FDNet: Feature Decoupling Framework for Trajectory Prediction

Trajectory prediction plays a significant role in autonomous driving, with current challenges primarily focused on capturing complex interactions in traffic scenes. Previous methods usually directly encode non-interactive and interactive information together, and then decode them for trajectory prediction. However, given the complexity inherent property in the trajectory generation process (e. g. , the generation of trajectory points are influenced by the interactions among multiple moving agents, as well as the interactions between agents and the static environment), previous approaches fail to precisely capture separate variations of the trajectory generation process. In this paper, we propose a general and plug-and-play feature decoupling framework for trajectory prediction called FDNet, which can learn the interactive and non-interactive factors in the latent space to capture separate variations of the trajectory generation process. At its core, FDNet is comprised of a Non-interactive Feature Extraction Module to extract non-interactive features, and an Interactive Feature Decoupling Module to decouple interactive features. Extensive experiments conducted on Argoverse and nuScenes demonstrate that FDNet significantly improves the performance of existing methods.

Authors

• Yuhang Li 0007
• Changsheng Li
• Baoyu Fan
• Rongqing Li
• Ziyue Zhang
• Dongchun Ren
• Ye Yuan 0001
• Guoren Wang

Keywords

• Predictive models
• Feature extraction
• Trajectory
• Complexity theory
• Intelligent robots
• Autonomous vehicles
• Trajectory Prediction
• Latent Space
• Interaction Information
• Static Environment
• Factor Space
• Loss Function
• High Cost
• Neural Network
• Transformer
• Distribution Characteristics
• Mutual Information
• Kullback-Leibler
• Generative Adversarial Networks
• Future Trajectories
• Graph Neural Networks
• Mixed Features
• Mutual Information Estimation
• Trajectories Of Agents
• Information Bottleneck
• Feature Subspace
• Feature decoupling
• Generative Adversarial Network