A.3.0 Ground vehicle guidance by vision

A.3.1 Road recognition and vehicle guidance



The key to success, beside recursive estimation, was to describe road shape in differential-geometry terms:

  • On the one side, this considerably reduces the number of parameters needed for describing a local road section; integration constants fixing global direction and position can be left off.

  • On the other side, driving on a road at velocity V turns the differential-geometry description into an ordinary differential equation in time in a coordinate system moved with the vehicle.

  • As early as 1987 this allowed driving at high speeds (up to Vmax = 96 km/h) on an obstacle-free stretch of Autobahn near Dingolfing with relatively little computing power available, when competitors using quasi-static approaches were at least an order of magnitude slower.

  • The dynamic model of egomotion is very simple but represents the properties of Ackermann steering (standard in road vehicles) as control input quite well.

The first demonstration of visual road vehicle guidance at speeds up to ~ 40 km/h was given to ‘Daimler-Benz AG Research’ in 1986.

Video 02 SkidpanDB-VaMoRs 1986

Video 04 VaMoRsAutobahn Dingolfing 1987

(First high-speed road vehicle guidance by vision on a free stretch of Autobahn) 

References

Dickmanns ED, Zapp A (1985). Guiding Land Vehicles Along Roadways by Computer Vision. Proc. Congres Automatique 1985, AFCET, Toulouse, pp 233-244

Dickmanns ED, Zapp A (1986). A Curvature-based Scheme for Improving Road Vehicle Guidance by Computer Vision. In: 'Mobile Robots', SPIE Proc. Vol. 727, Cambridge, Mass., pp 161-168

Mysliwetz B, Dickmanns ED (1986). A Vision System with Active Gaze Control for real-time Interpretation of Well Structured Dynamic Scenes. In L.O. Hertzberger (ed): Proc. of 1st Conference on Intelligent Autonomous Systems (IAS-1), Amsterdam, Dec. 1986, pp 477-483

Dickmanns ED, Zapp A (1987). Autonomous High Speed Road Vehicle Guidance by Computer Vision. 10th IFAC World Congress Munich, Prep rint Vol. 4, 1987, pp 232-237

Dickmanns ED, Graefe V (1988). a) Dynamic monocular machine vision. Machine Vision and Applications, Springer International, Vol. 1, pp 223-240. b) Applications of dynamic monocular machine vision. (ibid), pp 241-261

Zapp A (1988). Automatische Straßenfahrzeugführung durch Rechnersehen, Dissertation UniBwM /LRT

Dickmanns ED, Mysliwetz B, Christians T (1990). Spatio-Temporal Guidance of Autonomous Vehicles by Computer Vision. IEEE-Transactions on Systems, Man and Cybernetics, Vol. 20, No. 6, Special Issue on Unmanned Vehicles and Intelligent Robotic Systems, pp 1273-1284

Mysliwetz B (1990). Parallelrechner-basierte Bildfolgen-Interpretation zur autonomen Fahrzeugsteuerung. Dissertation, UniBwM / LRT

Behringer R, von Holt V, Dickmanns D (1992). Road and Relative Ego-State Recognition. In: Proc. Int. Symp. 'Intelligent Vehicles', IEEE, SAE, Detroit

Dickmanns ED, Mysliwetz B (1992). Recursive 3-D Road and Relative Ego-State Recognition. IEEE-Transactions PAMI, Vol. 14, No. 2, Special Issue on 'Interpretation of 3-D Scenes', pp 199-213

Behringer R (1994). Road Recognition from Multifocal Vision. In Masaki (ed.): Proc. of Int. Symp. on Intelligent Vehicles '94, Paris, pp 302-307

Behringer R, Hötzl S (1994). Simultaneous Estimation of Pitch Angle and Lane Width from the Video Image of a Marked Road. IEEE-Conf. on Intelligent Robots and Systems (IROS'94), Neubiberg,

Brüdigam C (1994). Intelligente Fahrmanöver sehender autonomer Fahrzeuge in autobahnähnlicher Umgebung. Dissertation, UniBwM / LRT

Dickmanns ED (2007). Dynamic Vision for Perception and Control of Motion. Springer-Verlag, London