Engineering Commons^™

A Study Of Deep Reinforcement Learning In Autonomous Racing Using Deepracer Car, Mukesh Ghimire

Honors Theses

Reinforcement learning is thought to be a promising branch of machine learning that has the potential to help us develop an Artificial General Intelligence (AGI) machine. Among the machine learning algorithms, primarily, supervised, semi supervised, unsupervised and reinforcement learning, reinforcement learning is different in a sense that it explores the environment without prior knowledge, and determines the optimal action. This study attempts to understand the concept behind reinforcement learning, the mathematics behind it and see it in action by deploying the trained model in Amazon's DeepRacer car. DeepRacer, a 1/18^th scaled autonomous car, is the agent which is trained …

Robot Object Detection And Locomotion Demonstration For Eecs Department Tours, Bryson Howell, Ethan Haworth, Chris Mobley, Ian Mulet

Chancellor’s Honors Program Projects

No abstract provided.

Path Planning With Deep Neural Networks, Paul Simmerling, Brendan Sayers, Paulo Alcantara Silva

Honors Scholar Theses

This report will cover the work and plans of the ECE 2107 Senior design team. The goal of the project is to design and build a fully autonomous self-driving car. This car will have a complete sensor suite including LIDAR, an IMU, a camera, and encoders. It will be based on a multi-level system where the highest level uses a neural network for advanced signal processing and analysis. The current state of the project is discussed as well as the final results. Project management and other constraints will be briefly investigated. This team is building a self driving car testbed …

Bibliometric Analysis On Hand Gesture Controlled Robot, Karthik Bankapur, Himmat Singh, Akshit Gupta, Hritik Mathur, Harikrishnan R, Shivali Amit Wagle

Library Philosophy and Practice (e-journal)

This paper discusses about the survey and bibliometric analysis of hand gesture-controlled robot using Scopus database in analyzing the research by area, influential authors, countries, institutions, and funding agencies. The 293 documents are extracted from the year 2016 till 6^th March 2021 from the database. Bibliometric analysis is the statistical analysis of the research published as articles, conference papers, and reviews, which helps in understanding the impact of publication in the research domain globally. The visualization analysis is done with open-source tools namely GPS Visualizer, Gephi, VOS viewer, and ScienceScape. The visualization aids in a quick and clear understanding …

Project Blipper, Peter Jacobs, Preston Delaware, Ryan Foster

Senior Design Project For Engineers

This project was sponsored by Clorox to design and create an automatic bottle-unscrambling system for possible implementation at their bottling plant in Chile. The objective was to use a robotic arm to unscramble bottles from an incoming conveyor belt and place them upright on an outbound conveyor belt. Throughout the research, design, and testing of solutions for this project, several design alternatives were found for each discipline, and will be presented to Clorox so that they can make an informed decision for how and if they want to move forward with implementation of this project.

The project was split into …

Owsnet: Towards Real-Time Offensive Words Spotting Network For Consumer Iot Devices, Bharath Sudharsan, Sweta Malik, Peter Corcoran, Pankesh Patel, John G. Breslin, Muhammad Intizar Ali

Publications

Every modern household owns at least a dozen of IoT devices like smart speakers, video doorbells, smartwatches, where most of them are equipped with a Keyword spotting(KWS) system-based digital voice assistant like Alexa. The state-of-the-art KWS systems require a large number of operations, higher computation, memory resources to show top performance. In this paper, in contrast to existing resource-demanding KWS systems, we propose a light-weight temporal convolution based KWS system named OWSNet, that can comfortably execute on a variety of IoT devices around us and can accurately spot multiple keywords in real-time without disturbing the device's routine functionalities.

When OWSNet …

Cognitive Digital Twins For Smart Manufacturing, Muhammad Intizar Ali, Pankesh Patel, John G. Breslin, Ramy Harik, Amit Sheth

Publications

Smart manufacturing or Industry 4.0, a trend initiated a decade ago, aims to revolutionize traditional manufacturing using technology-driven approaches. Modern digital technologies such as the Industrial Internet of Things (IIoT), Big Data Analytics, Augmented/Virtual Reality, and Artificial Intelligence (AI) are the key enablers of new smart manufacturing approaches. The digital twin is an emerging concept whereby a digital replica can be built of any physical object. Digital twins are becoming mainstream; many organizations have started to rely on digital twins to monitor, analyze, and simulate physical assets and processes. The current use of digital twins for smart manufacturing is largely …

Human-Machine Communication: Complete Volume. Volume 2

Human-Machine Communication

This is the complete volume of HMC Volume 2.

Social Robots As The Bride? Understanding The Construction Of Gender In A Japanese Social Robot Product, Jindong Liu

Human-Machine Communication

This study critically investigates the construction of gender on a Japanese hologram animestyle social robot Azuma Hikari. By applying a mixed method merging the visual semiotic method and heterogeneous engineering approach in software studies, the signs in Azuma Hikari’s anthropomorphized image and the interactivity enabled by the multimedia interface have been analyzed and discussed. The analysis revealed a stereotyped representation of a Japanese “ideal bride” who should be cute, sexy, comforting, good at housework, and subordinated to “Master”-like husband. Moreover, the device interface disciplines users to play the role of “wage earner” in the simulated marriage and reconstructs the gender …

Forms And Frames: Mind, Morality, And Trust In Robots Across Prototypical Interactions, Jaime Banks, Kevin Koban, Philippe De V. Chauveau

Human-Machine Communication

People often engage human-interaction schemas in human-robot interactions, so notions of prototypicality are useful in examining how interactions’ formal features shape perceptions of social robots. We argue for a typology of three higher-order interaction forms (social, task, play) comprising identifiable-but-variable patterns in agents, content, structures, outcomes, context, norms. From that ground, we examined whether participants’ judgments about a social robot (mind, morality, and trust perceptions) differed across prototypical interactions. Findings indicate interaction forms somewhat influence trust but not mind or morality evaluations. However, how participants perceived interactions (independent of form) were more impactful. In particular, perceived task interactions fostered functional …

Moving Ahead With Human-Machine Communication, Leopoldina Fortunati, Autumn P. Edwards

Human-Machine Communication

In this essay, we introduce the 10 articles comprising Volume 2 (2021) of Human-Machine Communication, each of which is innovative and offers a substantial contribution to the field of human-machine communication (HMC). As a collection, these articles move forward the HMC project by touching on four layers of important discourse: (1) updates to theoretical frameworks and paradigms, including Computers as Social Actors (CASA), (2) examination of ontology and prototyping processes, (3) critical analysis of gender and ability/disability relations, and (4) extension of HMC scholarship into organizational contexts. Building upon the insights offered by the contributing authors and incorporating perspectives …

“Looks Like Its Rush Hour Again” – How Botted Users Have Increased The Traffic Of Websites, Ali Shahrokhi

Ramaley Celebration

The main purpose of this paper is to discuss the ideas about how botted users are affecting websites. The problem that comes when bots take over websites is that these botted users cause so much traffic that websites cannot scale well enough. Websites after the holidays see a mass decrease in the number of users on their sites. However, in 2021 and with years to come this has changed where we will see an increase. It is estimated that the number of bots on a website through 2021 is about 35% of all traffic. In this paper, I will discuss …

Assistive Robotics And Their Uses During The Pandemic, Thomas Klassen, Jeremy Evert

Student Research

• “Assistive Robotics” defines any device that can sense, process sensory information, and perform actions that benefit people with disabilities.

• This form of technology can be used on a much higher scale with a greater number of uses.

• We have an opportunity to expand the usage of assistive robotics to help combat COVID-19.

A Comprehensive Mapping And Real-World Evaluation Of Multi-Object Tracking On Automated Vehicles, Alexander Bassett

Doctoral Dissertations and Master's Theses

Multi-Object Tracking (MOT) is a field critical to Automated Vehicle (AV) perception systems. However, it is large, complex, spans research fields, and lacks resources for integration with real sensors and implementation on AVs. Factors such those make it difficult for new researchers and practitioners to enter the field.

This thesis presents two main contributions: 1) a comprehensive mapping for the field of Multi-Object Trackers (MOTs) with a specific focus towards Automated Vehicles (AVs) and 2) a real-world evaluation of an MOT developed and tuned using COTS (Commercial Off-The-Shelf) software toolsets. The first contribution aims to give a comprehensive overview of …

Distance-Based Formation Control Using Decentralized Sensing With Infrared Photodiodes, Steven Williams

LSU Master's Theses

This study presents an onboard sensor system for determining the relative positions of mobile robots, which is used in decentralized distance-based formation controllers for multi-agent systems. This sensor system uses infrared photodiodes and LEDs; its effective use requires coordination between the emitting and detecting robots. A technique is introduced for calculating the relative positions based on photodiode readings, and an automated calibration system is designed for future maintenance. By measuring the relative positions of their neighbors, each robot is capable of running an onboard formation controller, which is independent of both a centralized controller and a global positioning-like system (e.g., …

On The Impact Of Gravity Compensation On Reinforcement Learning In Goal-Reaching Tasks For Robotic Manipulators, Jonathan Fugal, Hasan A. Poonawala, Jihye Bae

Electrical and Computer Engineering Faculty Publications

Advances in machine learning technologies in recent years have facilitated developments in autonomous robotic systems. Designing these autonomous systems typically requires manually specified models of the robotic system and world when using classical control-based strategies, or time consuming and computationally expensive data-driven training when using learning-based strategies. Combination of classical control and learning-based strategies may mitigate both requirements. However, the performance of the combined control system is not obvious given that there are two separate controllers. This paper focuses on one such combination, which uses gravity-compensation together with reinforcement learning (RL). We present a study of the effects of gravity …

Ticknet: A Lightweight Deep Classifier For Tick Recognition, Li Wang

Masters Theses

The world is increasingly controlled by machine learning and deep learning. Deep neural networks are becoming powerful, encroaching on many tasks in computer vision system areas previously seen as the unique domain of humans, such as image classification, object detection, semantic segmentation, and instance segmentation. The success of a deep learning model at a specific application is determined by a sequence of choices, like what kind of deep neural network will be used, what data to be fed into the deep model, and what manners will be adopted to train a deep model.

The goal of this work is to …

The Rise Of The Machine: How Industrial Robots Will Revolutionize U.S. Manufacturing, Alexander Koontz

Engineering: Student Scholarship & Creative Works

Automation has become a term to symbolize many different movements in today’s world. It could represent anything from the blind, preprogrammed robotic arm in an automotive assembly plant to the increasing prevalence of driverless cars on the road. It could be used as a word of praise in the chase of more efficiency and optimization, or as a curse against the aspect of the obsolescence of humans as their roles are rendered redundant by robotic laborers. However, the lack of clarity of the term stems from a lack of understanding about its historical connotations, precisely how it applies today, and …

Human-Robot Collaboration Enabled By Real-Time Vision Tracking, Travis Deegan

Electronic Theses and Dissertations

The number of robotic systems in the world is growing rapidly. However, most industrial robots are isolated in caged environments for the safety of users. There is an urgent need for human-in-the-loop collaborative robotic systems since robots are very good at performing precise and repetitive tasks but lack the cognitive ability and soft skills of humans. To fill this need, a key challenge is how to enable a robot to interpret its human co-worker’s motion and intention. This research addresses this challenge by developing a collaborative human-robot interface via innovations in computer vision, robotics, and system integration techniques. Specifically, this …

Human-Aware Information-Theoretic Control Of Robotic Swarms, Rafal David Krzysiak

Graduate Research Theses & Dissertations

Robotic swarms provide a scalable and robust solution for monitoring large environments. In this context, the inclusion of a human has the potential advantage of incorporating prior knowledge about the target location or dynamics, thus increasing the overall efficiency of the task at hand. This is especially critical when dealing with time-intensive missions such as search and rescue. In this thesis we develop a general information-theoretic framework to control multiple autonomous robots in search and rescue missions that include a human teleoperator. Human prior knowledge is modeled to capture target location and dynamics, and a mutual information based control is …

Imu-Based Estimation Of Body Posture In Commercial Fishing, Umme Kawsar Alam

Graduate Research Theses & Dissertations

According to the U.S. Bureau of Labor Statistics (BLS), work-related musculoskeletaldisorders (WMSDs) account for 33% of all occupational injuries and illnesses in the U.S. In addition, one of the most strenuous occupations in which musculoskeletal disorders are common is known to be commercial fishing. The first step to address this issue is to precisely measure the working postures of workers so that the relation between WMSDs and nonneutral working postures can be systematically investigated. Although the inertial measurement unit (IMU) has recently gained attention in posture measurement due to its portability, it is highly limited to the use as an …

Deep Learning Assisted Intelligent Visual And Vehicle Tracking Systems, Liang Xu

Theses and Dissertations

Sensor fusion and tracking is the ability to bring together measurements from multiple sensors of the current and past time to estimate the current state of a system. The resulting state estimate is more accurate compared with the direct sensor measurement because it balances between the state prediction based on the assumed motion model and the noisy sensor measurement. Systems can then use the information provided by the sensor fusion and tracking process to support more-intelligent actions and achieve autonomy in a system like an autonomous vehicle. In the past, widely used sensor data are structured, which can be directly …

Design Of Lower Legs Of Mithra, A High-Performance Backdrivable Humanoid Robot, Drake Taylor

Electronic Theses and Dissertations

This thesis presents the design of the knee and ankle of Mithra, a new humanoid robot that aims to be an energy-efficient and highly agile machine. Mithra makes use of new optimization metrics for legged robots to develop a system capable of mimicking human movement. A series of low-impedance, high-torque actuator systems were developed with the goal of creating lightweight, powerful, and robust motion. The structure of Mithra's legs mimics the human structure in leg segment length and weight proportions. Detailed design and analysis were conducted in order to allow Mithra to be a robust and maintainable system. Mithra will …

Design, Manufacture, And Test Of A Hybrid Aerial-Ground Robotic Platform, William Garrett Willmon

Electronic Theses and Dissertations

A hybrid aerial-ground robotic platform allows for enhanced functionality combining most of the operational profiles of an aerial and ground vehicle with applications to intelligence, surveillance, reconnaissance (ISR), infrastructure inspection, emergency response, photography, etc. Motivated by this challenge, we designed, developed, and tested a prototype hybrid aerial-ground robotic vehicle capable of guidance, navigation, and control in the air and on the ground. The thesis focus is on the system design. As such, at first, we designed and analyzed the mechanical component to ensure durability. We then designed the electrical component to reduce overall weight and maximize battery life. We developed …

Toward Intelligent Welding By Building Its Digital Twin, Qiyue Wang

Theses and Dissertations--Electrical and Computer Engineering

To meet the increasing requirements for production on individualization, efficiency and quality, traditional manufacturing processes are evolving to smart manufacturing with the support from the information technology advancements including cyber-physical systems (CPS), Internet of Things (IoT), big industrial data, and artificial intelligence (AI). The pre-requirement for integrating with these advanced information technologies is to digitalize manufacturing processes such that they can be analyzed, controlled, and interacted with other digitalized components. Digital twin is developed as a general framework to do that by building the digital replicas for the physical entities. This work takes welding manufacturing as the case study to …

Planning Algorithms Under Uncertainty For A Team Of A Uav And A Ugv For Underground Exploration, Matteo De Petrillo

Graduate Theses, Dissertations, and Problem Reports

Robots’ autonomy has been studied for decades in different environments, but only recently, thanks to the advance in technology and interests, robots for underground exploration gained more attention. Due to the many challenges that any robot must face in such harsh environments, this remains an challenging and complex problem to solve.

As technology became cheaper and more accessible, the use of robots for underground ex- ploration increased. One of the main challenges is concerned with robot localization, which is not easily provided by any Global Navigation Services System (GNSS). Many developments have been achieved for indoor mobile ground robots, making …

Development Of An Autonomous Navigation System For The Shuttle Car In Underground Room & Pillar Coal Mines, Vasileios Androulakis

Theses and Dissertations--Mining Engineering

In recent years, autonomous solutions in the multi-disciplinary field of the mining engineering have been an extremely popular applied research topic. The growing demand for mineral supplies combined with the steady decline in the available surface reserves has driven the mining industry to mine deeper underground deposits. These deposits are difficult to access, and the environment may be hazardous to mine personnel (e.g., increased heat, difficult ventilation conditions, etc.). Moreover, current mining methods expose the miners to numerous occupational hazards such as working in the proximity of heavy mining equipment, possible roof falls, as well as noise and dust. As …

Integration Of Robotic And Electro-Pneumatic Systems Using Advanced Control And Communication Schemes, Chinmay Kondekar

Dissertations, Master's Theses and Master's Reports

Modern industrial automation systems are designed by interconnecting various subsystems which work together to perform a process. The thesis project aims to integrate fragmented subsystems into a flexible and reconfigurable system through advanced communication protocols and perform a process to demonstrate the effectiveness of interconnected systems.

The system consists of three six-axis robots, one electro-pneumatic robot, and two conveyors connected using EthernetIP communication and hardwired connections. The interconnected system works together to perform machining of a workpiece using advanced control methods of CAD to robot path generation, central control through a PLC, and process control through HMI.

Standardized programming blocks …

Open-Source Tig-Based Metal 3d-Printing, Shane Oberloier

Dissertations, Master's Theses and Master's Reports

Metal 3-D printing has been relegated to high-cost proprietary high-resolution systems and low-resolution low-cost metal inert gas (MIG) systems. In order to provide a path to high-resolution, low-cost, metal 3-D printing, this manuscript proposes a new open source metal 3-D printer design based around a low-cost tungsten inert gas (TIG) welder coupled to a commercial open source self replicating rapid prototyper. Optimal printing parameters for the machine are acquired using a novel computational intelligence software. TIG has many advantages over MIG, such as having a low heat input, clean beads, and the potential for both high-resolution prints as well as …

Leveraging Chemical And Computational Biology To Probe The Cellulose Synthase Complex, B. Kirtley Amos

Theses and Dissertations--Plant and Soil Sciences

Cellular expansion in plants is a complex process driven by the constraint of internal cellular turgor pressure by an expansible cell wall. The main structural element of the cell wall is cellulose. Cellulose is vital to plant fitness and the protein complex that creates it is an excellent target for small molecule inhibition to create herbicides. In the following thesis many small molecules (SMs) from a diverse library were screened in search of new cellulose biosynthesis inhibitors (CBI). Loss of cellular expansion was the primary phenotype used to search for putative CBIs. As such, this was approached in a forward …