This study proposes a 5G C-V2I (Cellular Vehicle-to-Infrastructure) enabled intelligent trajectory prediction and warning system, which can be implemented in a framework including RSUs (Road Side Units) with radar detection ability and 5G edge computing servers. This study exploits artificial intelligence to predict instant trajectories of vehicles at crossroads. The resulting augmented-awareness navigation information is then broadcasted to road users through 5G C-V2I with low latency. In practical applications, road users can obtain real-time dynamics of surrounding vehicles so that their level of safety can be effectively enhanced.

The proposed trajectory prediction system adopts mmWave radars as the detection devices, which is more reliable in harsh environments than using GPS and image-based systems. This study proposes a light-weight residual ST-LSTM (Spatial-Temporal Long-Short Term Memory) deep learning neural network to greatly enhance the model’s capability of extracting parameters of moving targets. This technique can achieve real-time trajectory prediction by using RSU radars. Through 5G C-V2I, the resulting prediction information is transmitted to road users via URLLC network protocols with a low latency.

The proposed intelligent trajectory prediction and warning system can provide more time margin for road users to conduct essential decision making and judgements. Road users can access this safety service through an easy-to-use APP operated on in-vehicle tablets or smart phones. The proposed system meets the specification of 5G C-V2I and can be integrated in existing traffic monitoring platforms for entering the intelligent transportation market. Road users can benefit from the system with augmented-awareness navigation and experience elevated level of safety. The proposed solution has great potential to open up a new 5G service market with a highly promising prospect.

歡迎有興趣者，與我們聯繫，謝謝!