Abstract This paper deals with the Cross-Entropy method application in the control theory. The method is a the combinatorial optimization technique that is mostly used in the networks theory and could be used in deterministic optimization problems as well. The paper shows the possibiliy of the Cross-Entropy usage in the control parameter tuning. Similar to genetics algorithms, this method minimizes a given performance function in order to find optimal parameters. The appropirate conclusions about relability and the convergence rate of the method were experimentaly supported. The first two experiments used PI controller with different performance functions, where the optimal controller values have been obtained through the simulation. The third experiment used LQR controller to control a complex system. The tunining of four parameters of a LQR control matrix and obtained values were compared with the ones generated by LQR algorithm.

The possibility of using different kind of cruise control algorithms in the vehicle tracking style adjustment was shown in this paper. These vehicle tracking styles ranged from extremely comfort to extremely sportive ones and different from each other respect to acceleration signals of the tracking vehicle. First, short overview of a neural network based algorithm was shown in order to achieve desired level of the tracking comfort. Also, the possibility of the tracking style adjustment was presented using Pipes and linear optimal control model. The appropriate parameter space regions for different level of comfort have been found with respect to the given cost function of the tracking style.

The purpose of this paper is to show a simple ability of using neural networks in longitudinal vehicle guidance. The main motivation is an opportunity of neural networks to learn from acquired real driver data, as well as to reproduce many driver behaviour styles raging from extremely comfort to extremely sportive ones. This possibility is shown with a simulated model based longitudinal trajectory generation. This model has used an adjustable comfort parameter for different sorts of driver behaviour. Experiment results, obtained with Audi test vehicle, are also presented.

The purpose of this paper is to show a simple ability of a neural network usage in longitudinal vehicle guidance for the comfort adjustment. It gives a short overview of a trajectory generation algorithm as well as comfort adjustment for longitudinal movement using neural networks. The algorithm for longitudinal trajectory generation was implemented in AUDI test vehicle and the results have been shown. Also, two concepts of comfort adjustment using neural networks were also presented. The comfort adjustment was associated with the certain driver tracking style ranging from extremely comfort to extremely sportive ones

Thepurpose ofthis paperistoshowasimple ability ofa neuralnetworkusageinlongitudinal vehicle guidance forthecomfortadjustment. Itgivesa short overview ofa trajectory generation algorithm aswellas comfort adjustment forlongitudinal movementusing neural networks.The algorithm for longitudinal trajectory generation wasimplemented inAUDItestvehicle andthe results havebeen shown.Also,twoconcepts ofcomfort adjustment using neural networks werealsopresented. The comfort adjustment wasassociated withthecertain driver tracking style ranging fromextremely comfort toextremely sportive ones.

A solution for a synchronized set of laboratory exercises covering both control theory and Matlab programming package is proposed in this paper. Some Matlab features are introduced in order to make a control course easy for understanding. Also, some general Matlab abilities are considered allowing usage of this program not only for control purposes but also for other electrical engineering fields. Sections presented in this paper may be used in a control laboratory as well as a sheet giving insight into some control fundamentals and Matlab abilities for non-control engineers

Parameter space and D stability are used in this paper to propose a simple PID tuning method and give some insight into the tuning point selection process. Parameter space is reduced to two parameters: the proportional and the integral coefficient of the PID regulator. The differential component is embedded in the plant as an internal feedback. The reduction of the parameter space to the parameter plane makes possible to find appropriate region in parameter plane without a need to use sophisticated mathematical methods. The presented technique may be applied to any linear plant. The time delay treatment does not require any approximations. The method allows a very quick way to find if a plant is tunable at all with a PID controller. Also it is easy to find robust tuning and check robustness for all relevant plant parameters. The influence of the shape of the D-stability region and the particular choice of the tuning point on the unit step response of the system is addressed as well.