Relative 3D-state estimation for autonomous visual guidance of road vehicles

Abstract The integrated spatio-temporal approach to real-time machine vision, which has allowed outstanding performance with moderate computing power, is extended to obstacle recognition and relative spatial state estimation using monocular vision. A modular vision system architecture is discussed centering around features and objects. Experimental results with VaMoRs, a 5-ton test vehicle are given. Stopping in front of obstacles of at least 0.5 m 2 cross section has been demonstrated on unmarked two-lane roads at velocitie up to 40 km/h.

[1]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[2]  Matthew Turk,et al.  Video road-following for the autonomous land vehicle , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[3]  Mark Thomas,et al.  Vision-based road following in the autonomous land vehicle , 1987, 26th IEEE Conference on Decision and Control.

[4]  Ernst D. Dickmanns,et al.  Distributed Scene Analysis For Autonomous Road Vehicle Guidance , 1987, Other Conferences.

[5]  Volker Graefe,et al.  Applications of dynamic monocular machine vision , 1988, Machine Vision and Applications.

[6]  Takeshi Hirose,et al.  An Automobile with Artificial Intelligence , 1979, IJCAI.

[7]  Volker Graefe,et al.  Dynamic monocular machine vision , 1988, Machine Vision and Applications.

[8]  Charles E. Thorpe,et al.  Vision and Navigation for the CMU Navlab , 1987, Other Conferences.

[9]  Volker Graefe,et al.  Dynamic Vision Systems for Autonomous Mobile Robots , 1989, Proceedings. IEEE/RSJ International Workshop on Intelligent Robots and Systems '. (IROS '89) 'The Autonomous Mobile Robots and Its Applications.