LOPR: Latent Occupancy PRediction using Generative Models
This work addresses the need for more realistic and accurate environment predictions for autonomous vehicles, representing an incremental improvement over prior deterministic methods.
The paper tackled the problem of unrealistic and incorrect predictions in LiDAR occupancy grid maps for autonomous vehicles by using generative models to decouple occupancy prediction into representation learning and stochastic prediction in latent space, achieving state-of-the-art performance on real-world datasets.
Environment prediction frameworks are integral for autonomous vehicles, enabling safe navigation in dynamic environments. LiDAR generated occupancy grid maps (L-OGMs) offer a robust bird's eye-view scene representation that facilitates joint scene predictions without relying on manual labeling unlike commonly used trajectory prediction frameworks. Prior approaches have optimized deterministic L-OGM prediction architectures directly in grid cell space. While these methods have achieved some degree of success in prediction, they occasionally grapple with unrealistic and incorrect predictions. We claim that the quality and realism of the forecasted occupancy grids can be enhanced with the use of generative models. We propose a framework that decouples occupancy prediction into: representation learning and stochastic prediction within the learned latent space. Our approach allows for conditioning the model on other available sensor modalities such as RGB-cameras and high definition maps. We demonstrate that our approach achieves state-of-the-art performance and is readily transferable between different robotic platforms on the real-world NuScenes, Waymo Open, and a custom dataset we collected on an experimental vehicle platform.