Vladimir Popov

The Problem of Selection of Fingerprints for Topological Localization

Visual navigation is extensively used in contemporary robotics. In particular, we can mention different systems of visual landmarks. In this paper, we consider one-dimensional color panoramas. Panoramas can be used for creating fingerprints. Fingerprints give us unique identifiers for visually distinct locations by recovering statistically significant features. Fingerprints can be used as visual landmarks for mobile robot navigation. In this paper, we consider a method for automatic generation of fingerprints. Since a fingerprint is a circular string, different string-matching algorithms can be used for selection of fingerprints. In particular, we consider the problem of finding the consensus of circular strings under the Hamming distance metric.

On Starting Population Selection for GSAT

GSAT is a well-known satisfiability search algorithm for conjunctive normal forms. GSAT uses some random functions. One of such functions is a function of starting population of truth assignments for the variables of conjunctive normal form. In this paper, we consider a method of artificial physics optimization for computing a function of starting population.

Particle Swarm Optimization Technique for Task-Resource Scheduling for Robotic Clouds

The task-resource scheduling problem is one of the fundamental problems for cloud computing. There are a large number of heuristics based approaches to various scheduling workflow applications. In this paper, we consider the problem for robotic clouds. We propose new method of selection of parameters of a particle swarm optimization algorithm for solution of the task-resource scheduling problem for robotic clouds. In particular, for the prediction of values of the inertia weight we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural networks with gradient learning algorithm, and 4-order Runge Kutta neural networks with different learning algorithms. Also, we present experimental results for different intelligent algorithms.

Self-Learning of Robots and the Model of Hamiltonian Path with Fixed Number of Color Repetitions for Systems of Scenarios Creation

In this paper, we propose a system of scenarios creation for self-learning of intelligent mobile robots. This model is based on the model of Hamiltonian path with fixed number of color repetitions for c-arc-colored digraphs. We show that the problem of Hamiltonian path with fixed number of color repetitions for c-arc-colored digraphs is NP-complete. We consider an approach to solve the problem. This approach is based on an explicit reduction from the problem to the satisfiability problem.

Reduction of the uncertainty in feature tracking

It is difficult to establish feature correspondences between distant viewpoints for panoramic images. For reliable navigation and development a human-like capability of interaction with the surrounding environment, we need a method of reduction of the uncertainty in feature tracking. To obtain a method of reduction of the uncertainty in feature tracking, we propose to use an algorithm for the problem of the longest common subsequence for a set of circular strings. We consider an explicit reduction from the problem of the longest common subsequence for a set of circular strings to the satisfiability problem. This reduction allows to obtain an efficient algorithm for finding the longest common subsequence for a set of circular strings. We present a general scheme of the method of reduction of the uncertainty in feature tracking. We considered the visual homing task to demonstrate the capabilities of our approach to solve the problem of reduction of the uncertainty in feature tracking. We present experimental results for the method of reduction of the uncertainty in feature tracking and novel robot visual homing methods.

Avoidance of Forbidden DNA Nanorobots Configurations in Patterned Immobilization of other Materials

DNA nanorobots can be applied for patterned immobilization of other materials. However, for successful patterned immobilization, we need to design the self-organization process so that some shapes of DNA nanostructures are avoided. In this paper, we consider an approach to solve the problem of the avoidance of forbidden shapes of DNA nanorobots in patterned immobilization of other materials.

An Approach to Design of DNA Smart Programmable Membranes

DNA molecules can be considered as a smart material. In particular, synthetic DNA can reliably self-organize. In this paper, we consider an approach to design of active DNA membranes with two stable states. Our approach is based on the usage of SAT-solvers to find proper set of DNA tiles.

Particle Swarm Optimization Technique for DNA Sensor Model Based Nanostructured Graphene

DNA biosensors has received significant attention. In particular, we can mention the model of a graphene-based DNA sensor which is used for electrical detection of DNA molecules. In this paper, we consider a method of selection of PSO parameters for optimization of the analytical model of a graphene-based DNA sensor. In particular, we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural networks with gradient learning algorithm, and 4-order Runge Kutta neural networks with different learning algorithms. Also, we present experimental results for different intelligent algorithms.

Anticipation in Robot Navigation and Mining for Intresting Patterns

We consider robot self-awareness from the point of view of temporal relation based data mining. We consider the problem of mining for intresting patterns. In particular, we study the longest common subsequence over the set problem.

Building the Panoramic Image for Mobile Robot Localization

Visual landmarks are extensively used in contemporary robotics. There are a large number of different systems of visual landmarks. In particular, fingerprints give us unique identifiers for visually distinct locations by recovering statistically significant features. Therefore, fingerprints can be used as visual landmarks for mobile robot navigation. To create fingerprints we need one-dimensional color panoramas of high quality. In this paper, we consider a method for building the panoramic image using string matching algorithms. In particular, we propose the shortest common ordered supersequence problem.