DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling

TL;DR

DiversityGAN introduces a semantic space-aware generative model for vehicle trajectory prediction, enabling realistic, diverse, and controllable trajectory sampling to improve safety evaluation in autonomous driving.

Contribution

The paper presents a novel GAN-based framework that incorporates a low-dimensional semantic space for diverse vehicle trajectory generation, enhancing coverage and interpretability.

Findings

Achieves state-of-the-art prediction accuracy.

Provides improved coverage of trajectory semantics.

Enables controllable sampling of diverse trajectories.

Abstract

Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it -- a key ability for evaluating safety from a planning and verification perspective. In this work, we devise a novel approach for generating realistic and diverse vehicle trajectories. We extend the generative adversarial network (GAN) framework with a low-dimensional approximate semantic space, and shape that space to capture semantics such as merging and turning. We sample from this space in a way that mimics the predicted distribution, but allows us to control coverage of semantically distinct outcomes. We validate our approach on a publicly available dataset and show results that achieve state-of-the-art prediction performance, while providing improved coverage of the space of predicted trajectory semantics.