{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/134307"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/134307","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Precision Robotics with Mid-Weight Hardware and Software: A Swerve Drive Implementation","abstract":"The era of AI (artificial intelligence) demands ever increasing computational power. As we dawn the age of general-purpose robotics, this trend continues. For complex robotics systems, thoughtful choices of both software and hardware architecture are required for minimizing hardware requirements: how do we deploy the most complex software systems on the most minimal hardware all while maximizing usability and reducing error? This question impacts the safety of future systems, as robotic error at its best can mean a fully leveraged and helpful system, and at its worst can mean anything on the order of property damage to reduced quality of human safety. This paper explores an advanced robotic system with lightweight compute hardware: a swerve drive robot, leveraging an Intel RealSense D435i depth camera, to navigate a room using the slam toolbox and Nav2 stack. This robot uses a Raspberry Pi 5 as its main compute. A swerve drive is a unique hybrid of traditional four-wheel drive and mecanum drive systems. Pivoting radially, they offer the ability to strafe and the ability to turn in place. This design, built with eight motors, is intended for factories and industry where moving highvalue, high-weight products in a controlled manor is critical. Using Gazebo as the simulation environment, and with the eventual goal of moving the software stack to a physical robot, this paper explores the development timeline, and how to leverage computationally light algorithms for a high-yield product. It also explores considerations for compute utilization to prevent system bottlenecks. The overall goal is to provide a roadmap for researchers and developers who are interested in building and optimizing swerve drive robots using ROS2 on less expensive hardware, specifically the Raspberry Pi 5","abstract_html":"The era of AI (artificial intelligence) demands ever increasing computational power. As we dawn the age of general-purpose robotics, this trend continues. For complex robotics systems, thoughtful choices of both software and hardware architecture are required for minimizing hardware requirements: how do we deploy the most complex software systems on the most minimal hardware all while maximizing usability and reducing error? This question impacts the safety of future systems, as robotic error at its best can mean a fully leveraged and helpful system, and at its worst can mean anything on the order of property damage to reduced quality of human safety. This paper explores an advanced robotic system with lightweight compute hardware: a swerve drive robot, leveraging an Intel RealSense D435i depth camera, to navigate a room using the slam toolbox and Nav2 stack. This robot uses a Raspberry Pi 5 as its main compute. A swerve drive is a unique hybrid of traditional four-wheel drive and mecanum drive systems. Pivoting radially, they offer the ability to strafe and the ability to turn in place. This design, built with eight motors, is intended for factories and industry where moving highvalue, high-weight products in a controlled manor is critical. Using Gazebo as the simulation environment, and with the eventual goal of moving the software stack to a physical robot, this paper explores the development timeline, and how to leverage computationally light algorithms for a high-yield product. It also explores considerations for compute utilization to prevent system bottlenecks. The overall goal is to provide a roadmap for researchers and developers who are interested in building and optimizing swerve drive robots using ROS2 on less expensive hardware, specifically the Raspberry Pi 5","abstract_has_math":false,"creators":["Forsyth, Robert Henry Jr."],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Engineering","degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Chantem, Thidapat","Williams, Ryan K."],"committee_members":["Ransbottom, Jeffrey Scot"],"year":2025,"date_issued":"2025-05-29","date_published":"2025-05-29","updated_at":"2026-07-22T22:20:23Z","subjects":["Robotics","Swerve Drive","ROS2","Gazebo","PID","four-wheel drive","omnidirectional movement"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44157"],"render_values":[{"text":"vt_gsexam:44157","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/134307","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Chantem, Thidapat","Williams, Ryan K."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Ransbottom, Jeffrey Scot"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Forsyth, Robert Henry Jr."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-05-30T08:04:49Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-05-30T08:04:49Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05-29"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Robotics","Swerve Drive","ROS2","Gazebo","PID","four-wheel drive","omnidirectional movement"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44157"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/134307"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The era of AI (artificial intelligence) demands ever increasing computational power. As we dawn the age of general-purpose robotics, this trend continues. For complex robotics systems, thoughtful choices of both software and hardware architecture are required for minimizing hardware requirements: how do we deploy the most complex software systems on the most minimal hardware all while maximizing usability and reducing error? This question impacts the safety of future systems, as robotic error at its best can mean a fully leveraged and helpful system, and at its worst can mean anything on the order of property damage to reduced quality of human safety. This paper explores an advanced robotic system with lightweight compute hardware: a swerve drive robot, leveraging an Intel RealSense D435i depth camera, to navigate a room using the slam toolbox and Nav2 stack. This robot uses a Raspberry Pi 5 as its main compute. A swerve drive is a unique hybrid of traditional four-wheel drive and mecanum drive systems. Pivoting radially, they offer the ability to strafe and the ability to turn in place. This design, built with eight motors, is intended for factories and industry where moving highvalue, high-weight products in a controlled manor is critical. Using Gazebo as the simulation environment, and with the eventual goal of moving the software stack to a physical robot, this paper explores the development timeline, and how to leverage computationally light algorithms for a high-yield product. It also explores considerations for compute utilization to prevent system bottlenecks. The overall goal is to provide a roadmap for researchers and developers who are interested in building and optimizing swerve drive robots using ROS2 on less expensive hardware, specifically the Raspberry Pi 5"]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["This paper discusses the development and optimization of a four-wheel robotic system. It highlights the importance of selecting appropriate software and hardware for achieving high software complexity and low error on a low power compute. The study involves a robot equipped with a depth camera for navigation, utilizing specific software tools for mapping and control. The system is evaluated in various environments, all in simulation, with the aim of realworld application."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Precision Robotics with Mid-Weight Hardware and Software: A Swerve Drive Implementation"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Chantem, Thidapat","Williams, Ryan K."],"dc:contributor.committeemember":["Ransbottom, Jeffrey Scot"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Forsyth, Robert Henry Jr."],"dc:date.accessioned":["2025-05-30T08:04:49Z"],"dc:date.available":["2025-05-30T08:04:49Z"],"dc:date.issued":["2025-05-29"],"dc:description.abstract":["The era of AI (artificial intelligence) demands ever increasing computational power. As we dawn the age of general-purpose robotics, this trend continues. For complex robotics systems, thoughtful choices of both software and hardware architecture are required for minimizing hardware requirements: how do we deploy the most complex software systems on the most minimal hardware all while maximizing usability and reducing error? This question impacts the safety of future systems, as robotic error at its best can mean a fully leveraged and helpful system, and at its worst can mean anything on the order of property damage to reduced quality of human safety. This paper explores an advanced robotic system with lightweight compute hardware: a swerve drive robot, leveraging an Intel RealSense D435i depth camera, to navigate a room using the slam toolbox and Nav2 stack. This robot uses a Raspberry Pi 5 as its main compute. A swerve drive is a unique hybrid of traditional four-wheel drive and mecanum drive systems. Pivoting radially, they offer the ability to strafe and the ability to turn in place. This design, built with eight motors, is intended for factories and industry where moving highvalue, high-weight products in a controlled manor is critical. Using Gazebo as the simulation environment, and with the eventual goal of moving the software stack to a physical robot, this paper explores the development timeline, and how to leverage computationally light algorithms for a high-yield product. It also explores considerations for compute utilization to prevent system bottlenecks. The overall goal is to provide a roadmap for researchers and developers who are interested in building and optimizing swerve drive robots using ROS2 on less expensive hardware, specifically the Raspberry Pi 5"],"dc:description.abstractgeneral":["This paper discusses the development and optimization of a four-wheel robotic system. It highlights the importance of selecting appropriate software and hardware for achieving high software complexity and low error on a low power compute. The study involves a robot equipped with a depth camera for navigation, utilizing specific software tools for mapping and control. The system is evaluated in various environments, all in simulation, with the aim of realworld application."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:44157"],"dc:identifier.uri":["https://hdl.handle.net/10919/134307"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Robotics","Swerve Drive","ROS2","Gazebo","PID","four-wheel drive","omnidirectional movement"],"dc:title":["Precision Robotics with Mid-Weight Hardware and Software: A Swerve Drive Implementation"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:23Z"}