[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81544-en":3,"doc-seo-81544-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},81544,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1782698725881665579",8,"Research & Report","Object-Adaptive Impact Point Predictor for Catching Diverse In-Flight Objects","In-flight object catching is tackled with a quadruped robot carrying a basket, aiming to accurately predict the impact point—the object’s landing position on a fixed-height catching plane. The work addresses two obstacles: the lack of public datasets covering diverse objects under unsteady aerodynamics, and the difficulty of early-stage impact prediction when trajectories look similar across objects. A real-world dataset of 8,000 trajectories from 20 objects is built, then used to train OIPP with an Object-Adaptive Encoder and two impact-point predictors (NAE and DPE). Results show improved accuracy on seen and unseen objects, with enhanced early-stage prediction improving simulated and real-robot catching success.","OIPP: Object-Adaptive Impact Point Predictor for Catching Diverse In-Flight Objects  \nNgoc Huy Nguyen 1 , Kazuki Shibata 1 and Takamitsu Matsubara 1  \narXiv :2509 . 15254v3 [ cs .RO] 10 Jul 2026  \nAbstract—In this study, we address the problem of in-flight object catching using a quadruped robot with a basket. Our objective is to accurately predict the impact point, defined as the object’s landing position. This task poses two key challenges: the absence of public datasets capturing diverse objects under unsteady aerodynamics, which are essential for training reliable predictors; and the difficulty of accurate earlystage impact point prediction when trajectories appear similar across objects. To overcome these issues, we construct a realworld dataset of 8,000 trajectories from 20 objects, providing a foundation for advancing in-flight object catching under complex aerodynamics. We then propose the Object-Adaptive Impact Point Predictor (OIPP), consisting of two modules:(i) an Object-Adaptive Encoder (OAE) that extracts objectdependent representations from motion histories, and (ii) an Impact Point Predictor (IPP) that estimates the impact point from these representations. Two IPP variants are implemented: a Neural Acceleration Estimator (NAE)-based method that predicts trajectories and derives the impact point, and a Direct Point Estimator (DPE)-based method that directly outputs it. Experimental results show that our dataset is more diverse and complex than existing datasets, and that our method outperforms baselines on both 15 seen and 5 unseen objects. Furthermore, we show that improved early-stage prediction enhances catching success in simulation and demonstrate the effectiveness of our approach through real-robot experiments. The dataset and demonstration are available at [https://](https://)[ ](https://)[sites.google.com/view/robot-catching-2025](sites.google.com/view/robot-catching-2025).  \nI. INTRODUCTION  \nAccurate prediction of the object’s future state is essential for robotic catching of in-flight objects [1]–[6] . Owing to limited flight time, the robot must predict the object’s future state from only a short segment of its motion history in the early stage. In addition, the prediction must remain accurate under complex aerodynamic effects that make trajectories deviate significantly from simple parabolic motion.  \nIn this study, we address in-flight object catching using a quadruped robot equipped with a basket mounted on its body, as illustrated in Fig. 1. While manipulator-based catching [1]–[6] can intercept objects at various points along their trajectories, our task is constrained to a catching plane ata fixed height. Consequently, our objective is not to predict the entire trajectory but to accurately estimate the impact point [7], defined as the intersection between the object’s trajectory and the catching plane.  \nPredicting the impact point of diverse in-flight objects poses two key challenges. First, there is no public dataset that captures complex aerodynamics across diverse objects, which  \n1All the authors are with the Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology (NAIST), Nara, Japan  \nFig. 1: Catching diverse in-flight objects with complex aerodynamics using a quadruped robot  \nis essential for training reliable predictors. Existing datasets are limited to six objects with mostly near-parabolic trajectories [5], while physics simulations diversify object shapes [6] but fail to capture unsteady aerodynamic phenomena such as lift variation, Magnus forces, and vortex shedding. Second, existing methods often fail to learn object-dependent representations from short motion histories, particularly in the early stage where trajectories appear similar across different objects. This makes it difficult to distinguish trajectories, leading to inaccurate predictions. Moreover, predicting trajectories of unseen objects is particularly chall","cbCaihgILwb0r5hk","https://ap.wps.com/l/cbCaihgILwb0r5hk","pdf",3141499,3,1,"English","en",105,"# Introduction\n## Problem and challenges\n## Dataset construction\n## Proposed method (OIPP)\n## Impact point predictor variants","[{\"question\":\"What is the main goal of OIPP in this study?\",\"answer\":\"OIPP aims to predict the impact point, defined as where an object’s trajectory intersects a fixed-height catching plane, enabling successful robotic catching.\"},{\"question\":\"Why is an impact point prediction dataset considered a key contribution?\",\"answer\":\"There is no public dataset capturing diverse objects under unsteady aerodynamics, so the study builds a real-world dataset of 8,000 trajectories from 20 objects to train reliable predictors.\"},{\"question\":\"What are the two modules and the two IPP variants proposed by OIPP?\",\"answer\":\"OIPP uses an Object-Adaptive Encoder (OAE) to extract object-dependent representations from motion histories and an Impact Point Predictor (IPP) with two variants: a Neural Acceleration Estimator (NAE) and a Direct Point Estimator (DPE).\"}]",1784174194,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"object-adaptive-impact-point-predictor-for-catching-diverse-in-flight-objects","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":20},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/object-adaptive-impact-point-predictor-for-catching-diverse-in-flight-objects/81544/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of OIPP in this study?","Question",{"text":74,"@type":75},"OIPP aims to predict the impact point, defined as where an object’s trajectory intersects a fixed-height catching plane, enabling successful robotic catching.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why is an impact point prediction dataset considered a key contribution?",{"text":79,"@type":75},"There is no public dataset capturing diverse objects under unsteady aerodynamics, so the study builds a real-world dataset of 8,000 trajectories from 20 objects to train reliable predictors.",{"name":81,"@type":72,"acceptedAnswer":82},"What are the two modules and the two IPP variants proposed by OIPP?",{"text":83,"@type":75},"OIPP uses an Object-Adaptive Encoder (OAE) to extract object-dependent representations from motion histories and an Impact Point Predictor (IPP) with two variants: a Neural Acceleration Estimator (NAE) and a Direct Point Estimator (DPE).","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]