Autonomous Driving

A Modular Approach Towards Autonomous Driving in Sim4CV

From our paper: M. Mueller, V. Casser, J. Lahoud, N. Smith and B. Ghanem: “Sim4CV: A Photo-Realistic Simulator for Computer Vision.” International Journal of Computer Vision (IJCV), 2018. (full text)

We present a novel and modular deep learning based approach towards autonomous driving. By using the deep network for pathway estimation only (thus de-coupling it from the underlying car controls), we show that tasks such as lane change, obstacle avoidance, and guided driving become straightforward and very simple to implement. Furthermore, changes regarding the vehicle or its behaviour can be applied easily on the controller side without changing the learned network. Our approach even works without any need for human-generated or hand-crafted training data (although manually collected data can be included if available), thus avoiding the high cost and tedious nature of manually collecting training data. We demonstrate the effectiveness of our approach by measuring the performance on different diversely arranged environments and maps, showing that it can outperform the capabilities of human drivers significantly.

Supplementary Material

Screenshot showing our sub-urban simulation environment.
Screenshot showing our car model in first-person view.
Performance comparison of our approach to human drivers.
Example obstacle avoidance result.
Our car in front of an intersection, sensing the three opportunities of where to drive next.
Track Editor Software developed to easily generate entire road networks and environments by hand or at random.