{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/84063"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/84063","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Prototype Development and Behavior Tree Optimization for Swarm Robotic Search","abstract":"M.Eng.","abstract_html":"M.Eng.","abstract_has_math":false,"creators":["Dhameliya, Maulikkumar; 0000-0002-3470-3818"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Chowdhury, Souma","Mechanical and Aerospace Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-06-21T15:47:32Z","date_published":"2022-06-21T15:47:32Z","updated_at":"2026-07-27T19:05:30Z","subjects":["mechanical engineering","robotics","swarm intelligence","swarm robotics","behavior tree","optimization","particle swarm optimization","virtual environment","motion planning"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/84063","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chowdhury, Souma","Mechanical and Aerospace Engineering"]},{"key":"dc:creator","label":"Author","values":["Dhameliya, Maulikkumar; 0000-0002-3470-3818"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-06-21T15:47:32Z","2020"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["mechanical engineering","robotics","swarm intelligence","swarm robotics","behavior tree","optimization","particle swarm optimization","virtual environment","motion planning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/84063"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.Eng.","This thesis encapsulates the conceptual design, fabrication, and testing of a new cm-scale wheeled robot. Teams of small (mm-to-cm scale) robots, often known as swarm-bots, can provide unique functionality owing to their small form factor, distributed sensing capabilities, resilience to disruptions and losing an agent, and likely low cost. Such swarm-bots are being increasingly touted to support various indoor surveillance, hazard detection, and search and rescue missions. New swarm robots are developed around a modular platform, comprising snap-on (3D printed) structural components, a stepper motor actuated wheel system, a Raspberry Pi computing node, a wireless radio module, a Lipo battery, and proximity sensors; all components are readily detachable, thereby allowing reconfiguration flexibility. Through three design generations, a stable prototype offering >20cm/s speed and ~50 min endurance, was developed, assembled and tested. The goal of developing these new swarm robots is to find the source of a spatially varying signal in a complex obstacle-ridden environment. A swarm intelligence algorithm, inspires from particle swarm optimization is used to locate the source of the signal and to navigate through a cluttered environment, a rule-based obstacle avoidance algorithm was hand-crafted. To handle these switching between this modular algorithm, most efficiently behavior tree structure is used. Behavior trees allow encoding explainable and reliable behavior, aka state-to-action mapping that can guide the motion of robotic agents in an unstructured environment. Simulation-based optimization was carried out to achieve an optimized and generalized behavior tree that enables both obstacle avoidance (at the trajectory decision level) as well as the implementation of a swarm intelligence algorithm (at waypoint planning level). Taking an evolutionary robotics perspective, a genetic algorithm is used to optimize critical parameters of the behavior tree to this end, via a two-stage optimization process. Environment feedback is provided by running simulations in the V-Rep environment, which somewhat constraints the swarm sizes that can be simulated (for optimization) in reasonable computing time. Finally, the effectiveness of the optimized behavior tree tested in physical experiments in the swarm robots to shedding insights into its performance and reality gap implications.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Prototype Development and Behavior Tree Optimization for Swarm Robotic Search"]}]}],"canonical_facts":{"dc:contributor":["Chowdhury, Souma","Mechanical and Aerospace Engineering"],"dc:creator":["Dhameliya, Maulikkumar; 0000-0002-3470-3818"],"dc:date":["2022-06-21T15:47:32Z","2020"],"dc:description":["M.Eng.","This thesis encapsulates the conceptual design, fabrication, and testing of a new cm-scale wheeled robot. Teams of small (mm-to-cm scale) robots, often known as swarm-bots, can provide unique functionality owing to their small form factor, distributed sensing capabilities, resilience to disruptions and losing an agent, and likely low cost. Such swarm-bots are being increasingly touted to support various indoor surveillance, hazard detection, and search and rescue missions. New swarm robots are developed around a modular platform, comprising snap-on (3D printed) structural components, a stepper motor actuated wheel system, a Raspberry Pi computing node, a wireless radio module, a Lipo battery, and proximity sensors; all components are readily detachable, thereby allowing reconfiguration flexibility. Through three design generations, a stable prototype offering >20cm/s speed and ~50 min endurance, was developed, assembled and tested. The goal of developing these new swarm robots is to find the source of a spatially varying signal in a complex obstacle-ridden environment. A swarm intelligence algorithm, inspires from particle swarm optimization is used to locate the source of the signal and to navigate through a cluttered environment, a rule-based obstacle avoidance algorithm was hand-crafted. To handle these switching between this modular algorithm, most efficiently behavior tree structure is used. Behavior trees allow encoding explainable and reliable behavior, aka state-to-action mapping that can guide the motion of robotic agents in an unstructured environment. Simulation-based optimization was carried out to achieve an optimized and generalized behavior tree that enables both obstacle avoidance (at the trajectory decision level) as well as the implementation of a swarm intelligence algorithm (at waypoint planning level). Taking an evolutionary robotics perspective, a genetic algorithm is used to optimize critical parameters of the behavior tree to this end, via a two-stage optimization process. Environment feedback is provided by running simulations in the V-Rep environment, which somewhat constraints the swarm sizes that can be simulated (for optimization) in reasonable computing time. Finally, the effectiveness of the optimized behavior tree tested in physical experiments in the swarm robots to shedding insights into its performance and reality gap implications.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/84063"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["mechanical engineering","robotics","swarm intelligence","swarm robotics","behavior tree","optimization","particle swarm optimization","virtual environment","motion planning"],"dc:title":["Prototype Development and Behavior Tree Optimization for Swarm Robotic Search"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T19:05:30Z"}