealing with high latency times for historical data and incomplete data sets. The proposed algorithm is able to provide predictions for 85% of the adaptive traffic lights with available historical SPaT in 65% of the time and thereby reaches an accuracy of 92% to 97%.