[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119375-en":3,"doc-seo-119375-105":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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119375,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Wind Estimation in Unmanned Aerial Vehicles with Causal Machine Learning","This work demonstrates wind-environment estimation for UAVs without dedicated wind sensors, relying solely on the UAV’s trajectory. A causal machine learning pipeline is introduced by implementing causal curiosity, which merges time-series classification and clustering within a causal framework. Three wind scenarios are analyzed: constant wind, shear wind, and turbulence. The study also compares optimisation strategies for selecting UAV manoeuvres that best reveal wind conditions. The approach supports safer, sensor-light flight planning by enabling optimal trajectories in challenging weather.","Wind Estimation in Unmanned Aerial Vehicles with  \nCausal Machine Learning  \nAbdulaziz Alwalan  \nSchool of Aerospace, Transport and Manufacturing Cranfield University United Kingdom [aziz.walan@gmail.com](aziz.walan@gmail.com)  \nMiguel Arana-Catania*  \nSchool of Aerospace, Transport and Manufacturing Cranfield University United Kingdom [miguel.aranacatania@cranfield.ac.uk](miguel.aranacatania@cranfield.ac.uk)  \n*Corresponding author  \narXiv :2407 .0 1 154v 1 [ cs .LG] 1 Jul 2024  \nAbstract—In this work we demonstrate the possibility of estimating the wind environment of a UAV without specialised sensors, using only the UAV’s trajectory, applying a causal machine learning approach. We implement the causal curiosity method which combines machine learning times series classification and clustering with a causal framework. We analyse three distinct wind environments: constant wind, shear wind, and turbulence, and explore different optimisation strategies for optimal UAV manoeuvres to estimate the wind conditions. The proposed approach can be used to design optimal trajectories in challenging weather conditions, and to avoid specialised sensors that add to the UAV’s weight and compromise its functionality.  \nIndex Terms—Aviation Control and Dynamics, UAV, Causal Learning, Aerospace, Machine Learning  \nI. INTRODUCTION  \nMulti-rotor Unmanned Aerial Vehicles (UAVs) have become increasingly popular in commercial and research sectors due to advantages over fixed-wing UAVs, such as vertical take-off and landing, hovering capabilities, and the ability to yaw on the spot. However, a significant challenge for those UAVs is their vulnerability to wind disturbances, which can affect their flight stability and energy efficiency [1] . Thus, recognising the effects of wind and incorporating this understanding into flight controls can enhance safety and efficiency.  \nCurrently, several methods allow different types of UAVs to measure wind speed. For instance, fixed-wing UAVs can gauge wind speed using sensors like the pitot tube, while multirotors can employ sonic anemometers. Nonetheless, these methods come with various constraints. For instance, it is essential to place flow sensors at a distance from the rotor’s turbulence. This arrangement might be straightforward for fixed-wing UAVs, but it poses challenges for multi-rotors. Another limitation of utilising a dedicated wind sensor is that it consumes a portion of the UAV’s mass budget, potentially compromising the inclusion of other components.  \nTo overcome these limitations, in this article we propose the use of a machine learning approach capable of identifying environmental conditions such as wind using only the UAV’s position information. This approach, called causal curiosity [2], is set in the framework of causal machine learning. Unlike traditional machine learning approaches that focus mainly on identifying patterns and correlations in the data, one of the objectives of this framework is to distinguish  \nbetween correlation and causation and establish and use the causal relationships between variables. In this particular case, identifying the relationship between the wind condition, the cause, and changes in the UAV’s trajectory, the effect. In this way, using UAV trajectory data, we can identify the specific wind conditions, without the need for specific sensors to measure the wind.  \nThe original proposal of this method [2] was demonstrated in the case of a robotic agent interacting with different objects in its environment. The study enabled a robotic fingers agent to conduct experiments that assist in classifying the interaction with unknown objects and consequently infer the properties of those objects. These parameters that determine the causal dynamics of the interactions are called causal factors. They are parameters such that, by applying a certain sequence of actionson the environment, the observations obtained are organised in distinguishable disjoint sets according to the","cbCaieUV1KLQhEUD","https://ap.wps.com/l/cbCaieUV1KLQhEUD","pdf",2291332,1,11,"English","en",105,"# Introduction\n## Motivation and UAV vulnerability to wind\n## Existing wind-measurement methods and limitations\n## Causal curiosity approach and causal framework\n## Contributions\n# Related Work","[{\"question\":\"How can the UAV estimate wind without specialised wind sensors?\",\"answer\":\"The method uses only the UAV’s position/trajectory data and applies causal machine learning to infer wind conditions from how the trajectory changes.\"},{\"question\":\"What wind environments are considered in the study?\",\"answer\":\"The paper analyzes constant wind, shear wind, and turbulence as distinct wind environments for testing the approach.\"},{\"question\":\"What is causal curiosity and why is it used here?\",\"answer\":\"Causal curiosity is a causal learning method that distinguishes correlation from causation by learning causal relationships between variables, here linking wind conditions (causal factors) to trajectory changes (effects).\"}]","Wind Estimation in Unmanned Aerial Vehicles with Causal Machine Learning | PDF",1785723984,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"wind-estimation-in-unmanned-aerial-vehicles-with-causal-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/wind-estimation-in-unmanned-aerial-vehicles-with-causal-machine-learning/119375/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How can the UAV estimate wind without specialised wind sensors?","Question",{"text":75,"@type":76},"The method uses only the UAV’s position/trajectory data and applies causal machine learning to infer wind conditions from how the trajectory changes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What wind environments are considered in the study?",{"text":80,"@type":76},"The paper analyzes constant wind, shear wind, and turbulence as distinct wind environments for testing the approach.",{"name":82,"@type":73,"acceptedAnswer":83},"What is causal curiosity and why is it used here?",{"text":84,"@type":76},"Causal curiosity is a causal learning method that distinguishes correlation from causation by learning causal relationships between variables, here linking wind conditions (causal factors) to trajectory changes (effects).","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]