Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planning

TL;DR

This paper presents a monocular camera-based trajectory planning system that uses Bird-Eye-View occupancy grids as an intermediate representation, improving interpretability and motion forecasting for autonomous driving.

Contribution

It introduces a novel method to predict BEV occupancy grids from camera images via semantic masks and homography, enhancing end-to-end driving networks.

Findings

Effective BEV occupancy grid prediction from monocular images.

Improved interpretability and accuracy in trajectory planning.

Robustness in motion forecasting using flat world assumptions.

Abstract

Camera-based end-to-end driving neural networks bring the promise of a low-cost system that maps camera images to driving control commands. These networks are appealing because they replace laborious hand engineered building blocks but their black-box nature makes them difficult to delve in case of failure. Recent works have shown the importance of using an explicit intermediate representation that has the benefits of increasing both the interpretability and the accuracy of networks' decisions. Nonetheless, these camera-based networks reason in camera view where scale is not homogeneous and hence not directly suitable for motion forecasting. In this paper, we introduce a novel monocular camera-only holistic end-to-end trajectory planning network with a Bird-Eye-View (BEV) intermediate representation that comes in the form of binary Occupancy Grid Maps (OGMs). To ease the prediction of OGMs in BEV from camera images, we introduce a novel scheme where the OGMs are first predicted as semantic masks in camera view and then warped in BEV using the homography between the two planes. The key element allowing this transformation to be applied to 3D objects such as vehicles, consists in predicting solely their footprint in camera-view, hence respecting the flat world hypothesis implied by the homography.