AA-SGAN: Adversarially Augmented Social GAN with Synthetic Data
This addresses the challenge of data scarcity for autonomous systems by improving synthetic data utility, though it is incremental as it builds on existing generative models.
The paper tackles the problem of training pedestrian trajectory prediction models with unrealistic synthetic data by proposing an adversarial augmentation method, resulting in significant performance gains on real-world trajectories.
Accurately predicting pedestrian trajectories is crucial in applications such as autonomous driving or service robotics, to name a few. Deep generative models achieve top performance in this task, assuming enough labelled trajectories are available for training. To this end, large amounts of synthetically generated, labelled trajectories exist (e.g., generated by video games). However, such trajectories are not meant to represent pedestrian motion realistically and are ineffective at training a predictive model. We propose a method and an architecture to augment synthetic trajectories at training time and with an adversarial approach. We show that trajectory augmentation at training time unleashes significant gains when a state-of-the-art generative model is evaluated over real-world trajectories.