Files in this item

FilesDescriptionFormat

application/pdf

application/pdfAMROUCHE-DISSERTATION-2021.pdf (7MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Vision-based dynamical systems and learning
Author(s):Amrouche, Massinissa
Director of Research:Stipanovic, Dusan
Doctoral Committee Chair(s):Stipanovic, Dusan
Doctoral Committee Member(s):Hovakimyan, Naira; Sreenivas, Ramavarapu; Beck, Carolyn
Department / Program:Industrial&Enterprise Sys Eng
Discipline:Systems & Entrepreneurial Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Control Theory, Vision Collision Avoidance, Dynamical Systems, Machine Learning, Deep neural networks
Abstract:Nowadays, it is widely recognized that autonomous robots are “intelligent” machines, capable of performing complex tasks in a dynamical environment without explicit human intervention. Moreover, these tasks are performed while ensuring safe interactions between human and robots. Hence, ensuring Collision Avoidance is critical in designing any autonomous system. Concretely, most collision avoidance systems in mobile robots rely heavily on a computer vision machinery that provides the necessary feedback to the decision making and control units. In recent years, the advances in both machine learning algorithms and computer hardware have led to more wide application of deep neural networks in computer vision. The first part of this thesis focuses on providing methodologies for designing control strategies that guarantee collision avoidance for multi-agent systems without any information about the relative distances among the agents. The controllers are designed such that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically they rely solely on the visual information, that is, times-to-collision and line-of-sight angle. These methods are particularly suitable to low-cost and/or small robotic systems that are not equipped with range measurement devices like radars and LIDARs. Furthermore, the collision avoidance is guaranteed using Lyapunov analysis type of technical arguments and illustrated using simulations. In the second part of this dissertation, a formal methodology for describing and designing activation functions in deep neural networks, is provided. The methodology is based on a precise characterization of the desired activation functions that satisfy particular criteria like circumventing vanishing or exploding gradient during training. The problem of finding desired activation functions is formulated as an infinite dimensional optimization problem, which is later relaxed to solving a partial differential equation. Furthermore, bounds that guarantee optimality of the designed activation function are provided. Finally, some examples are provided to illustrate the methodology, where some state-of-the-art activation functions are derived analytically.
Issue Date:2021-07-12
Type:Thesis
URI:http://hdl.handle.net/2142/113161
Rights Information:Copyright 2021 Massinissa Amrouche
Date Available in IDEALS:2022-01-12
Date Deposited:2021-08


This item appears in the following Collection(s)

Item Statistics