End-to-End Autonomous Driving: An Angle Branched Network Approach

Imitation learning for the end-to-end autonomous driving has drawn renewed attention from academic communities. Current methods either only use images as the input, which will yield ambiguities when a vehicle approaches an intersection, or use additional command information to navigate the vehicle but inefficiently. Focusing on making the vehicle automatically drive along the given path, the authors propose a new and effective navigation command called as subgoal angle which does not require human participation and is calculated by the current position and subgoal of the ego-vehicle. Thus, the subgoal angle contains more information than the navigation command represented as a one-hot vector. Additionally, the authors propose a model architecture called as angle branched network that makes predictions based on the subgoal angle. In this network, the subgoal angle is not only used for extracting useful features but also for guiding the appropriate prediction layer to make predictions for both the steer angle and the throttle status (which controls the acceleration). Experiments are conducted in a three-dimensional urban simulator. Both quantitative and qualitative results show the effectiveness of the navigation command and the angle branched network. Moreover, the performance can be further boosted by integrating both semantic and depth information into the driving model. Especially by using the depth information, collisions with vehicles and pedestrians can be reduced.

• Record URL:
  https://doi.org/10.1109/TVT.2019.2921918
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00189545
• Supplemental Notes:
  • Copyright © 2019, IEEE.
• Authors:
  • Wang, Qing
  • Chen, Long
  • Tian, Bin
  • Tian, Wei
  • Li, Lingxi
  • Cao, Dongpu
• Publication Date: 2019-12

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 11599-11610
• Serial:
  • IEEE Transactions on Vehicular Technology
  • Volume: 68
  • Issue Number: 12
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 0018-9545
  • Serial URL: http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=25

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Cameras; Driving; Machine learning; Navigation
• Subject Areas: Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01729361
• Record Type: Publication
• Files: TRIS
• Created Date: Jan 29 2020 2:30PM