Robotics Commons^™

Dynamic Maze Puzzle Navigation Using Deep Reinforcement Learning, Luisa Shu Yi Chiu

Master's Theses

The implementation of deep reinforcement learning in mobile robotics offers a great solution for the development of autonomous mobile robots to efficiently complete tasks and transport objects. Reinforcement learning continues to show impressive potential in robotics applications through self-learning and biological plausibility. Despite its advancements, challenges remain in applying these machine learning techniques in dynamic environments. This thesis explores the performance of Deep Q-Networks (DQN), using images as an input, for mobile robot navigation in dynamic maze puzzles and aims to contribute to advancements in deep reinforcement learning applications for simulated and real-life robotic systems. This project is a step …

Uav-Based Tracking And Following Of Railroad Lines, Keith Michael Lewandowski

Theses and Dissertations

Given the pivotal role of the railroad industry in modern transportation and the potential risks associated with track malfunctions, the inspection and maintenance of railroad tracks emerges as a critical concern. While existing solutions excel in performing accurate measurements and detection, they often rely on large, expensive, and time-consuming platforms for inspections. This project, however, seeks to solve the same problem with the use of an unmanned aerial vehicle (UAV), significantly reducing time and cost while maintaining detection capabilities. In particular, this solution is ideal for large-scale, high-level inspections following major events such as floods [6], hurricanes [7] or earthquakes …

Training Uav Teams With Multi-Agent Reinforcement Learning Towards Fully 3d Autonomous Wildfire Response, Bryce Hopkins

All Theses

As climate-exacerbated wildfires increasingly threaten landscapes and communities, there is an urgent and pressing need for sophisticated fire management technologies. Coordinated teams of Unmanned Aerial Vehicles (UAVs) present a promising solution for detection, assessment, and even incipient-stage suppression – especially when integrated into a multi-layered approach with other recent wildfire management technologies such as geostationary/polar-orbiting satellites and CCTV detection networks. However, there remains significant challenges in developing the necessary sensing, navigation, coordination, and communication subsystems that enable intelligent UAV teams. Further, federal regulations governing UAV deployment and autonomy pose constraints on real-world aerial testing, creating a disconnect between theoretical research …

Convex Approach To Data-Driven Optimal Control With Safety Constraints Using Linear Transfer Operator, Joseph Raphel Moyalan

All Dissertations

This thesis is concerned with the data-driven solution to the optimal control problem with safety constraints for a class of control-affine nonlinear systems. Designing optimal control satisfying safety constraints is a problem of interest in various applications, including robotics, power systems, transportation networks, and manufacturing. This problem is known to be non-convex. One of this thesis's main contributions is providing a convex formulation to this non-convex problem. The second main contribution is providing a data-driven framework for solving the control problem with safety constraints. The linear operator theoretic framework involving Perron-Frobenius and Koopman operators provides the convex formulation and associated …

Vision-Based Autonomy Stacks For Farm Tractors And Intelligent Spraying Systems In Orchards, Shengli Xu

All Dissertations

Autonomous tractors equipped with intelligent sprayers have become a pivotal aspect of smart farming (SF), marking a transformative shift in traditional agricultural practices and holding the potential to revolutionize the farming industry. With 2,453,620 fruit-bearing acres in the United States as of 2022, there is a pressing need for the implementation of autonomous systems for farm tractors and intelligent spraying systems in orchards. These advancements can significantly reduce labor costs, address labor shortages, and minimize spray loss. Furthermore, to enhance profitability and productivity, it is essential to develop low-cost yet effective vision-based autonomy systems that can operate efficiently across various …

The Effects Of Using Artificial Intelligence Techniques In The Security Work System, Abdalla Alnaqbi

Journal of Police and Legal Sciences

The goal of the research is to shed light on the techniques of artificial intelligence in the work of experts and groups, and to achieve this goal by seeking to search for the concept of artificial intelligence, as well as the classification of artificial intelligence, and clarifying the role of artificial intelligence in organizations and bodies, and it also reached the definition of the positive and cooperative effects of artificial intelligence in... the job. And the. The researcher followed the descriptive model of analysis in order to achieve the objectives of the study, and the study reached one of the …

Criminal Confrontation Of The Crime Committed Via An Automated Robot In Libyan And Emirati Law, . Mashaallah Alzwae

Journal of Police and Legal Sciences

Today's world is witnessing an important development in telecommunications, information technology and computers that has resulted in what are known as automated robots as one of the most important applications of artificial intelligence and has increased reliance on them in various areas of life for the importance of the services they provide to humanity. However, such robots may be used to commit an offence and the study therefore aims to determine the effectiveness of legal texts in the face of the offence from which they may occur. The study required an analytical and comparative approach by analysing and comparing the …

Authenticated Diagnosing Of Covid-19 Using Deep Learning-Based Ct Image Encryption Approach, Mohamed Attia Abdelgwad, Amira Hassan Abed, Mahmoud Bahloul

Future Computing and Informatics Journal

Researchers are motivated to use artificial intelligence in biometrics, medical imaging encryption, as well as cybersecurity due to its rapid progress. An encryption method for CT scans—which are used to diagnose COVID-19 disease—is proposed in this study. The suggested encryption method creates a connection among an individual's face picture and CT image to increase confidentiality. The simple CT picture is first enhanced with a host image. An encryption key is multiplied by the final result. This key is produced by applying a Convolutional Neural Network (CNN) to recognize characteristics from people's face photographs. Additionally, a straightforward CNN with three convolutional …

Development Of A Rule-Based Monitoring System For Autonomous Heavy Equipment Safety, Amirpooya Shirazi

Department of Construction Engineering and Management: Dissertations, Theses, and Student Research

Roadway construction work zones are constantly exposed to interactions among construction equipment, workers, and vehicles. Furthermore, ensuring safety in these areas is considered a challenging task due to the complexity of the environment. As shown in the rising trend of fatal accidents in roadway work zones, current OSHA regulations in construction safety are insufficient in effectively detecting unsafe situations and mitigating the risks. Furthermore, best practices, such as internal traffic control planning (ITCP), exhibit critical limitations requiring continuous monitoring of active work zones as well as adjustments to the site coordination plans due to the dynamic nature of work zone …

Studying The Performance Of Object Recognition With Fusion Of Visible Light And Infrared Images With Neural Networks, Plamen Petkov

Doctoral Dissertations and Master's Theses

Neural networks have been used for object detection and recognition in both color and intensity camera images. As the use of infrared cameras, colloquially termed thermal cameras, has increased and costs have decreased, object detection and recognition in infrared camera images have been increasingly studied. An infrared image is treated as an intensity image, just like a grayscale camera image, except the intensity corresponds to infrared radiation instead of visible light. The information provided by these two types of images are different, especially in different lighting and environmental situations, and some types of objects are more easily recognized in visible …

Authentic Impediments: The Influence Of Identity Threat, Cultivated Perceptions, And Personality On Robophobia, Kate K. Mays

Human-Machine Communication

Considering possible impediments to authentic interactions with machines, this study explores contributors to robophobia from the potential dual influence of technological features and individual traits. Through a 2 x 2 x 3 online experiment, a robot’s physical human-likeness, gender, and status were manipulated and individual differences in robot beliefs and personality traits were measured. The effects of robot traits on phobia were non-significant. Overall, subjective beliefs about what robots are, cultivated by media portrayals, whether they threaten human identity, are moral, and have agency were the strongest predictors of robophobia. Those with higher internal locus of control and neuroticism, and …

What’S In A Name And/Or A Frame? Ontological Framing And Naming Of Social Actors And Social Responses, David Westerman, Michael Vosburg, Xinyue Liu, Patric R. Spence

Human-Machine Communication

Artificial intelligence (AI) is fundamentally a communication field. Thus, the study of how AI interacts with us is likely to be heavily driven by communication. The current study examined two things that may impact people’s perceptions of socialness of a social actor: one nonverbal (ontological frame) and one verbal (providing a name) with a 2 (human vs. robot) x 2 (named or not) experiment. Participants saw one of four videos of a study “host” crossing these conditions and responded to various perceptual measures about the socialness and task ability of that host. Overall, data were consistent with hypotheses that whether …

Navigating The Rules: Integrating Td3 And Sensor Fusion For Traffic-Aware Autonomous Vehicle Path Planning, Mahmoud Ayman Mohamed Elsayed

Theses and Dissertations

This work presents a novel algorithm for local path planning for autonomous vehicles (AVs) which prioritizes both safety and adherence to traffic regulations, addressing critical functions for AV navigation, such as navigating complex environments, avoiding obstacles, and ensuring passenger and road users safety. The algorithm integrates the Twin Delayed Deep Deterministic Policy Gradient (TD3) with sensor fusion based on Nvidia Convolutional Neural Network (NCNN). The study utilizes the CARLA simulator, and real-world datasets, including KITTI and WAYMO, to train and evaluate the proposed algorithm. The proposed algorithm leverages the complementary strengths of Imitation Learning (IL) and Deep Reinforcement Learning (DRL) …

Smart Robot Design And Implementation To Assist Pedestrian Road Crossing, Hovannes Kulhandjian

Mineta Transportation Institute

This research focuses on designing and developing a smart robot to assist pedestrians with road crossings. Pedestrian safety is a major concern, as highlighted by the high annual rates of fatalities and injuries. In 2020, the United States recorded 6,516 pedestrian fatalities and approximately 55,000 injuries, with children under 16 being especially vulnerable. This project aims to address this need by offering an innovative solution that prioritizes real-time detection and intelligent decision-making at intersections. Unlike existing studies that rely on traffic light infrastructure, our approach accurately identifies both vehicles and pedestrians at intersections, creating a comprehensive safety system. Our strategy …

Autonomous Apple Harvester Robot, Jack Ryan Cline, Tyus Green, Devon Woolston

Electrical Engineering

As agricultural demands rise and manual labor costs increase, there has become a dire need to automate apple harvesting. However, the precision and speed necessary for cost-efficient apple harvesting pose a significant challenge for robotic automation. To maintain cost-effective production, a harvester must be able to operate fast enough and long enough to compete with human labor. It must also be able to navigate and traverse apple orchards autonomously and pick apples without damaging the fruit or tree. This project presents an apple harvesting robot that uses a Mask R-CNN vision system with an RGB-D camera to detect the location …

Technocene, Vir Joseph Naidu

Masters Theses

Embodied human communication within the Anthropocene. Existing at the intersection of technology, and the body.

The design industry has developed technology that is, paradoxically, isolating. The exposure to a vast audience in the digital sphere has introduced new societal pressures, leading to a disconnection from our immediate surroundings, detached, and donning metaphorical masks. Technocene lives on the fringes of the discipline by blending conceptual thinking with practical application. Through curious, experimental artifacts, it prompts us to shed our masks and embrace vulnerability. Technocene endeavors to reimagine the human experience by acting as a discursive design project. It probes the boundaries …

Drone Swarm Search And Rescue, Rushabh Shah, Christopher Short, Anderson Macmillan, Wyatt Colburn

Electrical Engineering

Drone swarms offer the potential to drastically reduce search times and improve the effectiveness of search and rescue operations. This senior project explores the development of a drone swarm system for search and rescue missions, focusing on two key challenges: (1) precise localization of each drone within the swarm relative to one another and (2) accurate localization of a target beacon relative to the drones. The project utilizes Real Time Kinematic (RTK) processing to enhance the accuracy of drone localization, achieving centimeter-level precision. Target localization is achieved through a triangulation-based approach using Received Signal Strength Indication (RSSI) data from a …

Effects Of A Wi-Fi Link On The Performance Of A Path Following Autonomous Ground Vehicle, Anthony Iwejuo, Austin Cagle, Billy Kihei, Ph.D.

Symposium of Student Scholars

As vehicles become more automated and connected, the future of safe and efficient travel will be dependent on efficient wireless networks. Artificial intelligence (AI) demands high power resources and computing resources that can be resource-intensive for mobile robotic systems. A new paradigm involving the remote computing of A.I. can enable robotics that are built lighter and more power efficient. In this study, we compare a locally run artificial intelligence algorithm for autonomous ground vehicle navigation against remote computation through various wireless links to highlight the need for low-latency access to remote computing resources over Wi-Fi network calls. Our findings show …

Mosaic Swarm Robotics: Emulating Natural Collective Behaviors For Efficient Task Execution With Custom Mobile Robots, Jonathan Ridley, Arielle Charles, Charles Koduru, Muhammad Hassan Tanveer, Razvan Voicu

Symposium of Student Scholars

Mosaics, as an artistic expression, involves the meticulous arrangement of diverse tiles to form a unified composition. Drawing inspiration from this concept, the field of swarm robotics seeks to emulate nature’s collective behaviors observed in ant colonies, fish schools, and bird flocks, employing multiple agents to accomplish tasks efficiently. Our research explores the concept of mosaic swarm robotics, where numerous nodes with specialized functions are deployed across various domains, including applications for outdoor data capture and environment mapping. We utilized custom mobile robots operated by Raspberry Pi microcontrollers. By establishing an elaborate web of client-to-client communications to enable true localized …

Securing The Skies: Safety-Constrained Decentralized Multi-Uav Coordination With Deep Reinforcement Learning, Jean-Elie Pierre

Electrical and Computer Engineering ETDs

In the dynamic landscape of autonomous aerial systems, the integration of uncrewed aerial vehicles (UAVs) has sparked a paradigm shift, offering unprecedented opportunities and challenges in collaborative decision-making and navigation. This thesis explores the application of multi-agent reinforcement learning (MARL) for the planning and coordination of UAVs in complex environments.

The first part of this thesis provides an introduction to single-agent reinforcement learning and MARL. We provide examples of the use of MARL for countering uncrewed aerial systems (C-UAS). We formulate the Counter-UAS problem as a multiagent partially observable Markov decision process (MAPOMDP), and we propose Multi-AGent partial observable deep …

Generalized Model To Enable Zero-Shot Imitation Learning For Versatile Robots, Yongshuai Wu

Master's Theses

The rapid advancement in Deep Learning (DL), especially in Reinforcement Learning (RL) and Imitation Learning (IL), has positioned it as a promising approach for a multitude of autonomous robotic systems. However, the current methodologies are predominantly constrained to singular setups, necessitating substantial data and extensive training periods. Moreover, these methods have exhibited suboptimal performance in tasks requiring long-horizontal maneuvers, such as Radio Frequency Identification (RFID) inventory, where a robot requires thousands of steps to complete.

In this thesis, we address the aforementioned challenges by presenting the Cross-modal Reasoning Model (CMRM), a novel zero-shot Imitation Learning policy, to tackle long-horizontal robotic …

Flexible Strain Gauge Sensors As Real-Time Stretch Receptors For Use In Biomimetic Bpa Muscle Applications, Rochelle Jubert

Student Research Symposium

This work presents a novel approach to real-time length sensing for biomimetic Braided Pneumatic Actuators (BPAs) as artificial muscles in soft robotics applications. The use of artificial muscles enables the development of more interesting robotic designs that no longer depend on single rotation joints controlled by motors. Developing robots with these capabilities, however, produces more complexities in control and sensing. Joint encoders, the mainstay of robotic feedback, can no longer be used, so new methods of sensing are needed to get feedback on muscle behavior to implement intelligent controls. To address this need, flexible strain gauge sensors from Portland company, …

Planetary Exploration Via Fully Automatic Topological Structure Extraction Using Adaptive Resonance, Jonathan Kissi

Electronic Thesis and Dissertation Repository

Renewed interest in Solar System exploration, along with ongoing improvements in computing, robotics and instrumentation technologies, have reinforced the case for remote science acquisition systems development in space exploration. Testing systems and procedures that allow for autonomously collected science has been the focus of analogue field deployments and mission planning for some time, with such systems becoming more relevant as missions increase in complexity and ambition. The introduction of lidar and laser scanning-type instruments into the geological and planetary sciences has proven popular, and, just as with the established image and photogrammetric methods, has found widespread use in several research …

Simulating And Training Autonomous Rover Navigation In Unity Engine Using Local Sensor Data, Christopher Pace

Senior Honors Theses

Autonomous navigation is essential to remotely operating mobile vehicles on Mars, as communication takes up to 20 minutes to travel between the Earth and Mars. Several autonomous navigation methods have been implemented in Mars rovers and other mobile robots, such as odometry or simultaneous localization and mapping (SLAM) until the past few years when deep reinforcement learning (DRL) emerged as a viable alternative. In this thesis, a simulation model for end-to-end DRL Mars rover autonomous navigation training was created using Unity Engine, using local inputs such as GNSS, LiDAR, and gyro. This model was then trained in navigation in a …

Summonable Construction Delivery Robot, Kevin M. Lewis

Honors Capstones

In many different construction industries, there is a need for tools, parts, and other necessary items to be transported quickly and efficiently over various types of terrain. Human resources have often been used to address these needs, which can become very time and cost inefficient over long periods. The design proposal here is aimed at addressing this need by developing an autonomous outdoor mobile robot based on a quadrupedal robot design. This approach differs by incorporating a wheeled and quadrupedal hybrid actuation system that provides terrain negotiation and speed at the appropriate times. The team uses Robot Operating System (ROS) …

Investigating Autonomous Ground Vehicles For Weed Elimination, Abraham Mitchell

Computer Science and Computer Engineering Undergraduate Honors Theses

The management of weeds in crop fields is a continuous agricultural problem. The use of herbicides is the most common solution, but herbicidal resistance decreases effectiveness, and the use of herbicides has been found to have severe adverse effects on human health and the environment. The use of autonomous drone systems for weed elimination is an emerging solution, but challenges in GPS-based localization and navigation can impact the effectiveness of these systems. The goal of this thesis is to evaluate techniques for minimizing localization errors of drones as they attempt to eliminate weeds. A simulation environment was created to model …

Mav Localization In Gps-Denied Environments And Synthetic Data Collection In Challenging Simulated Conditions, Julio A. Reyes Munoz

Open Access Theses & Dissertations

The development of unmanned aerial systems presents an opportunity for conducting industrial inspections in environments where traditional navigation systems, such as the Global Navigation Satellite System (GNSS), are compromised. This dissertation investigates the implementation of a micro aerial vehicle (MAV) capable of autonomous data acquisition in complex, GNSS-degraded industrial settings. The primary challenge addressed is the robust localization of MAVs, a critical aspect in ensuring reliable operation under varying and uncertain environmental conditions.

The work is divided into two main parts. The first part focuses on the design and integration of a MAV system specifically for power plant inspections in …

Determining The Viability Of Marine Sensor Construction, Roman Sequeira

Honors College

I intend to determine the viability of building a sensor that can be deployed in marine environments. Viability is defined as a summary of economic affordability, practicality of construction and deployment, knowledge required, and effectiveness. In order to get the best results, our sensor must be able to be modified to suit individual circumstances, constructed out of easy to obtain materials, be robust enough to withstand less than lab grade environments, and most importantly function well enough to be worth the effort of building it. I have built a sensor using the cheapest and most widely available options available. It …

Autonomous Fish Identification For The Remotely Operated Vehicle Control System, Jacob Wildes

Honors College

A Remotely Operated Vehicle was designed, constructed, and programmed as a senior design project in Electrical and Computer Engineering by Dyllon Dunton and Jacob Wildes. The system was intended to be an alternative means to inspect the underside of ships. Given the small footprint of the system, it can be easily extended into other applications. In this thesis project, the observation system is modified to detect if a fish is present or not, classify the species, localize where in the image the fish is, and mask the fish by separating fish pixels from non-fish pixels. Additionally, the original design will …

Development And Feasibility Studies Of Ai-Powered Socially Assistive Robotics To Promote Wellbeing Of Persons With Alzheimer’S Disease And Related Dementias, Fengpei Yuan

Doctoral Dissertations

The number of persons living with Alzheimer's Disease and Related Dementias (PLWDs) has been keeping growing. In 2024, it is estimated that there will be approximately 6.7 million individuals living with Alzheimer's Dementia. This number will increase to about 14 million in 2060. Due to the damage in neurons, the capabilities of memory, thinking, and language will decline as the disease progress. As a result, persons with dementia will gradually withdraw from their social activities and become more dependent on others during their activities of daily living. Making it worse, our society is not ready for the increasing requirements of …