A Localizability Constraint-Based Path Planning Method for Autonomous Vehicles

During autonomous navigation, environmental information and map noises at different locations may have dissimilar influence on a vehicle’s localization process. This implies that the vehicle’s localizability, i.e., the ability to localize itself in an environment using laser range finder (LRF) readings, varies over a given map. It is essential to take this factor into consideration when planning a path to avoid large localization errors or placing the vehicle at risk of failure to perform localization. The authors propose a localizability constraint (LC)-based path planning method for autonomous vehicles which plans the navigation path according to LRF sensor model of the vehicle in an effort to maintain a satisfactory level of localizability throughout the path, as well as to reduce the overall localization error. Their method is not limited to any specific algorithm in the optimization stage. Paths planned with and without LC are compared, and the influence of the LRF sensor model on planning outcomes is discussed through simulations. By conducting comparative experiments on a “JiaoLong” intelligent wheelchair in both indoor and outdoor environments, they show that the proposed method effectively lowers the localization error along the planned paths.

• Record URL:
  • https://doi.org/10.1109/TITS.2018.2868377
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2019, IEEE.
• Authors:
  • Irani, Behnam
  • Wang, Jingchuan
  • Chen, Weidong
• Publication Date: 2019-7

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 2593-2604
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 20
  • Issue Number: 7
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Automatic vehicle location; Autonomous vehicle guidance; Autonomous vehicles; Driving; Image analysis; Laser radar; Trajectory control
• Uncontrolled Terms: Localization
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting; Vehicles and Equipment;

Filing Info

• Accession Number: 01713041
• Record Type: Publication
• Files: TLIB, TRIS
• Created Date: Jul 30 2019 9:38AM