Scene Recognition and Landmark Navigation for Road Vehicles

Abstract The development of autonomous visual guidance of land vehicles at UniBwM is reviewed. An initial breakthrough in performance level has been achieved in 1986 by combined differential/integral representations of the road skeleton and the vehicle state in conjunction with recursive estimation techniques (4-D approach). Feedback control laws allowed easy implementation of reactive behavioral competences; complementing this approach by generic feedforward control time histories for several mission elements introduces the capability for mission performance. Lane changes, turn-offs and handling road forkings are the most essential ones; in conjunction with the capability of landmark recognition and digital map reading this allows the autonomous performance of entire missions. Recently developed capabilities of our test vehicle VaMoRs are discussed.

[1]  Reinhold Behringer,et al.  The seeing passenger car 'VaMoRs-P' , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[2]  C. Goerick,et al.  Towards all around automatic visual obstacle sensing for cars , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[3]  Ernst D. Dickmanns,et al.  Relative 3D-state estimation for autonomous visual guidance of road vehicles , 1989, Robotics Auton. Syst..

[4]  C. Hock.  Landmark navigation with ATHENE , 1991, Fifth International Conference on Advanced Robotics 'Robots in Unstructured Environments.

[5]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[6]  Dirk Dickmanns,et al.  Multiple object recognition and scene interpretation for autonomous road vehicle guidance , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[7]  B. Ulmer.  VITA II-active collision avoidance in real traffic , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[8]  E D Dickmanns,et al.  AUTONOMOUS HIGH SPEED ROAD VEHICLE GUIDANCE BY COMPUTER VISION , 1987 .