DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks

Traditional modular self-driving frameworks scale poorly in new scenarios, which usually require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable occasions. Therefore, robust and safe self-driving using traditional frameworks is still challenging, especially in complex and dynamic environments. Recently, deep-learning based self-driving methods have shown promising results with better generalization capability but less hand engineering effort. However, most of the previous learning-based methods are trained and evaluated in limited driving scenarios with scattered tasks, such as lane-following, autonomous braking, and conditional driving. In this paper, we propose a graph-based deep network to achieve scalable self-driving that can handle massive traffic scenarios. Specifically, more than 7,000 km of evaluation is conducted in a high-fidelity driving simulator, in which our method can obey the traffic rules and safely navigate the vehicle in a large variety of urban, rural, and highway environments, including unprotected left turns, narrow roads, roundabouts, and pedestrian-rich intersections. The results also show that our method achieves better performance over the baselines in terms of success rate. This work is accompanied with some demonstration videos which are available at https://sites.google.com/view/dignet-self-driving/video-clips/