Path Planning Based on Support Vector Machine for Autonomous Vehicle Part 2

This paper describes a new approach for a path planning algorithm based on a Support Vector Machine (SVM). An SVM is a binary classification method that finds the optimal separating hyperplane based on the concept of margin maximization. The authors algorithm focused on the parameters that correlated with the curvature in the solution of the SVM. The authors have developed the path planning method generating the safe and smooth path in a single process. For the practical use of autonomous vehicles using this technology, the authors verified if it could be applied in situations where lane change and parked vehicle avoidance were necessary. The results of the simulation showed that it was possible to generate appropriate paths under both situations.

  • Availability:
  • Supplemental Notes:
    • Abstract used with permission of ITS Japan. Paper No. 3199.
  • Corporate Authors:

    ITS Japan

    Tokyo,   Japan 
  • Authors:
    • Ueda, Yusuke
    • Tsuruta, Tomohiko
    • Hayashi, Rina
    • Hatoh, Takeshi
    • Mita, Seiichi
  • Conference:
  • Publication Date: 2013


  • English

Media Info

  • Media Type: Digital/other
  • Features: CD-ROM; Figures; References;
  • Pagination: 10p
  • Monograph Title: 20th ITS World Congress, Tokyo 2013. Proceedings

Subject/Index Terms

Filing Info

  • Accession Number: 01536655
  • Record Type: Publication
  • ISBN: 9784990493981
  • Files: TRIS
  • Created Date: Aug 28 2014 12:12PM