Skip to content
forked from agrimgupta92/sgan

Code uses SGAN for predicting trajectories of cars

License

Notifications You must be signed in to change notification settings

Chandrayee/sgan

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CarGAN

This project uses SocialGAN to synthesize edge-case driving scenarios for training self-driving cars. We use Social GAN to jointly forecast trajectories of traffic participants (cars) capturing socially relevant group behavior in traffic. The original SocialGAN paper can be found here: Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

Model

CarGAN has four components: i) the original SocialGAN component uses recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people, ii) a CNN based feature extractor from LiDAR data and road marking and iii) attention models that decompose the car behaviors into social context and physical context and iv) a second discriminator that verifies that the synthesized anomalous trajectories are physically correct but socially inappropriate or even adversarial.

About

Code uses SGAN for predicting trajectories of cars

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 85.5%
  • Jupyter Notebook 13.2%
  • Shell 1.3%