[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85479-en":3,"doc-seo-85479-105":28,"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":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},85479,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","ReMoSPLAT Reactive Mobile Manipulation Control on a Gaussian Splat","Reactive control coordinates the base and arm motions of a mobile manipulator, yet achieving collision-free movement without costly global planning depends on how the environment is represented. ReMoSPLAT introduces a quadratic-program-based reactive controller that uses Gaussian Splatting to enable collision avoidance in cluttered scenes. Additional optimisation constraints and costs drive the end-effector to a target pose while preventing collisions. Simulations on synthetic and real scans validate feasibility with performance comparable to controllers using perfect ground-truth.","ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat  \nNicols Marticorena, Tobias Fischer, Niko Suenderhauf  \narXiv :2512 .09656v2 [ cs .RO] 13 Jul 2026  \nAbstract—Reactive control can gracefully coordinate the motion of the base and the arm of a mobile manipulator. However, incorporating an accurate representation of the environment to avoid obstacles without involving costly planning remains a challenge. In this work, we present ReMoSPLAT, areactive controller based on a quadratic program formulation for mobile manipulation that leverages a Gaussian Splat representation for collision avoidance. By integrating additional constraints and costs into the optimisation formulation, a mobile manipulator platform can reach its intended end effector pose while avoiding obstacles, even in cluttered scenes. We investigate the trade-offs of two methods for efficiently calculating robotobstacle distances, comparing a purely geometric approach with a rasterisation-based approach. Our simulation experiments on both synthetic and real-world scans demonstrate the feasibility of the proposed method, achieving performance comparable to controllers that rely on perfect ground-truth information. We further validate the approach on a real robot platform more details: [https://remosplat.github.io](https://remosplat.github.io)  \nI. INTRODUCTION  \nReactive control is an effective approach to control a mobile manipulator towards a desired target pose, without requiring costly global planning [1]–[3] . However, how the robot should perceive and represent the geometry of its surroundings to obtain collision-free motion in such a scenario is still an open challenge [4] . This problem is often overlooked [1], oversimplified [2], or assumed to be solved [3] .  \nTraditionally, scene representations for control and planning have relied on occupancy grids [5], meshes [6], or point clouds [7] . More recently, Gaussian Splatting (GS) [8] has emerged as an explicit scene representation that is efficient to render and represents the underlying scene geometry with sufficient fidelity to support downstream tasks in robotics [9] . For example, recent works have explored leveraging the geometric information encoded in GS representations for robotic navigation [10]–[12], where each Gaussian is interpreted as an obstacle in the environment. However, the potential of Gaussian Splatting as a scene representation for reactive mobile manipulation control remains unexplored.  \nIn this work, we explore bridging modern differential rendering based GS scene representations with a established control framework for mobile manipulation, enabling for the first time collision-aware mobile manipulation directly over a GS. As illustrated in Fig. 1, we show how collision avoidance can be integrated into a reactive controller by incorporating additional constraints and cost terms into a  \nThe authors are with the QUT Centre For Robotics, School of Electrical Engineering and Robotics at the Queensland University of Technology, Brisbane, QLD 4000, Australia. This research was partially supported by the QUT Centre for Robotics and by funding from ARC DECRA Fellowship DE240100149 to TF. Email: [nicolas.marticorena@hdr.qut.edu.au](nicolas.marticorena@hdr.qut.edu.au)  \nFig. 1. Illustration of our reactive control approach for a mobile manipulator tasked with reaching a 3D pose inside a bookshelf. The scene is represented as a 2D Gaussian Splat, visualised as ellipsoids in the Front view. The controller computes joint velocities to drive the robot toward the target pose, producing the yellow end-effector and blue base trajectories. Collision avoidance is enforced through hard and soft constraints, shown as red line segments derived from distance estimates against the Gaussian Splat.  \nQuadratic Program (QP) . Importantly, we show how both the geometry (i.e., position and shape) and the opacity of the Gaussian Splats must be considered for successful obstacle avoidance in clutt","cbCaik7O2VEWTxO7","https://ap.wps.com/l/cbCaik7O2VEWTxO7","pdf",8611532,1,"English","en",105,"# Introduction\n# Related Works\n## Collision avoidance in motion generation\n## Gaussian Splatting in robotics","[{\"question\":\"What problem does ReMoSPLAT address in mobile manipulation?\",\"answer\":\"It addresses how to represent the environment accurately enough for collision-free motion in reactive mobile manipulation without relying on costly global planning.\"},{\"question\":\"How does ReMoSPLAT perform collision avoidance?\",\"answer\":\"It formulates reactive control as a quadratic program and leverages a Gaussian Splat representation, integrating additional constraints and cost terms to avoid obstacles while reaching the target end-effector pose.\"},{\"question\":\"What trade-offs are evaluated for robot-obstacle distance computation?\",\"answer\":\"The work compares a purely geometric method with a rasterisation-based approach that accounts for opacity in Gaussian Splatting, assessing accuracy and efficiency differences.\"}]",1784203903,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":26},"remosplat-reactive-mobile-manipulation-control-on-a-gaussian-splat","",{"@graph":34,"@context":84},[35,52,67],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/remosplat-reactive-mobile-manipulation-control-on-a-gaussian-splat/85479/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","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 problem does ReMoSPLAT address in mobile manipulation?","Question",{"text":74,"@type":75},"It addresses how to represent the environment accurately enough for collision-free motion in reactive mobile manipulation without relying on costly global planning.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does ReMoSPLAT perform collision avoidance?",{"text":79,"@type":75},"It formulates reactive control as a quadratic program and leverages a Gaussian Splat representation, integrating additional constraints and cost terms to avoid obstacles while reaching the target end-effector pose.",{"name":81,"@type":72,"acceptedAnswer":82},"What trade-offs are evaluated for robot-obstacle distance computation?",{"text":83,"@type":75},"The work compares a purely geometric method with a rasterisation-based approach that accounts for opacity in Gaussian Splatting, assessing accuracy and efficiency differences.","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":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":44,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":44,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":44,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":44,"category_name":124,"show_sort_weight":27,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":127,"show_sort_weight":27,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":44,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":44,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]