{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/110849"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/110849","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Towards explainable AI: directed inference of linear temporal logic constraints","abstract":"\"Many systems in robotics and beyond may be classified as mixed logical-dynamical (MLD) systems. These systems are subject to both logical constraints, which govern their safe operation and goals; and dynamical constraints, which describe their physical behavior. These time-dependent constraints can be described with linear temporal logic (LTL). In the case where the constraints are not known, their inference offers a type of explanation for their behavior. Previous work has attempted to infer constraints for MLD systems by Bayesian methods, searching for optimally contrastive rules between \"\"good\"\" and \"\"bad\"\" system runs. However, due to a reliance on an unknown prior distribution, as well as a limited search space, these efforts are unable to recover all desired constraints. We propose an alternative inference method called directed hypothesis space generation (DHSG). DHSG compares each system run and constructs a full hypothesis space of all conjunctions and disjunctions of the desired LTL formula types. In simulation, DHSG recovered a full hypothesis space for each test case. However, due to a comparatively high computational demand, it also exhibited run times which increased significantly with state space complexity. The computational load was lightened by limiting the length of inferred formulas, at the cost of hypothesis space completeness. However, the adjustable computation time of the Bayesian approach means that it retains an advantage under some use cases. Finally, for scenarios in which neither the LTL rules are known, nor the state-space regions they govern, DHSG has potential to construct the unknown regions. This approach would give a basis on which to perform further inference. Region construction would apply to lesser-understood systems and presents a topic for future work.\"","abstract_html":""Many systems in robotics and beyond may be classified as mixed logical-dynamical (MLD) systems. These systems are subject to both logical constraints, which govern their safe operation and goals; and dynamical constraints, which describe their physical behavior. These time-dependent constraints can be described with linear temporal logic (LTL). In the case where the constraints are not known, their inference offers a type of explanation for their behavior. Previous work has attempted to infer constraints for MLD systems by Bayesian methods, searching for optimally contrastive rules between ""good"" and ""bad"" system runs. However, due to a reliance on an unknown prior distribution, as well as a limited search space, these efforts are unable to recover all desired constraints. We propose an alternative inference method called directed hypothesis space generation (DHSG). DHSG compares each system run and constructs a full hypothesis space of all conjunctions and disjunctions of the desired LTL formula types. In simulation, DHSG recovered a full hypothesis space for each test case. However, due to a comparatively high computational demand, it also exhibited run times which increased significantly with state space complexity. The computational load was lightened by limiting the length of inferred formulas, at the cost of hypothesis space completeness. However, the adjustable computation time of the Bayesian approach means that it retains an advantage under some use cases. Finally, for scenarios in which neither the LTL rules are known, nor the state-space regions they govern, DHSG has potential to construct the unknown regions. This approach would give a basis on which to perform further inference. Region construction would apply to lesser-understood systems and presents a topic for future work."","abstract_has_math":false,"creators":["Brindise, Noel Christine"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Aerospace Engineering","degree_department":null,"school":null,"contributors":["Langbort, Cedric"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-09-17T04:06:51Z","date_published":"2021-09-17T04:06:51Z","updated_at":"2026-07-22T22:24:52Z","subjects":["Constraint inference, Linear temporal logic, explainable AI, xAI, mixed logical dynamical systems, Bayesian inference"],"languages":["en"],"rights":["Copyright 2021 Noel Brindise"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/110849","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Langbort, Cedric"]},{"key":"dc:creator","label":"Author","values":["Brindise, Noel Christine"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-09-17T04:06:51Z","2021-04-26","2021-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Aerospace Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Constraint inference, Linear temporal logic, explainable AI, xAI, mixed logical dynamical systems, Bayesian inference"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Noel Brindise"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/110849"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["\"Many systems in robotics and beyond may be classified as mixed logical-dynamical (MLD) systems. These systems are subject to both logical constraints, which govern their safe operation and goals; and dynamical constraints, which describe their physical behavior. These time-dependent constraints can be described with linear temporal logic (LTL). In the case where the constraints are not known, their inference offers a type of explanation for their behavior. Previous work has attempted to infer constraints for MLD systems by Bayesian methods, searching for optimally contrastive rules between \"\"good\"\" and \"\"bad\"\" system runs. However, due to a reliance on an unknown prior distribution, as well as a limited search space, these efforts are unable to recover all desired constraints. We propose an alternative inference method called directed hypothesis space generation (DHSG). DHSG compares each system run and constructs a full hypothesis space of all conjunctions and disjunctions of the desired LTL formula types. In simulation, DHSG recovered a full hypothesis space for each test case. However, due to a comparatively high computational demand, it also exhibited run times which increased significantly with state space complexity. The computational load was lightened by limiting the length of inferred formulas, at the cost of hypothesis space completeness. However, the adjustable computation time of the Bayesian approach means that it retains an advantage under some use cases. Finally, for scenarios in which neither the LTL rules are known, nor the state-space regions they govern, DHSG has potential to construct the unknown regions. This approach would give a basis on which to perform further inference. Region construction would apply to lesser-understood systems and presents a topic for future work.\"","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2023-05-01","The student, Noel Brindise, accepted the attached license on 2021-04-22 at 10:50.","The student, Noel Brindise, submitted this Thesis for approval on 2021-04-22 at 11:02.","This Thesis was approved for publication on 2021-04-26 at 11:49.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16499 on 2021-09-16 at 20:13:58","Made available in DSpace on 2021-09-17T04:06:51Z (GMT). No. of bitstreams: 2 BRINDISE-THESIS-2021.pdf: 1310770 bytes, checksum: d778d40d641631667ae4aef6075d1fb1 (MD5) LICENSE.txt: 4210 bytes, checksum: cad96089a508bb8f74c1508feb96c21b (MD5) Previous issue date: 2021-04-26","Embargo set by: Seth Robbins for item 118695 Lift date: 2023-09-17T04:07:01Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","U of I Only Restriction set for Item 118695 on 2022-03-09T15:32:08Z with date 2023-09-17 by eliasbh2@illinois.edu.","Open Restriction set for Item 118695 on 2022-03-09T15:32:12Z with date null by eliasbh2@illinois.edu.","Open Restriction set for Item 118695 on 2022-03-09T15:32:14Z with date null by eliasbh2@illinois.edu.","Open"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards explainable AI: directed inference of linear temporal logic constraints"]}]}],"canonical_facts":{"dc:contributor":["Langbort, Cedric"],"dc:creator":["Brindise, Noel Christine"],"dc:date":["2021-09-17T04:06:51Z","2021-04-26","2021-05"],"dc:description":["\"Many systems in robotics and beyond may be classified as mixed logical-dynamical (MLD) systems. These systems are subject to both logical constraints, which govern their safe operation and goals; and dynamical constraints, which describe their physical behavior. These time-dependent constraints can be described with linear temporal logic (LTL). In the case where the constraints are not known, their inference offers a type of explanation for their behavior. Previous work has attempted to infer constraints for MLD systems by Bayesian methods, searching for optimally contrastive rules between \"\"good\"\" and \"\"bad\"\" system runs. However, due to a reliance on an unknown prior distribution, as well as a limited search space, these efforts are unable to recover all desired constraints. We propose an alternative inference method called directed hypothesis space generation (DHSG). DHSG compares each system run and constructs a full hypothesis space of all conjunctions and disjunctions of the desired LTL formula types. In simulation, DHSG recovered a full hypothesis space for each test case. However, due to a comparatively high computational demand, it also exhibited run times which increased significantly with state space complexity. The computational load was lightened by limiting the length of inferred formulas, at the cost of hypothesis space completeness. However, the adjustable computation time of the Bayesian approach means that it retains an advantage under some use cases. Finally, for scenarios in which neither the LTL rules are known, nor the state-space regions they govern, DHSG has potential to construct the unknown regions. This approach would give a basis on which to perform further inference. Region construction would apply to lesser-understood systems and presents a topic for future work.\"","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2023-05-01","The student, Noel Brindise, accepted the attached license on 2021-04-22 at 10:50.","The student, Noel Brindise, submitted this Thesis for approval on 2021-04-22 at 11:02.","This Thesis was approved for publication on 2021-04-26 at 11:49.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16499 on 2021-09-16 at 20:13:58","Made available in DSpace on 2021-09-17T04:06:51Z (GMT). No. of bitstreams: 2 BRINDISE-THESIS-2021.pdf: 1310770 bytes, checksum: d778d40d641631667ae4aef6075d1fb1 (MD5) LICENSE.txt: 4210 bytes, checksum: cad96089a508bb8f74c1508feb96c21b (MD5) Previous issue date: 2021-04-26","Embargo set by: Seth Robbins for item 118695 Lift date: 2023-09-17T04:07:01Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","U of I Only Restriction set for Item 118695 on 2022-03-09T15:32:08Z with date 2023-09-17 by eliasbh2@illinois.edu.","Open Restriction set for Item 118695 on 2022-03-09T15:32:12Z with date null by eliasbh2@illinois.edu.","Open Restriction set for Item 118695 on 2022-03-09T15:32:14Z with date null by eliasbh2@illinois.edu.","Open"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/110849"],"dc:language":["en"],"dc:rights":["Copyright 2021 Noel Brindise"],"dc:subject":["Constraint inference, Linear temporal logic, explainable AI, xAI, mixed logical dynamical systems, Bayesian inference"],"dc:title":["Towards explainable AI: directed inference of linear temporal logic constraints"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Aerospace Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:52Z"}