Robotics Commons^™

End-To-End Development And Experimental Validation Of A 1/10-Scale Autonomous Vehicle, Rikkin Pankaj Panchal

Electrical Engineering Theses

Autonomous vehicle development demands vast resources, making scaled down platforms a critical alternative for solving core algorithmic challenges. The primary contribution of this thesis is the end to end development and validation of a complete real time autonomous driving pipeline deployed on a one tenth scale vehicle. To streamline platform development, an AI assisted annotation framework automates dataset generation, significantly reducing manual labor while improving training data quality. The system perception stack features a reinforcement learning guided online multi camera calibration framework that enables adaptive surround view stitching without the need for offline recalibration. This is paired with robust lane …

Cross-Layer Supervisory Control For Low-Altitude Uav Swarm Networks, Nitin Singh Rathore

Computer Science and Engineering Theses

Low-altitude unmanned aerial vehicle (UAV) swarms are increasingly used in applications such as aerial sensing, disaster response, and communication support, where reliable operation under dynamic and uncertain conditions is essential. In these environments, performance degradation arises from multiple sources, including external disturbances, sensing uncertainty, and communication impairments. Although these effects originate from different layers of the system, such as dynamics, observation, and networking, they often manifest as similar tracking or coordination errors. Conventional control approaches, which rely primarily on error-driven feedback, do not explicitly account for the underlying cause of these deviations, limiting their effectiveness in multi-agent settings. This thesis …

Controlling A Mobile Inverted Pendulum And Optimizing Leaning Angle To Apply Force Using Reinforcement Learning, Aryan Mediratta

2025 Spring Honors Capstone Projects - Archive

Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning …

Virtual Fixtures For Teleoperated Robots For The Visually Impaired, Vishwaak Chandran Thamaraiselvan

Computer Science and Engineering Theses - Archive

This paper presents our preliminary study on enabling individuals with visual impairments to safely operate mobile robots and vehicles. To achieve this, we developed a teleoperation with accessibility at its core. The system incorporates features that enhance usability and situational awareness, including assistive control based on artificial potential fields to prevent collisions and ensure smooth navigation. It also provides multimodal feedback through (a) haptic vibrations on the gamepad controller, which convey the proximity of nearby objects detected by the robot’s laser sensor, and (b) color-coded overlays that differentiate paths, obstacles, and people through semantic segmentation performed by a deep neural …

Exploring Instruction Generation For Uavs: Dataset Adaptation, Model Behavior, And Diagnostic Insights, Seyedarman Vaziri Bozorg

Computer Science and Engineering Theses - Archive

This thesis explores the development of an answering agent capable of generating natural language instructions for unmanned aerial vehicles (UAVs), grounded in a limited, real-world dialogue dataset. The objective is to adapt a static dataset into a training pipeline that can support instruction generation and serve as a foundation for future interactive systems involving question-asking agents and internal dialogue. A hybrid architecture is implemented using a semantic teacher model (MPNet) and a T5-base encoder-decoder trained with contrastive and supervised objectives. The adapted training process yields statistically acceptable performance across standard evaluation metrics. However, qualitative analysis reveals a mismatch between metric …

Transformer And Recurrent Architectures For Dynamics Prediction And Policy Learning On Long-Horizon Tasks, Vinal Jitendrabhai Gadhiya

Computer Science and Engineering Theses - Archive

Model-based reinforcement learning promises improved sample efficiency by learning environment dynamics and using them for planning or policy improvement. However, the choice of neural architecture for dynamics prediction significantly impacts the model's ability to capture temporal dependencies and maintain long-term context, capabilities crucial for complex, open-world environments.

This thesis investigates three neural architectures for learning world models: Transformer-based, GRU-based, and a hybrid Transformer+GRU approach. We evaluate these architectures on Crafter, a 2D open-world survival environment that requires long-horizon planning and sequential task completion. In Crafter, agents must perform hierarchical sequences of actions, such as collecting wood, placing a table, and …

Multi-Modal Model-Based Optical Flow Estimation For Event-Based Vision, Pritam Karmokar

Computer Science and Engineering Dissertations - Archive

Event cameras offer a fundamentally different sensing paradigm by asynchronously capturing brightness changes at high temporal resolution, directly encoding motion in the scene. However, their sparse and non-traditional data format poses significant challenges for dense motion estimation, particularly in the context of optical flow. Contrast Maximization (CM) has emerged as a powerful model-based framework for estimating optical flow from event data by optimizing the sharpness of motion-compensated event representations. This dissertation builds upon and significantly advances the CM framework through two complementary contributions.

First, we propose Edge-Informed Contrast Maximization (EINCM), a hybrid approach that augments the traditional events-only CM framework …

3d Perception, Mapping, And Navigation For Mobile Cobot, Tuan T. Dang

Computer Science and Engineering Dissertations - Archive

Service robots are migrating from tightly controlled factory lines into offices, hospitals, and homes, where they must perceive, remember, and act amid people, clutter, and perpetual change. Humans solve this daily by forming compact, task-relevant “cognitive maps”: we sample just enough sensory detail to guide the moment, stitch those snapshots into a sparse topological scaffold, and continuously refine it as we move. Guided by that insight, this dissertation proposes a biologically inspired mapping framework that turns partial RGB-D observations into a hybrid temporal-spatial memory—locally metric for centimeter-scale navigation yet globally topological for room-to-building navigation. The system first distills raw depth …

Environment And Intention Awareness For Navigation And Collaboration, Bhaskar Chandra Trivedi

Computer Science and Engineering Dissertations - Archive

Unmanned Aerial Systems (UAS) have become increasingly popular as versatile platforms for tasks such as surveillance, inspection, delivery, and maintenance. In many applications, UAS operate in environments frequented by people or containing sensitive infrastructure, which introduces physical risks in case of vehicle failure, as well as psychological and privacy concerns that may limit their acceptability. Ensuring safe and efficient operation thus requires that UAS consider these risks when planning navigation strategies. While prior information, such as city maps and building layouts, can partially inform risk assessment, such data is often incomplete, necessitating real-time augmentation of risk maps using sensor information. …

Exploring Smart Thermostat, Don P. Dang

2024 Fall Honors Capstone Projects - Archive

This study examines the security, privacy, and compatibility challenges associated with smart thermostats in smart home systems. Smart thermostats, as part of the growing Internet of Things (IoT) ecosystem, face vulnerabilities such as unauthorized access, data breaches, and inconsistent security protocols. Using a mixed-methods approach, this research evaluates encryption techniques, communication protocols (Zigbee, Z-Wave, Wi Fi), and user behaviors that impact system security and efficiency. Key findings indicate that 35% of users are concerned about hacking risks, while 25% express data privacy concerns. Many users lack awareness of security measures, such as firmware updates and password management, which increases vulnerabilities. …

Nonlinear Guidance And Control Of Unmanned Aerial Manipulators For Delivering A Payload On A Moving Platform, Ravi Gyawali

Mechanical and Aerospace Engineering Theses - Archive

Unmanned Aerial manipulators (UAMs) are a class of Unmanned Aerial Vehicles (UAVs) equipped with a manipulator. By combining the aerial mobility of a UAV with a manipulator's dexterity, these hybrid systems can perform a wide range of complex tasks while reducing risks and costs. As a result, they are increasingly being utilized for military, industrial, and agricultural applications.

The thesis presents a novel approach for a multi-UAM system to collaboratively deliver a payload on a stationary or maneuvering platform. A sliding-mode-based guidance law, sourced from existing literature, is integrated with a combined control technique for the UAVs and their respective …

Manifold Learning In Robotics: A Tutorial And Survey, Marcus Hawkins

Computer Science and Engineering Theses - Archive

In this article, we hope to represent the current state of the art of manifold learning in an understandable and approachable way. The authors will present a general overview core algorithms associated with linear and nonlinear dimensionality reduction techniques, give rudimentary definitions from differential geometry, and tenets of robotic perception, manipulation and path planning. Some of the historical applications of these algorithms will be presented, as well as conjectures about future uses, through examples from peer-reviewed journals.

A Learning-Based Framework For Autonomous Robotic Operations In Resource-Denied Environments, Joseph M. Cloud

Computer Science and Engineering Dissertations - Archive

Establishing a sustained human presence beyond Earth necessitates the development of autonomous systems capable of extracting and utilizing local resources. On the Moon, in-situ resource utilization (ISRU) is essential to reduce the dependency on Earth-based supplies. Leveraging lunar resources such as water ice for life support and fuel production or regolith for surface construction will enable long-term lunar missions and future deep space exploration. NASA's Artemis program is targeting the lunar south pole (LSP), an area with raw, yet abundant resources available. The harsh environmental conditions present significant challenges for humans operating and installing surface infrastructure. Autonomous robotic systems are …