{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/32995121"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/32995121","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Analytics-Driven Cooperative Multi-Robot Additive Manufacturing: Advancing Efficiency and Quality","abstract":"Robotic additive manufacturing (AM) leverages the unbounded work envelopes and high degrees of freedom of articulated manipulators to revolutionize large-scale fabrication; however, the transition from single robot to cooperative multi-robot and multi-head systems introduces complex, coupled decisions in decomposition, placement, and path planning under time, energy, quality, strength, and thermal constraints. This dissertation establishes a comprehensive analytics framework that links robot kinematics and dynamics, process parameters, and cooperation strategies to the resulting process–structure–property relationships in multi-robot AM. First, it characterizes the dimensional accuracy and energy consumption of single-robot AM through analytically grounded and experimentally validated model and use these models to construct three-dimensional energy–quality (EQ) maps that relate workspace location to manufacturing performance and guide part placement within a manipulator’s workspace. Second, to address multi-robot scenarios, these concepts of EQ maps are extended into inverse EQ maps for multi- robot scenarios, enabling the optimal positioning of multiple robot bases around decomposed sub-parts while satisfying reachability, collision, and tolerance constraints to enable cooperative printing. Third, to accelerate decision-making and address the computational limitations of traditional analytical models, the thesis introduces a Kinematics-Guided Multi-Task learning architecture that jointly predicts path feasibility and energy consumption. By embedding inverse kinematics into a shared backbone, KG-MT internalizes reachability and joint limits, achieves orders-of-magnitude speedups over simulation, and generalizes across robot platforms to support cross-platform, energy-aware planning. Finally, the thesis addresses the critical process planning challenges of strength- and thermal-aware decomposition and path planning respectively, : for multi-head extrusion-based systems, where decomposition creates weak interfaces, thesis proposes a Synchronous Multi-Layer Printing strategy that recovers the joint strength of single-head deposition while preserving the throughput of multi-head printing; for multi-laser systems, the thesis establishes a framework that links decomposed multi-laser trajectories to thermal histories and uses clustering-based selection of path-planning strategies to stabilize thermal distributions and promote uniform temperature fields, validated experimentally and via a physics-informed neural network. Collectively, these contributions unify robot-, process-, structure-, and property-level analytics into a coherent decision-making foundation for cooperative multi-robot AM, supporting energy-efficient, high- quality, and property-aware decision-making across placement, decomposition, and path planning.","abstract_html":"Robotic additive manufacturing (AM) leverages the unbounded work envelopes and high degrees of freedom of articulated manipulators to revolutionize large-scale fabrication; however, the transition from single robot to cooperative multi-robot and multi-head systems introduces complex, coupled decisions in decomposition, placement, and path planning under time, energy, quality, strength, and thermal constraints. This dissertation establishes a comprehensive analytics framework that links robot kinematics and dynamics, process parameters, and cooperation strategies to the resulting process–structure–property relationships in multi-robot AM. First, it characterizes the dimensional accuracy and energy consumption of single-robot AM through analytically grounded and experimentally validated model and use these models to construct three-dimensional energy–quality (EQ) maps that relate workspace location to manufacturing performance and guide part placement within a manipulator’s workspace. Second, to address multi-robot scenarios, these concepts of EQ maps are extended into inverse EQ maps for multi- robot scenarios, enabling the optimal positioning of multiple robot bases around decomposed sub-parts while satisfying reachability, collision, and tolerance constraints to enable cooperative printing. Third, to accelerate decision-making and address the computational limitations of traditional analytical models, the thesis introduces a Kinematics-Guided Multi-Task learning architecture that jointly predicts path feasibility and energy consumption. By embedding inverse kinematics into a shared backbone, KG-MT internalizes reachability and joint limits, achieves orders-of-magnitude speedups over simulation, and generalizes across robot platforms to support cross-platform, energy-aware planning. Finally, the thesis addresses the critical process planning challenges of strength- and thermal-aware decomposition and path planning respectively, : for multi-head extrusion-based systems, where decomposition creates weak interfaces, thesis proposes a Synchronous Multi-Layer Printing strategy that recovers the joint strength of single-head deposition while preserving the throughput of multi-head printing; for multi-laser systems, the thesis establishes a framework that links decomposed multi-laser trajectories to thermal histories and uses clustering-based selection of path-planning strategies to stabilize thermal distributions and promote uniform temperature fields, validated experimentally and via a physics-informed neural network. Collectively, these contributions unify robot-, process-, structure-, and property-level analytics into a coherent decision-making foundation for cooperative multi-robot AM, supporting energy-efficient, high- quality, and property-aware decision-making across placement, decomposition, and path planning.","abstract_has_math":false,"creators":["Suyog Ghungrad (24400076)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05-01T00:00:00Z","date_published":"2026-05-01T00:00:00Z","updated_at":"2026-07-27T21:33:48Z","subjects":["Engineering, Industrial","Engineering, Mechanical","Computer Science"],"languages":[],"rights":["In Copyright","Open Access after 2028-05-01"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.32995121.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Suyog Ghungrad (24400076)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-05-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Analytics-Driven_Cooperative_Multi-Robot_Additive_Manufacturing_Advancing_Efficiency_and_Quality/32995121"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Engineering, Industrial","Engineering, Mechanical","Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright","Open Access after 2028-05-01"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.32995121.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Robotic additive manufacturing (AM) leverages the unbounded work envelopes and high degrees of freedom of articulated manipulators to revolutionize large-scale fabrication; however, the transition from single robot to cooperative multi-robot and multi-head systems introduces complex, coupled decisions in decomposition, placement, and path planning under time, energy, quality, strength, and thermal constraints. This dissertation establishes a comprehensive analytics framework that links robot kinematics and dynamics, process parameters, and cooperation strategies to the resulting process–structure–property relationships in multi-robot AM. First, it characterizes the dimensional accuracy and energy consumption of single-robot AM through analytically grounded and experimentally validated model and use these models to construct three-dimensional energy–quality (EQ) maps that relate workspace location to manufacturing performance and guide part placement within a manipulator’s workspace. Second, to address multi-robot scenarios, these concepts of EQ maps are extended into inverse EQ maps for multi- robot scenarios, enabling the optimal positioning of multiple robot bases around decomposed sub-parts while satisfying reachability, collision, and tolerance constraints to enable cooperative printing. Third, to accelerate decision-making and address the computational limitations of traditional analytical models, the thesis introduces a Kinematics-Guided Multi-Task learning architecture that jointly predicts path feasibility and energy consumption. By embedding inverse kinematics into a shared backbone, KG-MT internalizes reachability and joint limits, achieves orders-of-magnitude speedups over simulation, and generalizes across robot platforms to support cross-platform, energy-aware planning. Finally, the thesis addresses the critical process planning challenges of strength- and thermal-aware decomposition and path planning respectively, : for multi-head extrusion-based systems, where decomposition creates weak interfaces, thesis proposes a Synchronous Multi-Layer Printing strategy that recovers the joint strength of single-head deposition while preserving the throughput of multi-head printing; for multi-laser systems, the thesis establishes a framework that links decomposed multi-laser trajectories to thermal histories and uses clustering-based selection of path-planning strategies to stabilize thermal distributions and promote uniform temperature fields, validated experimentally and via a physics-informed neural network. Collectively, these contributions unify robot-, process-, structure-, and property-level analytics into a coherent decision-making foundation for cooperative multi-robot AM, supporting energy-efficient, high- quality, and property-aware decision-making across placement, decomposition, and path planning."]},{"key":"dc:title","label":"Title","values":["Analytics-Driven Cooperative Multi-Robot Additive Manufacturing: Advancing Efficiency and Quality"]}]}],"canonical_facts":{"dc:creator":["Suyog Ghungrad (24400076)"],"dc:date":["2026-05-01T00:00:00Z"],"dc:description":["Robotic additive manufacturing (AM) leverages the unbounded work envelopes and high degrees of freedom of articulated manipulators to revolutionize large-scale fabrication; however, the transition from single robot to cooperative multi-robot and multi-head systems introduces complex, coupled decisions in decomposition, placement, and path planning under time, energy, quality, strength, and thermal constraints. This dissertation establishes a comprehensive analytics framework that links robot kinematics and dynamics, process parameters, and cooperation strategies to the resulting process–structure–property relationships in multi-robot AM. First, it characterizes the dimensional accuracy and energy consumption of single-robot AM through analytically grounded and experimentally validated model and use these models to construct three-dimensional energy–quality (EQ) maps that relate workspace location to manufacturing performance and guide part placement within a manipulator’s workspace. Second, to address multi-robot scenarios, these concepts of EQ maps are extended into inverse EQ maps for multi- robot scenarios, enabling the optimal positioning of multiple robot bases around decomposed sub-parts while satisfying reachability, collision, and tolerance constraints to enable cooperative printing. Third, to accelerate decision-making and address the computational limitations of traditional analytical models, the thesis introduces a Kinematics-Guided Multi-Task learning architecture that jointly predicts path feasibility and energy consumption. By embedding inverse kinematics into a shared backbone, KG-MT internalizes reachability and joint limits, achieves orders-of-magnitude speedups over simulation, and generalizes across robot platforms to support cross-platform, energy-aware planning. Finally, the thesis addresses the critical process planning challenges of strength- and thermal-aware decomposition and path planning respectively, : for multi-head extrusion-based systems, where decomposition creates weak interfaces, thesis proposes a Synchronous Multi-Layer Printing strategy that recovers the joint strength of single-head deposition while preserving the throughput of multi-head printing; for multi-laser systems, the thesis establishes a framework that links decomposed multi-laser trajectories to thermal histories and uses clustering-based selection of path-planning strategies to stabilize thermal distributions and promote uniform temperature fields, validated experimentally and via a physics-informed neural network. Collectively, these contributions unify robot-, process-, structure-, and property-level analytics into a coherent decision-making foundation for cooperative multi-robot AM, supporting energy-efficient, high- quality, and property-aware decision-making across placement, decomposition, and path planning."],"dc:identifier":["10.25417/uic.32995121.v1"],"dc:relation":["https://figshare.com/articles/thesis/Analytics-Driven_Cooperative_Multi-Robot_Additive_Manufacturing_Advancing_Efficiency_and_Quality/32995121"],"dc:rights":["In Copyright","Open Access after 2028-05-01"],"dc:subject":["Engineering, Industrial","Engineering, Mechanical","Computer Science"],"dc:title":["Analytics-Driven Cooperative Multi-Robot Additive Manufacturing: Advancing Efficiency and Quality"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:33:48Z"}