国产欧美精品一区二区,中文字幕专区在线亚洲,国产精品美女网站在线观看,艾秋果冻传媒2021精品,在线免费一区二区,久久久久久青草大香综合精品,日韩美aaa特级毛片,欧美成人精品午夜免费影视

The accurate prediction of the future state of moving objects in the surrounding environment is an important influencing factor for autonomous vehicles to make accurate decisions. Vehicle is one of the most common and demanding moving objects. A depth prediction network based on an attention mechanism is proposed for the multi-modal input problem of vehicle trajectory prediction on the structural road. An interactive module is proposed to extract the interactive features of target vehicle, surrounding vehicles and lane information. Combined with the guidance of lane information to the vehicle movement, the target point prediction module is added to predict the possible target point of the target vehicle to increase the prediction accuracy. In the Argoverse public data set, the prediction network achieves the prediction accuracy of 1.45 m minimum average distance error and 3.21 m minimum final distance error in the 3-second prediction range, better than current mainstream methods.