허건수 교수

Vision-based lane sensing systems require accurate and robust sensing performance in lane detection. Besides, there exists trade-off between the computational burden and processor cost, which should be considered for implementing the systems in passenger cars. In this paper, a stereo vision-based lane detection system is developed with considering sensor configuration aspects. An inverse perspective mapping method is formulated based on the relative correspondence between the left and right came

The tractor and trailer units of the semi-trailer truck are connected through the hitch point. The articulation angle is generated when lateral force is applied to the vehicle and it causes the tractor and trailer units to move in different trajectories. When driving on narrow road or large curvature road, considerable level of driving skill is required to drive within the road boundary. If the driver passes through a narrow road without considering the articulation angle, a collision accident m

Existing adaptive observers may cause parameter estimate drift due to disturbances even if state estimation errors remain in small. To avoid the drift phenomena in the presence of bounded disturbances, several robust adaptive observers have been introduced addressing bounds in state and parameter estimates. However, it is not easy for these observers to manipulate the size of the bounds with the selection of the observer gain. In order to reduce estimation errors, this paper introduces the H-inf

The linear motors are easily affected by load disturbance, force ripple, friction, and parameter variations because there is no mechanical transmission to reduce the effects of model uncertainties and external disturbance. For high-speed/high-accuracy position control of a linear-motor-driven X-Y table, a nonlinear adaptive controller including a cross-coupling algorithm is designed in this paper, where the nonlinear effects such as friction and force ripple are estimated and compensated. A cros

In this paper, track tension estimation methods are developed for tracked vehicles which are subject to various maneuvering tasks such as longitudinal driving on sloping and/or rough roads. The information of the track tension is very important for the tracked vehicles because the track tension is c...

Lane Sensing techniques based on vision sensors are regarded promising because they require little infrastructure on the highway except clear lane markers. However, they require more intelligent processing algorithms in vehicles to generate the previewed roadway from the vision images. In this paper, a lane sensing algorithm using vision sensors is developed to improve the sensing robustness. The parallel stereo-camera is utilized to regenerate the 3-dimensional road geometry. The lane geometry