InstitutNews
New paper published @ikg: how to predict movements of road users with DL

New paper published @ikg: how to predict movements of road users with DL

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.   Hao Cheng and his colleagues developed a Deep Learning Model to predict trajectories.

AMENet: Attentive Maps Encoder Network for trajectory prediction

by: Hao Cheng, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn, Monika Sester

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.

The efficacy of AMENet is validated using the recent benchmarks Trajnet (Sadeghian et al., 2018) that contains 20 unseen scenes in various environments and InD (Bock et al., 2019) of four different intersections for trajectory prediction. Each module of AMENet is validated via a series of ablation studies.

The source code is available at github.com/haohao11/AMENet.

The paper can be found at the ISPRS Journal: 

Verfasst von sester