Machine Vision and Applications

, Volume 8, Issue 6, pp 359–364 | Cite as

Vision-based robotic convoy driving

  • H. Schneiderman
  • M. Nashman
  • A. J. Wavering
  • R. Lumia


This article describes a method for vision-based autonomous convoy driving in which a robotic vehicle autonomously pursues another vehicle. Pursuit is achieved by visually tracking a target mounted on the back of the pursued vehicle. Visual tracking must be robust, since a failure leads to catastrophic results. To make our system as reliable as possible, uncertainty is accounted for in each measurement and propagated through all computations. We use a best linear unbiased estimate (BLUE) of the target's position in each separate image, and a polynomial least-mean-square fit (LMSF) to estimate the target's motion. Robust autonomous convoy driving has been demonstrated in the presence of various lighting conditions, shadowing, other vehicles, turns at intersections, curves, and hills. A continuous, autonomous, convoy drive of over 33 km (20 miles) was successful, at speeds averaging between 50 and 75km/h (30–45 miles/h).

Key words

Convoy driving Caravan driving Autonomous navigation Mobile robots Visual tracking 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Aloimonos Y, Tsakiris DP (1991) On the visual mathematics of tracking. Image Vision Comput 4:235–251Google Scholar
  2. Aspex (1987) PIPE-an introduction to the PIPE system. Aspex Inc., New YorkGoogle Scholar
  3. Bierman G (1977) Factorization Methods for Discrete Sequential Estimation. Academic Press. New York.Google Scholar
  4. Dickmanns ED (1991) 4D dynamic vision for intelligent motion control. Eng Appl Artif Intell 4:301–307Google Scholar
  5. Dickmanns ED, Graffe V (1988a) Dynamic monocular machine vision. Machine Vision Appl 1:223–240Google Scholar
  6. Dickmanns ED, Graffe V (1988b) Applications of dynamic monocular machine vision. Machine Vision Appl 1:241–261Google Scholar
  7. Dickmanns ED, Christians T, Brudigam C (1990) Convoy driving by monocular dynamic vision. Pro-Art Workshop on Vision, Sophia-AntipolisGoogle Scholar
  8. Gennery DB (1992) Visual tracking of known three-dimensional objects. Int J Comput Vision 7:243–270Google Scholar
  9. Helstrom CW (1984) Probability and stochastic processes for engineers. Macmillan, New YorkGoogle Scholar
  10. Kay SM (1993) Fundamentals of statistical signal processing: estimation theory. Prentice Hall, Englewood Cliffs, NJGoogle Scholar
  11. Kehtarnavaz N, Griswold NC, Lee JS (1991) Visual control of an autonomous vehicle (BART)—the vehicle-following problem. IEEE Trans Vehicular Technol 40:654–662Google Scholar
  12. Kent EW, Shneier MO, Lumia R (1985) PIPE. J Parallel Distributed Comput 1:50–78Google Scholar
  13. Kories R, Rehfeld H, Zimmermann G (1988) Toward autonomous convoy driving: recognizing the starting vehicle in front. 9th International Conference on Pattern Recognition, Washington DC, IEEE Computer Society Press, pp 531–535Google Scholar
  14. Lowe DG (1993) Robust model-based motion tracking through the integration of search and estimation. Int J Comput Vision 8:113–122Google Scholar
  15. Murphy KN (1992) Navigation and retro-traverse on a remotely operated vehicle. Proceedings of the IEEE Conference on Intelligent Control and Instrumentation, SingaporeGoogle Scholar
  16. Murphy KN (1994) Analysis of robotic vehicle steering and controller delay. 5th International Symposium on Robotics and Manufacturing, Maui, Hawaii, pp 631–636Google Scholar
  17. Murphy KN, Juberts M, Legowik SA, Nashman M, Schneiderman H, Scott HA, Szabo S (1993) Ground vehicle control at NIST: from teleoperation to autonomous. SOAR '93. HoustonGoogle Scholar
  18. Ng LC, LaTourette RA (1983) Equivalent bandwidth of a general class of polynomial smoothers. J Acoust Soc Am 74:814–826Google Scholar
  19. Papanikolopoulos NP, Khosla PK, Kanade T (1993) Visual tracking of a moving target by a camera mounted on a robot: a combination of control and vision. IEEE Trans Robotics Automation 9:14–35Google Scholar
  20. Papoulis A (1984) Probability, random variables and stochastic processes. McGraw-Hill, New YorkGoogle Scholar
  21. Pomerleau D (1990) Neural network based autonomous navigation. Vision and Navigation: The Carnegie Mellon Navlab. Kluwer, Norwell, Mass.Google Scholar
  22. Pomerleau D (1992) Progress in neural network-based vision for autonomous robot driving. Proceedings of Intelligent Vehicles '92 Symposium, Detroit, Mich., pp 391–396Google Scholar
  23. Schwarzinger M, Zielke T, Noll D, Brauckmann M, von Seelen W (1992) Vision-based car-following: detection, tracking, and identification. Proceedings of the Intelligent Vehicles '92 Symposium. Detroit, Mich., pp 24–29Google Scholar
  24. Szabo S, Scott H, Murphy KN, Legowik S, Bostelman R (1992) Highlevel mobility controller for a remotely operated land vehicle. J Intell Robotic Syst 5:63–77Google Scholar
  25. Wavering AJ, Lumia R (1993) Predictive visual tracking. Proceedings of Intelligent Robots and Computer Vision XII: Active Vision and 3D Methods. SPIE 2056:86–97Google Scholar
  26. Zielke T, Brauckmann M, von SeelenW (1992) CARTRACK: computer vision-based car-following. IEEE Workshop on Applications of Computer Vision, Palm Springs, Calif., pp 156–163Google Scholar

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  • H. Schneiderman
    • 1
  • M. Nashman
    • 2
  • A. J. Wavering
    • 3
  • R. Lumia
    • 4
  1. 1.Robotics Institute Carnegie Mellon UniversityPittsburghUSA
  2. 2.Intelligent Systems DivisionNational Institute of Standards and TechnologyGaithersburgUSA
  3. 3.Intelligent Systems DivisionNational Institute of Standards and TechnologyGaithersburgUSA
  4. 4.Mechanical Engineering DepartmentThe University of New MexicoAlbuquerqueUSA

Personalised recommendations