Andrej Brodnik

Planning Smooth and Obstacle-Avoiding B-Spline Paths for Autonomous Mining Vehicles

We study the problem of automatic generation of smooth and obstacle-avoiding planar paths for efficient guidance of autonomous mining vehicles. Fast traversal of a path is of special interest. We consider fourwheel four-gear articulated vehicles and assume that we have an a priori knowledge of the mine wall environment in the form of polygonal chains. Computing quartic uniform B-spline curves, minimizing curvature variation, staying at least at a proposed safety margin distance from the mine walls, we plan high speed paths. We present a study where our implementations are successfully applied on eight path-planning cases arising from real-world mining data provided by the Swedish mining company Luossavaara-Kiirunavaara AB (LKAB). The results from the study indicate that our proposed methods for computing obstacle-avoiding minimum curvature variation B-splines yield paths that are substantially better than the ones used by LKAB today. Our simulations show that, with an average 32.13%, the new paths are faster to travel along than the paths currently in use. Preliminary results from the production at LKAB show an overall 5%-10% decrease in the total time for an entire mining cycle. Such a cycle includes both traveling, ore loading, and unloading.

An Integrated Framework for Bus Logistics Management: Case Studies

This paper describes the most obvious way for public transportation companies to decrease their operational cost. This is to optimize the logistics of their operations. The optimization process is a very complex operation and therefore we split the logistics into three phases: vehicle scheduling, driver scheduling and driverrostering. The phases reflect also the split of a large problem (long term optimization) to the daily operation and finally to individual trips. The individual trips are then grouped into working shifts and to these are scheduled individual drivers. In the paper we present a detail description of bus scheduling. We use its mapping to the multiple depot vehicle scheduling problem (MDVSP) using a time-space network model. Finally, we solve the problem for two different cases – the city of Szeged and the city of Ljubljana.

An Adaptive BIC Approach for Robust Speaker Change Detection in Continuous Audio Streams

In this paper we focus on an audio segmentation. We present a novel method for robust and accurate detection of acoustic change points in continuous audio streams. The presented segmentation procedure was developed as a part of an audio diarization system for broadcast news audio indexing. In the presented approach, we tried to remove a need for using pre-determined decision-thresholds for detecting of segment boundaries, which are usually the case in the standard segmentation procedures. The proposed segmentation aims to estimate decision-thresholds directly from the currently processed audio data and thus reduces a need for additional threshold tuning from development data. It employs change-detection methods from two well-established audio segmentation approaches based on the Bayesian Information Criterion. Combining methods from both approaches enabled us to adaptively tune boundary-detection thresholds from the underlying processing data. All three segmentation procedures are tested and compared on a broadcast news audio database, where our proposed audio segmentation procedure shows its potential.

A practical approach to the 2D incremental nearest-point problem suitable for different point distributions

In this paper we present a new practical approach to solve the incremental nearest-point problem in the plane. We used the proposed approach in industrial applications with a superior behaviour to the theoretically better solutions. The method efficiently avoids the requirement of initial randomization of the input points by splitting the plane in strips using a heuristic. Points in strips are stored either in (a,b)-skip lists or in (a,b)-trees. Testing of the algorithms at different point distributions shows that our algorithm, using proposed heuristic, is almost insensible to distributions of input points, what makes the algorithm very attractive for various engineering applications.

Extending Traditional Learning by Enforcing Collaboration and Self-Assessment

The paper presents a way to overcome the shortcomings of traditional learning by enforcing collaboration between students and introducing self-assessment as part of the process of final grade formation. Treating collaboration and self assessment as two elements of a modern learning process that are very closely bounded together, the authors argue that these elements should by no means replace the traditional (ex-cathedra) way of learning but rather extend it. A specifically designed computer science course is presented as an illustration of how the introduction of self-assessment combined with teacher evaluation can encourage collaboration between students. The benefits and drawbacks of this method are discussed.

Performance analysis of the partial use of a local optimization operator on the genetic algorithm for the Travelling Salesman Problem

Performance analysis of the partial use of a local optimization operator on the genetic algorithm for the Travelling Salesman Problem Background: The Travelling Salesman Problem is an NP-hard problem in combinatorial optimization with a number of practical implications. There are many heuristic algorithms and exact methods for solving the problem. Objectives: In this paper we study the influence of hybridization of a genetic algorithm with a local optimizer on solving instances of the Travelling Salesman Problem. Methods/Approach: Our algorithm uses hybridization that occurs at various percentages of generations of a genetic algorithm. Moreover, we have also studied at which generations to apply the hybridization and hence applied it at random generations, at the initial generations, and at the last ones. Results: We tested our algorithm on instances with sizes ranging from 76 to 439 cities. On the one hand, the less frequent application of hybridization decreased the average running time of the algorithm from 14.62 sec to 2.78 sec at 100% and 10% hybridization respectively, while on the other hand, the quality of the solution on average deteriorated only from 0.21% till 1.40% worse than the optimal solution. Conclusions: In the paper we have shown that even a small hybridization substantially improves the quality of the result. Moreover, the hybridization in fact does not deteriorate the running time too much. Finally, our experiments show that the best results are obtained when hybridization occurs in the last generations of the genetic algorithm.

LMS in the pre-school education program

Traditional learning environments are today placed face to face with information and communication technologies (ICT) which gradually ambush visible place in education. For this reason it is important for both students and tutors to be capable to use new methods of supplying and receiving the knowledge. One of possible methods are online learning management systems (LMS) which incorporate principles of social constructionism which is based on the idea that we all better acquire new knowledge within a social process when communicating facts to others and base new knowledge on already known facts. We introduced such online learning environment to a first year students at the Faculty of Education with no previous knowledge or little knowledge of ICT usage. We tried to find out how much time a future preschool teachers need to gain satisfying level of digital literacy and competences for learning and teaching skills with information and educational technology (IET)

Interoperability and Semantic Filtering

Interoperability is often seen only as a technological problem related to reusability. We would like to give interoperability a new role in the structure of the learning environment and in collaborative activities. For us interoperability is also connected with didactical, semiotic and cultural aspects. It improves the interaction between the materials produced with different tools, the construction of kaleidoscopic artifacts and the refl ection on the learning process.