Extremal problems for integral time lag parabolic systems are presented. An optimal boundary control problem for distributed parabolic systems in which integral time lags appear in the state equations and in the bound...
详细信息
Extremal problems for integral time lag parabolic systems are presented. An optimal boundary control problem for distributed parabolic systems in which integral time lags appear in the state equations and in the boundary conditions simultaneously is solved. Such equations constitute in a linear approximation a universal mathematical model for many diffusion processes. the time horizon is fixed. Making use of the Dubovicki-Milutin scheme, necessary and sufficient conditions of optimality for the Neumann problem withthe quadratic performance functionals and constrained control are derived.
the paper is devoted to the development and experimental validation of a radar model elaborated for an automotive application. the described numerical model takes into account the physical properties of a typical auto...
详细信息
the paper is devoted to the development and experimental validation of a radar model elaborated for an automotive application. the described numerical model takes into account the physical properties of a typical automotive radar, the environmental conditions as well as the properties of targeted objects. Moreover, a dedicated, very efficient algorithm of geometric transformations - implemented in the radar model for simulation of wave scattering phenomena - is presented. A phenomenological model of uncertainty is enclosed to the algorithm to represent more effectively radar detections. the solution presented by the authors is thus ready to be used in hardware-in-the-loop simulations of various road traffic scenarios.
the paper presents selected methods for improving the accuracy of classification of headlights and taillights of the vehicles. the methods include analyzing blob properties and locations of the detections. A new featu...
详细信息
the paper presents selected methods for improving the accuracy of classification of headlights and taillights of the vehicles. the methods include analyzing blob properties and locations of the detections. A new feature for describing binary blob shape has been proposed. Moreover, data augmentation technique has been used to improve the results of the classification. the referenced system is based on convolutional neural networks (CNNs). New solutions have been tested with comprehensive set of video sequences (of total duration exceeding ten hours) under various weather conditions and from different road types.
An approach for decision-level fusion for gesture and speech based human-robot interaction (HRI) is proposed. A rule-based method is compared with several machine learning approaches. Gestures and speech signals are i...
详细信息
An approach for decision-level fusion for gesture and speech based human-robot interaction (HRI) is proposed. A rule-based method is compared with several machine learning approaches. Gestures and speech signals are initially classified using hidden Markov models, reaching accuracies of 89.6% and 84% respectively. the rule-based approach reached 91.6% while SVM, which was the best of all evaluated machine learning algorithms, reached an accuracy of 98.2% on the test data. A complete framework is deployed in real time humanoid robot (NAO) which proves the efficacy of the system.
We consider a class of non-linear dynamic systems with finite memory and nonlinear characteristic that reveals time-varying behavior. It is assumed that the considered systems can change their mode in the a priori kno...
详细信息
We consider a class of non-linear dynamic systems with finite memory and nonlinear characteristic that reveals time-varying behavior. It is assumed that the considered systems can change their mode in the a priori known range of modes but the switching moments are unknown and cannot be directly detected. In the considered approach, based on the noisy measurements of the system output, we apply exponentially weighted aggregation techniques to estimate noise-free counterparts of the possessed output observations. theoretical properties of the method as well as exemplary numerical simulations are also described and discussed in the paper.
Current research on autism raises an important methodological issue concerning reliable measurement tools to diagnose abnormal social interactions within autistic children. Here we presents proposal of a interdiscipli...
详细信息
Current research on autism raises an important methodological issue concerning reliable measurement tools to diagnose abnormal social interactions within autistic children. Here we presents proposal of a interdisciplinary approach combining psychology and robotics yielding Human-Robot interaction to recognize autism symptoms based on a pre-schoolers' play withthe social robot (`Touch me' and `Dance with me'). the observational measures combined with competent raters technique indicated abnormal interaction patterns in children with autism during interactive games with NAO robot. Our research, by linking psychological and engineering perspectives provides promising preliminary results on application of robot to study autism based on HRI and results in collection of user's requirements and evaluation's criteria for a robot design.
In the paper the problem of action recognition withthe help of Markov models is considered. We propose an algorithm aiming at reduction of the false positive rate. We state a hypothesis that these errors are caused b...
详细信息
In the paper the problem of action recognition withthe help of Markov models is considered. We propose an algorithm aiming at reduction of the false positive rate. We state a hypothesis that these errors are caused by learning gesture sequences representing rare movements and not that containing popular ones. Our algorithm translates the sequence of gestures into the corresponding Markov models which are used for a preliminary classification. the obtained evaluation coefficients (numbers of proper classifications) are then used to determine the best weights in a combined model composed of these models. In order to find a compromise between the number of true positives and the number of false positives, the power function of weights is examined.
Since Advanced Driver Assistance Systems are getting more and more complex a strong effort is put into the development of open-source autonomous driving simulators. However a robust virtual environment should not only...
详细信息
Since Advanced Driver Assistance Systems are getting more and more complex a strong effort is put into the development of open-source autonomous driving simulators. However a robust virtual environment should not only be assessed by its realistic physics or 3D assets variety, but it also has to incorporate highly accurate and real-time capable sensor models. the research presented in this paper introduces a robust method for validating radar sensor models enabling a simple proof of their reliability in a virtual scenario. To give an overview of radar sensor modeling approaches, the solutions available in the literature are evaluated in terms of usage in virtual environments based on simple criteria. Finally, an exemplary radar sensor model integrated into the CARLA simulator is presented and also a short outline of further research is depicted.
this article presents the design and the subsequent implementation stages for the low-cost shape scanner of relatively small elements. the main concept of hardware and data processing algorithm are described. the code...
详细信息
this article presents the design and the subsequent implementation stages for the low-cost shape scanner of relatively small elements. the main concept of hardware and data processing algorithm are described. the code used for controlling the operation of individual parts of the device was implemented in the Arduino platform. Special software for managing work of the scanner and collecting measurement data was prepared using the Processing programming language. Assuming cost reduction and simple device construction, limited precision of the shape scanning is expected. In order to improve the obtained results, reduce the disturbances and increase the resolution (the number of points describing shape), additional data conversions performed using the neural network were used.
the need to reduce energy consumption, resources, the introduction of new and ecological materials, the multiplicity of modern technologies available, and the complexity and multi-branch nature of architectural and co...
详细信息
the need to reduce energy consumption, resources, the introduction of new and ecological materials, the multiplicity of modern technologies available, and the complexity and multi-branch nature of architectural and construction projects means that designers must make complex and difficult decisions. this work presents currently available and used in the AEC industry project tools, sustainable building design analysis and provides an overview of the possibilities of using artificial intelligence methods and tools, such as Knowledge Based Engineering (KBE), fuzzy logic, neural networks, genetic algorithms, Monte-Carlo simulation. these methods can be used in the early design stage to improve decision making process and to optimize boththe design process and the project itself. this article presents possible ways of developing AI methods for wider application in architectural design with possibilities to commercialize them.
暂无评论