Environment prediction frameworks are essential for autonomous vehicles to facilitate safe maneuvers in a dynamic environment. Previous approaches have used occupancy grid maps as a bird's eye-view representation of the scene and optimized the prediction architectures directly in pixel space. Although these methods have had some success in spatiotemporal prediction, they are, at times, hindered by unrealistic and incorrect predictions. We postulate that the quality and realism of the forecasted occupancy grids can be improved with the use of generative models. We propose a framework that decomposes occupancy grid prediction into task-independent low-dimensional representation learning and task-dependent prediction in the latent space. We demonstrate that our approach achieves state-of-the-art performance on the real-world autonomous driving dataset, NuScenes.

翻译：环境预测框架对于自主载体在动态环境中便利安全操作至关重要。以前的做法已经将占用网图用作鸟类对现场的视觉显示,并直接优化了像素空间的预测结构。虽然这些方法在时空预测方面有些成功,但有时受到不现实和不正确的预测的阻碍。我们假设,使用基因模型可以改进预测占用网的质量和现实性。我们提出了一个框架,将占用网预测分解成在潜空进行依赖任务的低维代言学习和任务预测。我们证明,我们的方法在现实世界自主驱动数据集Nuscenes上取得了最先进的表现。