[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127935-en":3,"doc-seo-127935-105":31,"detail-sidebar-cat-0-en-105":92},{"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":28,"seo_description":14,"update_tm":29,"read_time":30},127935,687207024478,"Liam","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Determination of Ship Collision Avoidance Timing Using Machine Learning Method","Accurate timing for maritime collision avoidance is essential to prevent collisions, yet traditional threshold-based approaches relying on DCPA and TCPA are constrained by environmental uncertainty and the decision variability of Officers on Watch (OOWs). A machine-learning framework is developed to learn collision avoidance behavior from AIS data collected around Ningbo Zhoushan Port, focusing on cross-encounter scenarios. After spatiotemporal preprocessing and trajectory-pair identification, the Douglas–Peucker algorithm generates collision-avoidance action timing labels and a decision dataset. Random Forest identifies key influencing factors and an optimized PSO-XGBoost model predicts an avoidance action time window, supported by case studies demonstrating practical effectiveness.","sustainability   \nArticle  \nDetermination of Ship Collision Avoidance Timing Using Machine Learning Method  \nYu Zhou 1,2,3, Weijie Du 4, Jiao Liu 1,2,3, Haoqing Li 1,2,3, Manel Grifoll 5, Weijun Song 6,* and Pengjun Zheng 1,2,3, *  \nCitation: Zhou, Y.; Du, W.; Liu, J.; Li, H.; Grifoll, M.; Song, W.; Zheng, P. Determination of Ship Collision Avoidance Timing Using Machine Learning Method. Sustainability 2024, 16, 4626. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)su16114626  \nAcademic Editors: Jiangang Fei, Junzhong Bao and Shenping Hu  \nReceived: 22 April 2024  \nRevised: 26 May 2024  \nAccepted: 27 May 2024  \nPublished: 29 May 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China;  \n[2111084021@nbu.edu.cn](2111084021@nbu.edu.cn) (Y.Z.); [liujiao@nbu.edu.cn](liujiao@nbu.edu.cn) (J.L.); [216002788@nbu.edu.cn](216002788@nbu.edu.cn) (H.L.)  \n2 Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing 211189, China  \n3 National Traffic Management Engineering & Technology Research Center Ningbo University Sub-Center, Ningbo 315832, China  \n4 Ningbo Pilot Station, Ningbo 315040, China; [duwi@nbport.com.cn](duwi@nbport.com.cn)  \n5 Barcelona School of Nautical Studies, Universitat Politècnica de Catalunya (UPC—BarcelonaTech), 08034 Barcelona, Spain; [manel.grifoll@upc.edu](manel.grifoll@upc.edu)  \n6 Ningbo Liwan New Material Co., Ltd., Ningbo 315812, China  \n* Correspondence: [songweijun@nbliwanxcl.com](songweijun@nbliwanxcl.com) (W.S.); [zhengpengjun@nbu.edu.cn](zhengpengjun@nbu.edu.cn) (P.Z.)  \nAbstract: The accurate timing for collision avoidance actions is crucial for preventing maritime collisions. Traditional methods often rely on collision risk assessments, using quantitative indicators like the Distance to the Closest Point of Approach (DCPA) and the Time to the Closest Point of Approach (TCPA) . Ship Officers on Watch (OOWs) are required to execute avoidance maneuvers once these indicators reach or exceed preset safety thresholds. However, the effectiveness of these indicators is limited by uncertainties in the maritime environment and the human behaviors of OOWs. To address these limitations, this study introduces a machine learning method to learn collision avoidance behavior from empirical data of ship collision avoidance, particularly in crossencounter situations. The research utilizes Automatic Identification System (AIS) data from the open waters around Ningbo Zhoushan Port. After data preprocessing and applying spatio-temporal constraints, this study identifies ship trajectory pairs in crossing scenarios and calculates their relative motion parameters. The Douglas–Peucker algorithm is used to identify the timing of ship collision avoidance actions and a collision avoidance decision dataset is constructed. The Random Forest algorithm was then used to analyze the factors affecting the timing of collision avoidance, and six key factors were identified: the distance, relative speed, relative bearing, DCPA, TCPA, and the ratio of the lengths of the giving-way and stand-on ships. These factors serve as inputs for the XGBoost algorithm model, which is enhanced with Particle Swarm Optimization (PSO), and thus constructing a ship collision avoidance decision model. In addition, considering the inherent errors in any model and the dynamic nature of the ship collision avoidance process, an action time window for collision avoidance is introduced, which provides a more flexible time range for ships to make timely collision avoidance responses based on actual conditions","cbCaihn4HBQgs1nA","https://ap.wps.com/l/cbCaihn4HBQgs1nA","pdf",5894204,2,1,23,"English","en",105,"# Introduction\n## Collision avoidance timing challenges\n## Overview of the proposed machine-learning approach\n# Data and trajectory processing\n## AIS data source and preprocessing\n## Spatio-temporal constraints and trajectory pair selection\n# Collision avoidance action timing generation\n## Douglas–Peucker based timing identification\n## Construction of the decision dataset\n# Modeling and factor analysis\n## Random Forest feature identification\n## XGBoost with PSO optimization\n# Action time window and validation\n## Flexible time-range decision strategy\n## Case studies and results","[{\"question\":\"Why is collision avoidance timing critical in maritime safety?\",\"answer\":\"Timing determines when an OOW should initiate, adjust, and possibly return from avoidance maneuvers. Too-early actions cause unnecessary deviation and inefficiency, while too-late decisions increase emergency risk and collision likelihood.\"},{\"question\":\"What limitations affect traditional DCPA/TCPA threshold-based methods?\",\"answer\":\"Their effectiveness is limited by uncertainties in the maritime environment and by human behavior variability among Officers on Watch, which can reduce the reliability of preset safety thresholds.\"},{\"question\":\"How does the study generate and model collision avoidance timing?\",\"answer\":\"It preprocesses AIS data, identifies crossing trajectory pairs, and uses the Douglas–Peucker algorithm to determine avoidance action timing. It then constructs a decision dataset, uses Random Forest to find key factors, and builds an optimized PSO-XGBoost model to predict an avoidance action time window.\"}]","Determination of Ship Collision Avoidance Timing Using Machine Learning Method | PDF",1785943094,58,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"determination-of-ship-collision-avoidance-timing-using-machine-learning-method","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/determination-of-ship-collision-avoidance-timing-using-machine-learning-method/127935/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-28","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is collision avoidance timing critical in maritime safety?","Question",{"text":76,"@type":77},"Timing determines when an OOW should initiate, adjust, and possibly return from avoidance maneuvers. Too-early actions cause unnecessary deviation and inefficiency, while too-late decisions increase emergency risk and collision likelihood.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What limitations affect traditional DCPA/TCPA threshold-based methods?",{"text":81,"@type":77},"Their effectiveness is limited by uncertainties in the maritime environment and by human behavior variability among Officers on Watch, which can reduce the reliability of preset safety thresholds.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the study generate and model collision avoidance timing?",{"text":85,"@type":77},"It preprocesses AIS data, identifies crossing trajectory pairs, and uses the Douglas–Peucker algorithm to determine avoidance action timing. It then constructs a decision dataset, uses Random Forest to find key factors, and builds an optimized PSO-XGBoost model to predict an avoidance action time window.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]