TY - GEN
T1 - DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks
AU - Cai, Peide
AU - Wang, Hengli
AU - Sun, Yuxiang
AU - Liu, Ming
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/12
Y1 - 2021/12
N2 - Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases. Recently, self-driving methods based on deep learning 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. Demonstration videos are available at https: //caipeide.github.io/dignet/.
AB - Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases. Recently, self-driving methods based on deep learning 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. Demonstration videos are available at https: //caipeide.github.io/dignet/.
UR - http://www.scopus.com/inward/record.url?scp=85124370493&partnerID=8YFLogxK
U2 - 10.1109/IROS51168.2021.9636376
DO - 10.1109/IROS51168.2021.9636376
M3 - Conference article published in proceeding or book
AN - SCOPUS:85124370493
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 8979
EP - 8984
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
Y2 - 27 September 2021 through 1 October 2021
ER -