Maximizing Reward in a Non-Stationary Mobile Robot Environment

The ability of a robot to improve its performance on a task can be critical, especially in poorly known and non-stationary environments where the best action or strategy is dependent upon the current state of the environment. In such systems, a good estimate of the current state of the environment is key to establishing high performance, however quantified. In this paper, we present an approach to state estimation in poorly known and non-stationary mobile robot environments, focusing on its application to a mine collection scenario, where performance is quantified using reward maximization. The approach is based on the use of augmented Markov models (AMMs), a sub-class of semi-Markov processes. We have developed an algorithm for incrementally constructing arbitrary-order AMMs on-line. It is used to capture the interaction dynamics between a robot and its environment in terms of behavior sequences executed during the performance of a task. For the purposes of reward maximization in a non-stationary environment, multiple AMMs monitor events at different timescales and provide statistics used to select the AMM likely to have a good estimate of the environmental state. AMMs with redundant or outdated information are discarded, while attempting to maintain sufficient data to reduce conformation to noise. This approach has been successfully implemented on a mobile robot performing a mine collection task. In the context of this task, we first present experimental results validating our reward maximization performance criterion. We then incorporate our algorithm for state estimation using multiple AMMs, allowing the robot to select appropriate actions based on the estimated state of the environment. The approach is tested first with a physical robot, in a non-stationary environment with an abrupt change, then with a simulation, in a gradually shifting environment.     

Comparison of metaheuristics for the k‐labeled spanning forest problem

In this paper, we study the k‐labeled spanning forest (kLSF) problem in which an undirected graph whose edges are labeled and an integer‐positive value are given; the aim is to find a spanning forest of the input graph with the minimum number of connected components and the upper bound on the number of labels. The problem is related to the minimum labeling spanning tree problem and has several applications in the real world. In this paper, we compare several metaheuristics to solve this NP‐hard problem. In particular, the proposed intelligent variable neighborhood search (VNS) shows excellent performance, obtaining high‐quality solutions in short computational running time. This approach integrates VNS with other complementary approaches from machine learning, statistics, and experimental algorithmics, in order to produce high‐quality performance and completely automate the resulting optimization strategy.     

Survey of Intelligent Control Techniques for Humanoid Robots

This paper focusses on the application of intelligent control techniques (neural networks, fuzzy logic and genetic algorithms) and their hybrid forms (neuro-fuzzy networks, neuro-genetic and fuzzy-genetic algorithms) in the area of humanoid robotic systems. It represents an attempt to cover the basic principles and concepts of intelligent control in humanoid robotics, with an outline of a number of recent algorithms used in advanced control of humanoid robots. Overall, this survey covers a broad selection of examples that will serve to demonstrate the advantages and disadvantages of the application of intelligent control techniques.     

Contribution to the decoupled control of large-scale mechanical systems

This paper presents the concept of decomposition as applied to the control synthesis of multivariable mechanical systems, in which the coupling among the subsystems can be very strong. The system class considered contains subsystems with powered degrees of freedom, as well as subsystems without their own actuators. Global control is introduced to diminish the influence of coupling on the stability of the whole system. The procedure is illustrated by simulation of two examples, one in robotics, the other in biomechanics.     

Influence of nitrogen content on the pit formation and pit propagation in the welded joints of X5CrNi18-10 stainless steel

The influence of welding current and nitrogen content in argon shielding gas on the resistance of the welded joint (weld metal and heat-affected zone [HAZ]) of the stainless steel X5CrNi18-10 to the formation and growth of pits was investigated. Also, the susceptibility of the welded joint to intergranular corrosion was examined. Pitting corrosion resistance indicators were determined based on anodic potentiodynamic polarization measurements in NaCl + Na₂SO₄ solution, while susceptibility to intergranular corrosion was determined by the potentiokinetic method with a double loop (DL EPR). SEM/EDS was used to analyze the microstructure. It has been shown that higher nitrogen content in shielding gas leads to an increase in the resistance of welded joints (weld metal and HAZ) to the pit formation. However, an improvement in the resistance to the pit formation leads to a decline in the resistance of the welded joint to pit growth. An explanation of this phenomenon is proposed. Also, it was shown that the increase of the welding current increases the susceptibility of the welded joint to intergranular corrosion, while the higher nitrogen content has no effect.     

Application of GC–MSD and LC–MS/MS for the determination of priority pesticides in baby foods in Serbian market

Babies and small children are especially sensitive population to the exposure to environmental contaminants. Their small mass and developing systems, including brain development may show adverse health effects from even low levels of contamination on a chronic or single dose case. In this paper one extraction method and two chromatographic techniques for the determination of pesticide residues in baby food were evaluated. A liquid chromatography–tandem mass spectrometry technique combined with electrospray ionization (ESI), (LC–MS/MS) and gas chromatography–mass spectrometry detection (GC–MSD) technique were applied in the detection of 50 pesticides in baby food. So-called QuEChERS (quick, easy, cheap, effective, rugged and safe) method was used as a sample preparation procedure. The recoveries were investigated at three levels (5, 10 and 50 μg/kg) and the results obtained showed compliance with the contemporary EU requirements with a few exceptions. LOQs for most of the tested pesticides were below the EU MRLs (10 μg/kg), except deltamethrin, cypermethrin, fenvalerate, phosalone and beta-cyfluthrin (LOQs were 10 μg/kg). Both techniques were applied in the analysis of 50 samples of baby food manufactured in Serbia.     

Phytochemical composition and antimicrobial activities of the essential oils from Satureja subspicata Vis. growing in Croatia

The present study describes the phytochemical profile and antimicrobial activity of Satureja subspicata Vis. essential oils, collected in Dalmatia (Croatia). Three samples of essential oils were obtained from the aerial parts of the plant by hydrodistillation and analyzed by GC–MS. From the 24 compounds representing 97.47% of the oils, carvacrol (16.76%), α-pinene (13.58), p-cymene (10.76%), γ-terpinene (9.54%) and thymol methyl ether (8.83%) appear as the main components. The oils also contained smaller percentages of myrcene, linalool, β-caryophyllene, limonene, geranyl acetate, 1-Octen-3-ol, nerol, thymol and borneol. Furthermore, antimicrobial activity of the oil was evaluated using agar diffusion and broth microdilution methods. The antimicrobial test results showed that the oils had a great potential antimicrobial activity against all 13 bacteria and 9 fungal strains. Gram-positive bacteria are more sensitive to the investigated oil, with a range of 0.09 to 6.25 μl/ml than Gram-negative bacteria in the range which is significantly higher from 1.56 to 25.00 μl/ml. Results presented here may suggest that the essential oil of S. subspicata possesses antimicrobial properties, and is therefore a potential source of antimicrobial ingredients for the food and pharmaceutical industry.     

Wheat flour confectionery products as a source of inorganic nutrients: zinc and copper contents in hard biscuits

Cereal-based confectionery products being consumed through whole human life are considered mainly to be a source of carbohydrates, that is energy, although cereals are a rich source of minerals as well. To evaluate some hard biscuits produced in Croatia as a source of different trace elements in nutrition, in this study Zn and Cu contents were determined in classic wheat flour biscuits and in dietetic biscuits enriched with whole wheat grain flour or whole wheat grain grits, soya flour and skimmed milk. Zn was determined by flame atomic absorption spectrometry (AAS); Cu was determined by inductively coupled plasma atomic emission spectroscopy (ICP-AES). The results show that the Zn content in different kinds of biscuits ranges from 5.89 up to 17.64 mg/kg and the Cu content ranges from 1.15 up to 2.79 mg/kg depending on the type of wheat milling products and mineral content of other ingredients used. Enriched dietetic biscuits produced from wheat flour type 850 and whole wheat grain flour and/or soya flour and skimmed milk were almost 200% and 150% higher in Zn and Cu, respectively, in comparison to classic white wheat flour biscuits and can be considered as good sources of Zn and Cu in nutrition.     

Changes of hydrogen peroxide and radical-scavenging activity of raspberry during osmotic, convective, and freeze-drying

This study was conducted to investigate the influence of different drying treatments on antioxidant (AO) activity and phenolic content of raspberry (Rubus idaeus), cultivar Willamette. Whole raspberry fruits were dried convectively (air-drying), osmotically, and freeze-dried. Acetone-water extracts of fresh and dried raspberries were assessed for total phenolic content by standard Folin-Ciocalteau method. Two AO assays were applied, a recently developed direct current (DC) polarographic assay based on decrease of anodic oxidation current of hydrogen peroxide and widely used radical scavenge against the 1,1-diphenyl-2-picrylhydrazyl (DPPH). Strong correlation has been obtained between both AO assays and total phenolic content. In addition, some individual phenolic compounds present in raspberry have been assessed using DPPH and DC polarographic assay. Comparison and evaluation of drying methods has been based on preservation of AO activity and total phenolic content. Obtained results confirmed superiority of freeze-drying; convective drying caused slight changes while osmotic dehydration showed a significant decrease of phenolic compounds and AO activity.