AMENet: Attentive Maps Encoder Network for Trajectory Prediction

Abstract

Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic. How an agent moves is affected by the various behaviors of its neighboring agents in different environments. To predict movements, we propose an end-to-end generative model named Attentive Maps Encoder Network (AMENet) that encodes the agent's motion and interaction information for accurate and realistic multi-path trajectory prediction. A conditional variational auto-encoder module is trained to learn the latent space of possible future paths based on attentive dynamic maps for interaction modeling and then is used to predict multiple plausible future trajectories conditioned on the observed past trajectories. The efficacy of AMENet is validated using two public trajectory prediction benchmarks Trajnet and InD.

arXiv commentAccepted by ISPRS Journal of Photogrammetry and Remote Sensing

References in corpus (9)

• Auto-Encoding Variational Bayes
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Social Force Model for Pedestrian Dynamics
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Semi-Supervised Learning with Deep Generative Models
• Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
• Multiple Futures Prediction
• Human Trajectory Prediction using Spatially aware Deep Attention Models
• An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark