A Reactionary obstacle avoidance algorithm for autonomous vehicles

Download
2012
Yücel, Gizem
This thesis focuses on the development of guidance algorithms in order to avoid a prescribed obstacle primarily using the Collision Cone Method (CCM). The Collision Cone Method is a geometric approach to obstacle avoidance, which forms an avoidance zone around the obstacles for the vehicle to pass the obstacle around this zone. The method is reactive as it helps to avoid the pop-up obstacles as well as the known obstacles and local as it passes the obstacles and continue to the prescribed trajectory. The algorithm is first developed for a 2D (planar) avoidance in 3D environment and then extended for 3D scenarios. The algorithm is formed for the optimized CCM as well. The avoidance zone radius and velocity are optimized using constraint optimization, Lagrange multipliers with Karush-Kuhn-Tucker conditions and direct experimentation.

Suggestions

Ability to forecast unsteady aerodynamic forces of flapping airfoils by artificial neural network
Kurtuluş, Dilek Funda (Springer Science and Business Media LLC, 2009-05-01)
The ability of artificial neural networks (ANN) to model the unsteady aerodynamic force coefficients of flapping motion kinematics has been studied. A neural networks model was developed based on multi-layer perception (MLP) networks and the Levenberg-Marquardt optimization algorithm. The flapping kinematics data were divided into two groups for the training and the prediction test of the ANN model. The training phase led to a very satisfactory calibration of the ANN model. The attempt to predict aerodynami...
A Model for Vertical-to-Horizontal Response Spectral Ratios for Europe and the Middle East
Bommer, Julian J.; Akkar, Dede Sinan; Kale, Ozkan (2011-08-01)
In the framework of probabilistic seismic hazard analysis, the preferred approach for obtaining the response spectrum of the vertical component of motion is to scale the horizontal spectrum by vertical-to-horizontal (V/H) spectral ratios. In order to apply these ratios to scenario or conditional mean spectra, the V/H ratios need to be defined as a function of variables such as magnitude, distance, and site classification. A new model for the prediction of V/H ratios for peak ground acceleration and spectral...
A stochastic gradient algorithm with momentum terms for optimal control problems governed by a convection–diffusion equation with random diffusivity
Toraman, Sıtkı Can; Yücel, Hamdullah (2023-04-01)
In this paper, we focus on a numerical investigation of a strongly convex and smooth optimization problem subject to a convection–diffusion equation with uncertain terms. Our approach is based on stochastic approximation where true gradient is replaced by a stochastic ones with suitable momentum term to minimize the objective functional containing random terms. A full error analysis including Monte Carlo, finite element, and stochastic momentum gradient iteration errors is done. Numerical examples are prese...
A new modal superposition method for nonlinear vibration analysis of structures using hybrid mode shapes
Ferhatoglu, Erhan; Ciğeroğlu, Ender; Özgüven, Hasan Nevzat (Elsevier BV, 2018-07-01)
In this paper, a new modal superposition method based on a hybrid mode shape concept is developed for the determination of steady state vibration response of nonlinear structures. The method is developed specifically for systems having nonlinearities where the stiffness of the system may take different limiting values. Stiffness variation of these nonlinear systems enables one to define different linear systems corresponding to each value of the limiting equivalent stiffness. Moreover, the response of the n...
Development of an intelligent model prediction controller for autonomous helicopters
Kubali, Şevket Eser; Yavrucuk, İlkay; Department of Aerospace Engineering (2016)
In this thesis, a new PID gain update law using linear least squares regression is introduced as an adaptive control method for autonomous helicopters. In addition, future prediction analyses are conducted for error dynamics of the closed loop system using recursive linear least squares regression. Combining these two concepts with classical PID controller, an intelligent PID controller is obtained. On the other hand, using PID controllers, a flight controller with three control loops is developed to demons...
Citation Formats
G. Yücel, “A Reactionary obstacle avoidance algorithm for autonomous vehicles,” M.S. - Master of Science, Middle East Technical University, 2012.