Vitalijs Komasilovs

Functional decomposition method reveals the number of possible specifications of multi-robot system

Number of robot classes in heterogeneous multi-robot systems refers to the number of different robot types in the system, where their members differ from others by any of features like mechanics, sensing or processing hardware, or by internal control architecture. The number of robot classes used for particular task, as well as the specification of functions for each class of robots is usually predefined and are not considered in scope of optimization. However in most cases such assumption is not verified by any calculations and alternative configurations of multi-robot system are not reviewed and evaluated. As a result, application of multi-robot system is impaired and may be economically ineffective. We propose a formal approach, based on decomposition of functional requirements, which can be used to determine the optimal configuration of multi-robot system for particular problem. The analysis of complexity of this problem is presented in this paper.

Specification development of robotic system for pesticide spraying in greenhouse

Robotic systems are replacing humans in increasing number of dangerous tasks. Pesticide spraying in greenhouses is one of tasks where a number of robotic systems have been developed and tested. Therefore it is the right time to raise the question about optimisation of the costs efficiency of robot colony. In case of homogenous robotic system only the number of universal robots has to be determined. The drawback is that some subsystems (vision, spraying) might be utilised at a very low rate and the investment may be inefficient. To avoid that it is possible to design a heterogeneous robotic system where the solution space of a robotic system specification is large and optimisation task becomes very complex. Still a good solution can reduce costs. Optimisation of specification of heterogeneous robotic system for pesticide spraying (plant inspection, spraying and pesticide transport functions) in a greenhouse with rectangular layout is performed using genetic algorithms and corresponding open source GAMBot-Eva software. Optimisation results demonstrate three groups of solutions that are within 3% range of lowest possible costs: 1) homogeneous system of universal robots, 2) heterogeneous system with two types of robots (inspection-spraying robots and spraying-transportation robots) and 3) heterogeneous system with two types of robots without duplicating functions (inspection-spraying robots and transportation robots). Applied optimisation approach can be adapted for different robot missions.

Procedure of specification optimization of heterogeneous robotic system

Economic benefit of an industrial company depends on forethought deployment of an industrial production system. Robotic systems are used to increase effectiveness of the production system providing variety of automation approaches. The selection of robotic system for particular mission is considered based on options available on the market. The analysis on more detailed level opens opportunity to find better solutions within the domain of heterogeneous robot systems. Authors propose a functional decomposition method that allows the optimization of specification of heterogeneous multi robot system according to defined objective function. Paper describes steps of optimization procedure and provides analysis of practical example. Achieved results are used in development of solution evaluation method using heuristic algorithms. The framework for finding best configuration of the heterogeneous multi-robot system is provided by specification optimization procedure.

Model-based metabolism design: constraints for kinetic and stoichiometric models

The implementation of model-based designs in metabolic engineering and synthetic biology may fail. One of the reasons for this failure is that only a part of the real-world complexity is included in models. Still, some knowledge can be simplified and taken into account in the form of optimization constraints to improve the feasibility of model-based designs of metabolic pathways in organisms. Some constraints (mass balance, energy balance, and steady-state assumption) serve as a basis for many modelling approaches. There are others (total enzyme activity constraint and homeostatic constraint) proposed decades ago, but which are frequently ignored in design development. Several new approaches of cellular analysis have made possible the application of constraints like cell size, surface, and resource balance. Constraints for kinetic and stoichiometric models are grouped according to their applicability preconditions in (1) general constraints, (2) organism-level constraints, and (3) experiment-level constraints. General constraints are universal and are applicable for any system. Organism-level constraints are applicable for biological systems and usually are organism-specific, but these constraints can be applied without information about experimental conditions. To apply experimental-level constraints, peculiarities of the organism and the experimental set-up have to be taken into account to calculate the values of constraints. The limitations of applicability of particular constraints for kinetic and stoichiometric models are addressed.

Autoregressive dynamic mechanism for urban area microscopic traffic flow models

To study traffic congestion, city routing, intersection control, emergency cases, or other types of scenarios it is necessary to have an accurate traffic flow model. Traffic models are comprised of different mechanisms that give it its realism. In this work two basic mechanisms are studied: the dynamic movement of the vehicle and a cautious car-following behavior. The dynamic movement of the vehicle is dependent on an autoregressive acceleration algorithm, which gives the vehicle an innate fluid motion. The model also considers a cautious car-following mechanism, where the vehicle decelerates if a safe distance threshold is crossed and the lagging vehicle is traveling faster. Additionally, using the described model, we performed a study to observe the impact of the standard deviation of the velocity on the overall average velocity. This deviation is caused by human reaction times, tiredness, distractions, etc. Therefore, these results reflect the human-driving efficiency.

Bus Arrival Time Prediction with Limited Data Set using Regression Models.

The increase of population has intensified everyday rush. Traffic congestions are still a problem in cities and are one of the main cause for public transport delays. City residents and visitors have experienced time loss by using public transport buses, because of waiting at the bus stops and not knowing if the bus is delayed or already serviced the stop. Therefore it is valuable for people to know at what time the bus should arrive (or is it already missed) at specific bus stop. Real-time public bus tracking and management system development has been the focus of many researchers, and many studies have been done in this area. This paper focuses on bus travel time prediction comparison between linear regression and support vector regression models (SVR), when using limited data set. Data were limited in a way that only historical GPS (Global Positioning System) coordinates of bus location (recorded each 30 seconds) and driven distance were used, there were no information about arrival/departure times, delays or dwell times. Distance between stops and delay (assumed values based on route observations by authors) were used as inputs for both models. It was concluded that SVR algorithm showed better results, but the difference was not significantly large.

Enhancing with EV Charging Station Functions a Residential RES based Network.

The emergence of Electric Vehicles is creating a possible congestion of the electric grid. The switch in transportation, especially in cities (future Smart Cities are considered) is asking for the utilization of Renewable Energy Sources, RES, to decrease pollution. To address these two demands the paper proposes a solution based on a Residential Charging station architecture for Urban Electric Vehicles. The theoretical structure is presented and then the practical solution, as Smart Residential MicroGrid based on RES, is shown. In order to make an implementation more economically and technically affordable and be able to address in the very near future the growing need of EV Charging stations, the presented solution starts from the existing equipment used in millions of homes, mainly for solar energy.

Traffic Monitoring System Development in Jelgava City, Latvia.

Smart traffic management and monitoring is one of the key aspects of the modern smart city. Traffic flow estimation is crucial for sustainable traffic planning in the city. A requirement for successful planning and optimization of traffic is vehicle counting on the streets. Surveillance video is a suitable data source for precise vehicle counting. A solution for real-time vehicle traffic monitoring, tracking and counting is proposed in Jelgava city, Latvia. It is based on motion detection using background modeling, which is enhanced by statistical analysis. Two-phase assessment is utilized: motion blobs are detected and tracked using custom state machine implementation, then tracking results are passed through number of statistical filters to eliminate false positive detections. The system demonstrates good performance and acceptable accuracy on given test cases (about 97% accuracy for regular traffic conditions).

Development of the Web Platform for Management of Smart Charging Stations for Electric Vehicles.

Shortage of fossil fuels and ecological thinking leads to shift in technologies for vehicle production. In the future only electric vehicles (EVs) would be produced. This will lead to huge increase in number of EVs worldwide, so it would be crucial to provide a broad public charging infrastructure. This paper exactly concentrates on the essential role of infrastructure in the mass implementation of electric vehicles. A focus is placed on sharing the residential infrastructure for public usage. Paper describes authors developed Web platform for sharing the information about privately owned charging stations, describing the additional option to link station hardware with software for real-time charging data and station availability updates. Developed platform brings together drivers of EVs and owners of the infrastructure. Developed platform is built like an interactive map, based on Google Maps service. Together with software part, authors developed also hardware, which is one Microgrid based on renewable energy sources with EV charging station functionality.

Implementation of Smart Parking Solution by Image Analysis.

Modern smart city concept implies various smart aspects including smart parking management. Searching for a free parking lot can be a challenging task, especially during major events, therefore automatic system, which will help drivers to find a free parking is very valuable. There are many intrusive and non-intrusive technologies available for smart parking development, but authors of this paper developed a system based on video processing and analysis. Authors developed Python application for real-time parking lot monitoring based on video analysis of public video stream. Five classifier models (Logistic Regression, Linear Support Vector Machine, Radial Basis Function Support Vector Machine, Decision Tree and Random Forest) were compared for parking lot occupancy detection. Logistic regression classifier showed better results and was chosen for real-time parking monitoring application. System shows good performance and correctly predicted parking lot occupancy almost in all test cases.