Ioannis K. Nikolos

Evolutionary algorithm based offline/online path planner for UAV navigation

An evolutionary algorithm based framework, a combination of modified breeder genetic algorithms incorporating characteristics of classic genetic algorithms, is utilized to design an offline/online path planner for unmanned aerial vehicles (UAVs) autonomous navigation. The path planner calculates a curved path line with desired characteristics in a three-dimensional (3-D) rough terrain environment, represented using B-spline curves, with the coordinates of its control points being the evolutionary algorithm artificial chromosome genes. Given a 3-D rough environment and assuming flight envelope restrictions, two problems are solved: i) UAV navigation using an offline planner in a known environment, and, ii) UAV navigation using an online planner in a completely unknown environment. The offline planner produces a single B-Spline curve that connects the starting and target points with a predefined initial direction. The online planner, based on the offline one, is given on-board radar readings which gradually produces a smooth 3-D trajectory aiming at reaching a predetermined target in an unknown environment; the produced trajectory consists of smaller B-spline curves smoothly connected with each other. Both planners have been tested under different scenarios, and they have been proven effective in guiding an UAV to its final destination, providing near-optimal curved paths quickly and efficiently.

Coordinated UAV Path Planning Using Differential Evolution

A differential evolution based framework is utilized to design an off-line path planner for unmanned aerial vehicles (UAVs) coordinated navigation in known static maritime environments. Considering the problem of having a number of UAVs starting from different known initial locations, the issue is to produce 2-D trajectories, formed by successive way-points, with a desirable velocity distribution along each trajectory, aiming at reaching a predetermined target location, while ensuring collision avoidance either with the environmental obstacles or with the UAVs and satisfying specific route and coordination constraints and objectives. The constraints are imposed in order to maximize the probabilities of UAVs survival and mission accomplishment

Computational benefits using artificial intelligent methodologies for the solution of an environmental design problem: saltwater intrusion

Artificial Neural Networks (ANNs) comprise a powerful tool to approximate the complicated behavior and response of physical systems allowing considerable reduction in computation time during time-consuming optimization runs. In this work, a Radial Basis Function Artificial Neural Network (RBFN) is combined with a Differential Evolution (DE) algorithm to solve a water resources management problem, using an optimization procedure. The objective of the optimization scheme is to cover the daily water demand on the coastal aquifer east of the city of Heraklion, Crete, without reducing the subsurface water quality due to seawater intrusion. The RBFN is utilized as an on-line surrogate model to approximate the behavior of the aquifer and to replace some of the costly evaluations of an accurate numerical simulation model which solves the subsurface water flow differential equations. The RBFN is used as a local approximation model in such a way as to maintain the robustness of the DE algorithm. The results of this procedure are compared to the corresponding results obtained by using the Simplex method and by using the DE procedure without the surrogate model. As it is demonstrated, the use of the surrogate model accelerates the convergence of the DE optimization procedure and additionally provides a better solution at the same number of exact evaluations, compared to the original DE algorithm.

Macroscopic traffic flow modeling with adaptive cruise control

The incorporation of two macroscopic approaches reflecting Adaptive Cruise Control (ACC) and Cooperative Adaptive Cruise Control (CACC) traffic dynamics in a gas-kinetic (GKT) traffic flow model is presented. The first approach was recently analyzed in the literature aiming to describe the effects induced by the ACC and CACC systems due to changes of the speed of the leading car(s) by the introduction of an acceleration/deceleration term. The second approach is a novel one and is based on the introduction of a relaxation term that satisfies the time/space-gap principle of ACC or CACC systems. In both approaches, the relaxation time is assigned on multiple leading vehicles in the CACC case; whereas in the ACC case this relaxation time is only assigned to the direct leading vehicle. We numerically approximate the resulting models by an accurate and robust high-resolution finite volume relaxation scheme, where the nonlinear system of partial differential equations is first recast to a diagonalizable semi-linear system and is then discretized by a higher-order WENO scheme. Numerical simulations investigate the effect of the different ACC and CACC approaches to traffic flow macroscopic stability with respect to perturbations introduced in a ring road and to flow characteristics in open freeways with merging flows at an on-ramp. Following from the numerical results, it can be concluded that CACC vehicles increase the stabilization of traffic flow, with respect to both small and large perturbations, compared to ACC ones. Further, the proposed CACC approach can better improve the dynamic equilibrium capacity and traffic dynamics, especially at the on-ramp bottleneck. A novel macroscopic modeling approach for Adaptive Cruise Control (ACC) in traffic flow dynamics.The proposed model is incorporated to a gas-kinetic (GKT) traffic flow model.A comparison with an alternative approach from the literature is performed.A high-resolution relaxation finite volume discretization (in space and time) is implemented.

Freeform Deformation Versus B-Spline Representation in Inverse Airfoil Design

Freeform deformation (FFD) is a well established technique for 3D animation applications, used to deform two—or three-dimensional geometrical entities. Over the past few years, FFD technique has aroused growing interest in several scientific communities. In this work, an extensive bibliographic survey of the FFD technique is initially introduced, in order to explore its capabilities in shape parametrization. Moreover, FFD technique is compared to the classical parametrization technique using B-spline curves, in the context of the airfoil design optimization problem, by performing inverse airfoil design tests, with a differential evolution algorithm to serve as the optimizer. The criterion of the comparison between the two techniques is the achieved accuracy in the approximation of the reference pressure distribution. Experiments are presented, comparing FFD to B-spline techniques under the same flow conditions, for various numbers of design variables. Sensitivity analysis is applied for providing further insight into the differences in the performance of the two techniques.

Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization

Abstract Artificial neural networks (ANNs) have recently been used to predict the hydraulic head in well locations. In the present work, the particle swarm optimization (PSO) algorithm was used to train a feed-forward multi-layer ANN for the simulation of hydraulic head change at an observation well in the region of Agia, Chania, Greece. Three variants of the PSO algorithm were considered, the classic one with inertia weight improvement, PSO with time varying acceleration coefficients (PSO-TVAC) and global best PSO (GLBest-PSO). The best performance was achieved by GLBest-PSO when implemented using field data from the region of interest, providing improved training results compared to the back-propagation training algorithm. The trained ANN was subsequently used for mid-term prediction of the hydraulic head, as well as for the study of three climate change scenarios. Data time series were created using a stochastic weather generator, and the scenarios were examined for the period 2010–2020. Editor Z.W. Kundzewicz; Associate editor L. See Citation Tapoglou, E., Trichakis, I.C., Dokou, Z., Nikolos, I.K., and Karatzas, G.P., 2014. Groundwater-level forecasting under climate change scenarios using an artificial neural network trained with particle swarm optimization. Hydrological Sciences Journal, 59(6), 1225–1239. http://dx.doi.org/10.1080/02626667.2013.838005

Using the Finite-Volume Method and Hybrid Unstructured Meshes to Compute Radiative Heat Transfer in 3-D Geometries

In this work an algorithm using the finite-volume method is presented for the parallelized computation of radiative heat transfer for absorbing, emitting, and either isotropically or anisotropically scattering gray media. Attention is mainly toward the extension of the finite-volume methodology to hybrid unstructured meshes, using a node-centered median-dual approach, with highly stretched elements at the solid wall regions, and the evaluation of its effectiveness and accuracy in such girds. As the parallelized calculation and the utilization of hybrid meshes are not common, results of the present algorithm against benchmark problems are used to demonstrate their equal potential.

A software tool for generic parameterized aircraft design

Abstract In this work a surface generation software named Ge.P.A.S. (for generic parameterized aircraft surface) is presented, designed for the construction of aircraft aerodynamic surfaces. The surface generation procedure is parameterized and different aircraft configurations can be produced in an interactive way. A hierarchical structure of geometric parameters was adopted, resulting in easier manipulation of the shape and a scalable number of control parameters. Additionally, the geometric parameters may serve as design optimization variables in cooperation with an external optimizer. The surface generation is based on the use of NURBS curves and surfaces, which provide the ability to produce complicated geometries with a relative small number of design variables. Standard or user-defined airfoil sections can be used for the wing generation. The surface description is compatible with international input/output standards; IGES and STEP formats are supported for the output files. Consequently, Ge.P.A.S. can serve as a preprocessor for other software packages, which may be used in order to refine the geometry or to generate the grid for numerical simulations. The geometric algorithms, the software features and its basic characteristics are presented in this paper, along with a demonstration of its abilities in sample aircraft configurations.

Path Planning for Cooperating Unmanned Vehicles over 3-D Terrain

In this paper we suggest an off-line/on-line path planner for cooperating unmanned vehicles that takes into account the mission objectives and constraints through an optimization procedure. The cooperating vehicles can be either Unmanned Aerial Vehicles (UAVs) or Autonomous Underwater Vehicles (AUVs); these two categories of vehicles share common features as far as path planning is concerned and these features are used in this work for the development of a unified approach to the path planning problem over 3-D terrains. A number of unmanned vehicles of the same category are launched from the same or different known initial locations. The main issue is to produce 3-D trajectories (represented by 3-D B-Spline curves) that ensure a collision free path, respect the mission objectives and constraints, and guide the vehicles to a common final destination. The off-line planner is designed for known environments. The on-line one generates paths in unknown static environments, by exchanging acquired information from the cooperating vehicles’ on-board sensors. For each vehicle a near optimum path is generated that guides it safely to an intermediate position within the already scanned area. The process is repeated for each vehicle until the final destination is reached by one or more members of the team. Then, each one of the remaining vehicles can either turn into the off-line mode to reach the target, moving through the already scanned area, or continue with the on-line mode. Both off-line and on-line path planning problems are formulated as optimization problems, and a Differential Evolution algorithm is used as the optimizer.

Coordinated UAV path planning using Differential Evolution

A Differential Evolution based framework is utilized to design an offline path planner for Unmanned Aerial Vehicles (UAVs) coordinated navigation in known static maritime environments. Considering the problem of having a number of UAVs starting from different known initial locations, the issue is to produce 2-D trajectories, formed by successive way-points, with a desirable velocity distribution along each trajectory, aiming at reaching a predetermined target location, while ensuring collision avoidance either with the environmental obstacles or with the UAVs and satisfying specific route and coordination constraints and objectives. The constraints are imposed in order to maximize the probabilities of UAVs survival and mission accomplishment.