弹道
判别式
计算机科学
运动学
人工智能
可靠性(半导体)
人工神经网络
一致性(知识库)
图形
机器学习
车辆动力学
保险丝(电气)
深度学习
解码方法
卡尔曼滤波器
路径(计算)
数据建模
编码(内存)
运动规划
生成模型
隐马尔可夫模型
数据挖掘
智能交通系统
作者
Zhiwu Huang,Yicong He,Guoyu Gu,Yongjie Liu,Zhuozhuo Zhang,Xiaoyong Zhang
标识
DOI:10.1109/tits.2026.3661758
摘要
Accurate prediction of vehicle trajectories in complex traffic environments is essential for path planning and safety decisions in autonomous driving systems. However, purely data-driven models lack physical constraints, making it challenging to ensure reliability and consistency in dynamic traffic scenarios, while physics models face challenges in maintaining long-term prediction reliability under complex traffic conditions. To address these issues, a trajectory prediction method is proposed by combining a data-driven model based on graph neural networks and Informer with a physics model, fused through discriminative learning. Firstly, graph neural networks are utilized to extract spatial information, and the Informer is used for long-term trajectory encoding and decoding to capture the temporal dynamics of trajectories. Then, to improve the physical plausibility of trajectory predictions, a kinematic model with Cubature Kalman Filtering is employed to estimate the trajectory distribution. Furthermore, discriminative learning is designed to fuse a physics model into the decoder of the data-driven model using a generative adversarial approach. This paper conducts ablation experiments and comparative tests on real-world highway trajectory data from the NGSIM dataset. The evaluation confirms that the proposed method achieves consistent and high-quality prediction results across multiple scenarios.
科研通智能强力驱动
Strongly Powered by AbleSci AI