Emil Petriu

Emil Petriu
University of Ottawa · School of Electrical Engineering and Computer Science

About

654
Publications
85,048
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
8,454
Citations

Publications

Publications (654)
Article
Full-text available
Identifying objects during the early phases of robotic grasping in unstructured environments is a crucial step toward successful dexterous robotic manipulation. Underactuated hands are versatile and quickly conform to unknown object surfaces to ensure a firm grasp. The trade-off of using such hands is that extracting information and recognizing obj...
Article
This paper proposes two nonlinear estimation approaches, namely based on Extended Kalman Filter (EKF) and a Takagi-Sugeno Fuzzy Observer with 32 rules (TSFO-32), for a Strip Winding System (SWS) characterized by variable reference input, variable moment of inertia with constant increasing tendency and variable parameters. The SWS is a complex and n...
Article
Servo systems become more and more important in control systems applications in various fields as both separate control systems and actuators. Ensuring very good control system performance using few information on the servo system model (viewed as a controlled process) is a challenging task. Starting with authors’ results on data-driven model-free...
Article
This paper proposes validates an Iterative Feedback Tuning (IFT) algorithm, which is a classical and also popular data-driven algorithm, on tower crane systems. The IFT algorithm is applied to improve the performances of three proportional-integral (PI) controllers by solving an optimization problem. The IFT algorithm is validated using experiments...
Article
The purpose of this paper is to design the optimal controllers for nonlinear processes with Shape Memory Alloy (SMA) wire actuators viewed as controlled processes. Optimal process models are first derived. A comparative analysis is done between the evolved Takagi-Sugeno-Kang (TSK) fuzzy models of SMA wire actuators, two linear dynamic system models...
Article
This paper presents a novel Reinforcement Learning (RL)-based control approach that uses a combination of a Deep Q-Learning (DQL) algorithm and a metaheuristic Gravitational Search Algorithm (GSA). The GSA is employed to initialize the weights and the biases of the Neural Network (NN) involved in DQL in order to avoid the instability, which is the...
Article
This paper presents a new Reinforcement Learning (RL)-based control approach that uses the Policy Iteration (PI) and a metaheuristic Grey Wolf Optimizer (GWO) algorithm to train the Neural Networks (NNs). Due to an efficient tradeoff to exploration and exploitation, the GWO algorithm shows good results in NN training and solving complex optimizatio...
Article
This paper presents a novel application of the metaheuristic Slime Mould Algorithm (SMA) to the optimal tuning of interval type-2 fuzzy controllers. Inserting the information feedback model F1 in SMA leads to a new version of the metaheuristic algorithm, further referred to as SMAF1. The paper discusses implementation details specific to interval t...
Article
Full-text available
The novel coronavirus SARS-CoV-2 that causes the disease COVID-19 has forced us to go into our homes and limit our physical interactions with others. Economies around the world have come to a halt, with non-essential businesses being forced to close in order to prevent further propagation of the virus. Developing countries are having more difficult...
Chapter
This paper proposes two applications of nature-inspired optimization algorithms (NIOAs) to solve a path planning problem and the optimal tuning of Proportional-Integral (PI)-fuzzy controllers as tracking controllers for nonholonomic wheeled mobile robots in static environments. Two optimization problems are solved by NIOAs and included first in an...
Article
The paper presents the application of the tensor product (TP)‐based model transformation technique to model and control the cart position of single‐input multi‐output pendulum‐cart systems (PCSs). The modeling is first carried out. The derived TP model, the nonlinear model of PCS, and the laboratory equipment are tested in the same open‐loop scenar...
Article
This paper presents the application of the tensor product (TP)‐based model transformation approach to produce Tower CRrane (TCR) systems models. The modeling approach starts with a nonlinear model of TCR systems as representative multi‐input–multi‐output controlled processes. A linear parameter‐varying model is next derived, and the modeling steps...
Article
Full-text available
This paper suggests five new contributions with respect to the state-of-the-art. First, the optimal tuning of cost-effective fuzzy controllers represented by Takagi–Sugeno–Kang proportional-integral fuzzy controllers (TSK PI-FCs) is carried out using a fresh metaheuristic algorithm, namely the Slime Mould Algorithm (SMA), and a fuzzy controller tun...
Article
This paper proposes an approach to the tuning of model-free controllers for the midcarpal joint angles, which are important finger angles that ensure the desired finger dynamics in prosthetic hand myoelectric-based control systems. The process in these control systems is characterized by fuzzy models that operate with myoelectric signals obtained f...
Conference Paper
The findings of this paper enhance the knowledge of machine learning in tactile texture recognition. Synthetic perception of textures was achieved using a recently developed miniaturized multi-modal tactile sensor. Thirteen commonly used textures were dynamically explored and classified using supervised learning classifiers. The best result was ach...
Chapter
Fast and accurate detection of objects, in 3D, is one of the critical components in an advanced driver assistance system. In this paper, we aim to develop an accurate 3D object detector that runs in near real-time on low-end embedded systems. We propose an efficient framework that converts raw point cloud into a 3D occupancy cuboid and detects cars...
Article
The paper presents the combination of the model-free control technique with two popular nonlinear control techniques, sliding mode control and fuzzy control. Two data-driven model-free sliding mode control structures and one data-driven model-free fuzzy control structure are given. The data-driven model-free sliding mode control structures are buil...
Article
This paper presents a real time system, which includes detecting and tracking bare hand in cluttered background using skin detection and hand postures contours comparison algorithm after face subtraction, and recognizing hand gestures using Principle Components Analysis (PCA). In the training stage, a set of hand postures images with different scal...
Article
This paper discusses the use of the Scale Invariance Feature Transform (SIFT) features for bare hand gesture recognition. In the training stage, we can not use SIFT keypoints of training images directly with a multi-class Support Vector Machine (SVM) to build a training classifier model, because of the space incompatibility of the SIFT keypoints fo...
Article
This paper proposes the Virtual Reference Feedback Tuning (VRFT) of a combination of two control algorithms, Active Disturbance Rejection Control (ADRC) as a representative data-driven (or model-free) control algorithm and fuzzy control, in order to exploit the advantages of data-driven control and fuzzy control. The combination of Active Disturban...
Article
This article proposes an approach based on experiments to teach optimization technique (OT) courses in the Systems Engineering curricula at undergraduate level. Artificial intelligence techniques in terms of nature-inspired optimization algorithms and neural networks are inserted in the lecture and laboratory parts of the syllabus. The experiments...
Article
The aim of this paper is to propose a stability analysis approach based on the application of the center manifold theory and applied to state feedback Takagi-Sugeno-Kang fuzzy control systems. The approach is built upon a similar approach developed for Mamdani fuzzy controllers. It starts with a linearized mathematical model of the process that is...
Article
In the past, hydraulic and structural design has predominantly relied on deterministic methods, often neglecting the stochastic nature that underlies transient loading processes. Nowadays, probabilistic design methods have gained wider attention. The accurate estimates of design conditions for structures must consider the probabilistic properties o...
Chapter
Monitoring the oceanographic activity of ships in restricted areas is an important task that can be done using sonar signals. To this end, a human expert may regularly analyze passive sonar signals to count the number of vessels in the region. To automate this process, we propose a deep neural network for counting the number of vessels using sonar...
Article
Full-text available
This paper proposes two applications of Grey Wolf Optimizer (GWO) algorithms to a path planning (PaPl) problem and a Proportional-Integral (PI)-fuzzy controller tuning problem. Both optimization problems solved by GWO algorithms are explained in detail. An off-line GWO-based PaPl approach for Nonholonomic Wheeled Mobile Robots (NWMRs) in static env...
Article
This paper applies an incremental online identification algorithm to develop a set of evolving fuzzy models (FMs) that characterize the nonlinear finger dynamics of the human hand for the myoelectric (ME)-based control of a prosthetic hand. FM inputs are ME signals obtained from eight ME sensors and past inputs and/or outputs. The FM outputs are th...
Article
Unscented Kalman Filter (UKF) is a technique used in non-linear applications and dynamic systems identification (e.g. tracking marine vessels and ships) that require state and parameter estimation. This paper studies Kalman Filter (KF) based techniques for tracking ships using Global Positioning System (GPS) data. The present work proposes to explo...
Article
Video footage from the 2004 Indian Ocean and 2011 Tohoku tsunamis showed large quantities of debris entrained within the inundating flows. Such extreme debris conditions can lead to a high probability for multiple impacts on structures particularly in built-in coastal communities. In the current North American design guidelines and standards, commo...
Conference Paper
Full-text available
Tactile sensing is the foundation of interaction within the environment. Tactile systems are used to gather information from its surroundings. This research contribution is to present a new feature of a recently proposed multimodal tactile sensor. Data acquisition was conducted by the Robotic Operating System (ROS) and data processing used a Smooth...
Conference Paper
Full-text available
A new framework¹ mixing evolutionary approach, discrete-event simulation and deep neural networks is proposed to achieve multi-asset collection/image acquisition scheduling in a surveillance context. It combines an extended graph-based hybrid genetic algorithm (GA) used for satellite image acquisition scheduling, with a predictive simulation-based...
Conference Paper
A new approach to the in-hand manipulation problem, using fuzzy controlled teleoperation and a recently proposed multimodal tactile sensor are presented in this article. Real-time grasping experiments were performed by a fuzzy controlled gripper, with a compliant tactile sensor mounted on the gripper. As a new approach for in-hand manipulation and...
Conference Paper
The paper presents a heart rate detection system using a novel miniaturized multimodal tactile sensor that emulates the four main mechanoreceptors – Meissner’s corpuscles, Merkel disks, Ruffini, and Pacinian corpuscles – of the human skin. A heart rate wrist monitor was used to validate the performance of the new proposed system. The experiment con...
Article
Full-text available
Underactuated hands are useful tools for robotic in-hand manipulation tasks due to their capability to seamlessly adapt to unknown objects. To enable robots using such hands to achieve and maintain stable grasping conditions even under external disturbances while keeping track of an in-hand object’s state requires learning object-tactile sensing da...
Article
Full-text available
In this paper a second-order data-driven Active Disturbance Rejection Control (ADRC) is merged with a proportional-derivative Takagi-Sugeno Fuzzy (PDTSF) logic controller, resulting in two new control structures referred to as second-order data-driven Active Disturbance Rejection Control combined with Proportional-Derivative Takagi-Sugeno Fuzzy Con...
Article
Debris loading has been identified during several forensic engineering field surveys in the aftermath of the 2004 Indian Ocean and 2011 Tohoku Japan tsunamis as a critical design load. However, little research has addressed the assessment of debris loading hazards. The study presented herein examines the entrainment and transport of debris over a 1...
Article
Full-text available
This paper develops an image processing based approach for classification of vehicles with the objective of their parking. In the paper, the heights and lengths of the vehicles are first measured on applying image processing and feature extraction techniques. Then, based on the information of the heights and lengths of the vehicles, the vehicles' e...
Article
Full-text available
Implementing aliasing-free (zero-aliasing) space compressors for built-in self-testing of very large scale integration circuits and systems is of great significance, especially in view of the technological paradigm shift in recent years from system-on-board to system-on-chip design. This paper investigates and provides new approach to realizing ali...
Conference Paper
Full-text available
Debris loading has been identified during several engineering field surveys in the aftermath of the 2004 and 2011 Tsunamis as a critical design load. However, little research has addressed the assessment of debris loading hazards. The study presented here examines the entrainment and transport of debris over a 1:10 sloped bed in tsunami-like condit...
Article
Field surveys of recent major flood events have emphasized the need for an in-depth examination of debris loading. Debris loading occurs when solid objects entrained within the flow interact with a structure in its movement path, exerting loads through direct impacts or damming. Until now, the focus of research into debris impacts has concentrated...
Chapter
This chapter uses genetic fuzzy systems (GFS) to assess the risk level of maritime vessels transmitting Automatic Identification System (AIS) data. Previous risk assessment approaches based on fuzzy inference systems (FIS) relied on domain experts to specify the FIS membership functions as well as the fuzzy rule base (FRB), a burdensome and time-co...
Presentation
Forensic engineering surveys of extreme flooding events, such as the 2011 Tohoku Tsunami and the 2012 Hurricane Katrina, demonstrated the importance of debris in estimating loading on structures. Debris are any solid objects entrained within the inundating flow. The resulting loads from these objects can be the result of debris damming, where debri...