[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85350-en":3,"doc-seo-85350-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85350,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","A Model for Mediating Multi-Modal Human Intent into Safe Maneuvers for UAVs","Direct human interaction with autonomous UAV systems can be enabled through speech, gestures, and graphical interfaces, but interpreting these inputs as immediate executable commands creates safety hazards in dynamic environments. Operator requests may conflict with terrain limits, inter-UAV separation requirements, or flight-envelope constraints. The paper proposes a requirements-governed maneuver-response model that mediates multi-modal intent into constrained maneuver requests, validating requests and enabling either constrained execution, rejection, or continuous runtime monitoring. Initial lab validation supports reliable voice and GUI operation under safety constraints.","A Model for Mediating Multi-Modal Human Intent into Safe Maneuvers for UAVs  \nSofia Nelson  \nUniversity of Notre Dame Notre Dame, IN, USA [snelso24@nd.edu](snelso24@nd.edu)  \nDalal Alrajeh  \nImperial College London London, UK [dalal.alrajeh@ic.ac.uk](dalal.alrajeh@ic.ac.uk)  \nPedro Antonio Alarcon Granadeno  \nUniversity of Notre Dame Notre Dame, IN, USA[palarcon@nd.edu](palarcon@nd.edu)  \nJane Cleland-Huang  \nUniversity of Notre Dame Notre Dame, IN, USA [janehuang@nd.edu](janehuang@nd.edu)  \narXiv :2607 . 11654v1 [ cs .RO] 13 Jul 2026  \nAbstract—Direct human interaction with autonomous UAV systems can be enabled through modalities such as speech, gestures, and graphical interfaces. However, interpreting such inputs as directly executable commands introduces safety risks in dynamic environments. Operator requests may conflict with terrain constraints, inter-UAV separation requirements, or flight-envelope limitations. In this paper, we present a requirements-governed maneuver-response model that mediates multi-modal human intent into safe UAV maneuvers by treating operator inputs as bounded maneuver requests rather than direct commands. Requested maneuvers are mapped to constrained motion primitivesand processed through a structured request–evaluate–execute pipeline. Each request is interpreted with associated confidence, validated against terrain, separation, workspace, and flightenvelope constraints, and either constrained, rejected, or executed under continuous runtime monitoring. We further formalize the approach as a requirements-based specification model in which maneuver primitives are associated with explicit preconditions, invariants, guard conditions, and postconditions governing admissibility, execution safety, and emergency handling. These requirements support runtime verification and future reactive synthesis approaches. We present an initial lab-based validation demonstrating that voice- and GUI-based inputs can be reliably interpreted and safely executed as constrained maneuver requests.  \nIndex Terms—Human–UAV Interaction, Runtime Assurance, Safety-Critical Systems, Multi-Modal Interaction, Requirements  \nI. MOTIVATION  \nWithin the Human-Machine Teaming (HMT) paradigm, small Uncrewed Aerial Vehicles (UAVs) operate as collaborative partners that combine autonomous decision-making with human oversight and intervention [1] . Although these systems are often deployed under human-on-the-loop (HoTL) supervision, operators may periodically engage more directly in the loop by issuing maneuver- or mission-level commands through speech, gestures, or hardware and software interfaces. Such interventions are especially important in dynamic operational contexts where human judgment, situational awareness, or mission intent may temporarily supersede autonomous behavior. For instance, an operator might direct a drone toreposition itself for a medical package delivery or to conduct a closer inspection of a structure when environmental conditions, mission priorities, or nuanced situational cues cannot be reliably interpreted by the autonomous system alone.  \nTo support these forms of interaction, a significant body of work has explored mechanisms through which humans provide directives to UAVs, especially rotorcraft platforms capable of hovering and maneuvering with high precision inclose proximity to people and objects. Several researchers have developed gesture-based systems, where real-time hand poses are mapped to flight commands for single UAVs [2]–[4] or even swarms [5], [6] . Others have used voice commands to enable hands-free communication [7], [8], and more recently multimodal fusion of gesture and voice inputs has been shown to outperform either modality alone, with each communication channel compensating for the other’s environmental limitations [9], [10] . However, this prior work has focused primarily on using Computer Vision (CV) or Natural Language Processing (NLP) to recognize human intent and to map it to UAV act","cbCail0nNobvm9fb","https://ap.wps.com/l/cbCail0nNobvm9fb","pdf",10541176,2,1,10,"English","en",105,"# Motivation\n## Human-Machine Teaming and direct operator interventions\n## Prior work on gestures and voice-based UAV commands\n## Safety limitations of direct command execution\n## Runtime constraint evaluation as a requirements engineering challenge","[{\"question\":\"Why is executing operator multi-modal inputs as direct UAV commands unsafe?\",\"answer\":\"Direct execution can violate terrain limits, inter-UAV separation requirements, or flight-envelope constraints when commands are incorrect, unclear, or issued under limited situational awareness. This can lead to crashes, collisions with people or objects, or UAV-to-UAV collisions.\"},{\"question\":\"How does the proposed model mediate human intent into safer UAV behavior?\",\"answer\":\"It treats operator inputs as bounded maneuver requests mapped to constrained motion primitives. Each request is interpreted with confidence, validated against terrain, separation, workspace, and flight-envelope constraints, and handled through a request–evaluate–execute pipeline with continuous runtime monitoring.\"},{\"question\":\"What requirements are formalized to support safe execution and emergency handling?\",\"answer\":\"Maneuver primitives are specified with explicit preconditions, invariants, guard conditions, and postconditions that govern admissibility, execution safety, and emergency handling. These requirements enable runtime verification and can support future reactive synthesis approaches.\"}]",1784202703,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-model-for-mediating-multi-modal-human-intent-into-safe-maneuvers-for-uavs","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/a-model-for-mediating-multi-modal-human-intent-into-safe-maneuvers-for-uavs/85350/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is executing operator multi-modal inputs as direct UAV commands unsafe?","Question",{"text":75,"@type":76},"Direct execution can violate terrain limits, inter-UAV separation requirements, or flight-envelope constraints when commands are incorrect, unclear, or issued under limited situational awareness. This can lead to crashes, collisions with people or objects, or UAV-to-UAV collisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed model mediate human intent into safer UAV behavior?",{"text":80,"@type":76},"It treats operator inputs as bounded maneuver requests mapped to constrained motion primitives. Each request is interpreted with confidence, validated against terrain, separation, workspace, and flight-envelope constraints, and handled through a request–evaluate–execute pipeline with continuous runtime monitoring.",{"name":82,"@type":73,"acceptedAnswer":83},"What requirements are formalized to support safe execution and emergency handling?",{"text":84,"@type":76},"Maneuver primitives are specified with explicit preconditions, invariants, guard conditions, and postconditions that govern admissibility, execution safety, and emergency handling. These requirements enable runtime verification and can support future reactive synthesis approaches.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":22,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]