[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84251-en":3,"doc-seo-84251-105":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},84251,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","CARLA-GS Decoupling Representation Reasoning and Physics Simulation for Autonomous Driving Corner-Case Synthesis","Safety evaluation for autonomous driving depends on rare, safety-critical interactions, driving the need for simulators that can deliberately synthesize realistic corner cases with photorealistic sensing. Corner-case generation spans multiple sources: visual representation, semantic scene reasoning, and vehicle trajectory generation plus control. Prior methods isolate components or struggle with spatiotemporal consistency and physical realism. CARLA-GS unifies them by reconstructing an editable Gaussian scene from real data, using a multiagent LLM for risk reasoning and intent-level waypoints, and delegating low-level motion feasibility to CARLA with PID control, then reprojecting simulated states for ego-centric rendering. Experiments on Waymo show controllable synthesis and physically feasible, video-consistent results.","CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis  \nKaicong Huang 1 , Meng Ma 1 , Ruimin Ke 1∗  \narXiv :2607 .0760 1v 1 [ cs .RO] 8 Jul 2026  \nAbstract—Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize corner cases with photorealistic observations. Corner-case generation is inherently a multisource problem spanning visual representation, scene reasoning, and vehicle trajectory generation and control. Prior knowledgeand model-based approaches typically focus on scene or trajectory components in isolation, while diffusion-based methods attempt end-to-end generation but still struggle to ensurespatiotemporal consistency and physical realism. To unify these aspects within a single framework, we propose CARLA-GS, a modular corner-case synthesis pipeline that decouples visual representation, semantic reasoning, and physics-based execution while maintaining tight cross-module coupling. Starting from real driving data, we reconstruct an editable gaussian scene with additional geometry-consistent constraints. A multiagent LLM then performs scene-level reasoning to identify risky interactions and generate intent-level waypoint trajectories, while the low-level motion control is delegated to CARLA, where a PID controller ensures kinematic and dynamic feasibility. The simulated vehicle states are finally re-projected into the gaussian scene for ego-centric rendering. This design enables high-level semantic reasoning, low-level physically executable motion, and photorealistic corner-case generation within a unified pipeline. Experiments on the Waymo Open Datasetshow, both quantitatively and qualitatively, that our framework enables controllable corner-case generation and produces photorealistic, spatiotemporally consistent videos aligned with semantic intent and physically feasible motion.  \nI. INTRODUCTION  \nAutonomous driving (AD) operates in open-world traffic where safety evaluation is inherently a rare-event problem, known as the Curse of Rarity [1] . This motivates simulation pipelines that intentionally expose corner cases. Meanwhile, camera-centric AD systems require simulators to provide not only trajectory rollouts but also photorealistic observations for reliable closed-loop evaluation [2] .  \nThis requirement has renewed interest in scalable drivingscene reconstruction for safety-oriented simulation. NeRFbased methods achieve high-fidelity view synthesis but remain expensive for large-scale optimization and rendering [3], while diffusion-based world models provide strong generative diversity yet still struggle with physical plausibility and multi-view consistency under real-time constraints [4], [5] . In contrast, 3D/4D Gaussian Splatting (GS) [6], [7] enables real-time differentiable rendering with explicit scene primitives, making it attractive for urban driving simulation [8], [9], [10] . However, vanilla 3DGS is  \n1 Department of Civil and Environmental Engineering, Rensselaer Polytechnic Institute, 110 Eighth Street, Troy, NY USA 12180 .  \n∗ Corresponding author. Email: [ker@rpi.edu](ker@rpi.edu)  \ndesigned for photometric reconstruction, lacking instancelevel control over traffic participants and remaining sensitive to reconstruction artifacts that may affect occlusion or collision outcomes [11], [12] .  \nMoreover, corner-case generation is not purely a visual problem. It requires semantic reasoning over agent intent, interaction context, and future motion evolution. Prior work synthesizes corner cases through data-driven, knowledgebased, or learning-based pipelines [13], [14], [15] . However, these approaches often lack semantic scene understanding and high-level decision reasoning for identifying plausible risky interactions, limiting their flexibility in generating targeted behaviors. Inspired by [16], we adopt LLM-based reasoning as a semantic planning modu","cbCaia0ALoPD5Yzu","https://ap.wps.com/l/cbCaia0ALoPD5Yzu","pdf",6139775,2,1,"English","en",105,"# Introduction\n## Safety-critical rare-event simulation and corner cases\n## Scene reconstruction: NeRF, diffusion world models, and 3D/4D Gaussian Splatting\n## Limits of vanilla 3DGS and the need for semantic reasoning and physical execution\n## CARLA-GS modular decoupling framework overview","[{\"question\":\"What problem does CARLA-GS address in autonomous driving safety evaluation?\",\"answer\":\"It targets safety evaluation dominated by rare, safety-critical interactions by enabling deliberate synthesis of photorealistic corner cases for closed-loop testing.\"},{\"question\":\"How does CARLA-GS decouple representation, reasoning, and physics in its pipeline?\",\"answer\":\"It reconstructs an editable Gaussian scene for visual representation, uses a multiagent LLM for semantic reasoning and intent-level waypoint trajectories, and delegates low-level feasible control to CARLA with PID ensuring kinematic and dynamic feasibility.\"},{\"question\":\"How does CARLA-GS improve physical realism and spatiotemporal consistency compared with prior approaches?\",\"answer\":\"It avoids purely end-to-end diffusion generation by separating semantic intent generation from physics-consistent execution, then reprojects simulated vehicle states into the Gaussian scene for ego-centric photorealistic rendering.\"}]",1784194376,20,{"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},"carla-gs-decoupling-representation-reasoning-and-physics-simulation-for-autonomous-driving-corner-case-synthesis","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,46,49],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":20},"https://docshare.wps.com/document/","Document",{"item":47,"name":12,"@type":42,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/carla-gs-decoupling-representation-reasoning-and-physics-simulation-for-autonomous-driving-corner-case-synthesis/84251/",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","2026-07-27","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 CARLA-GS address in autonomous driving safety evaluation?","Question",{"text":74,"@type":75},"It targets safety evaluation dominated by rare, safety-critical interactions by enabling deliberate synthesis of photorealistic corner cases for closed-loop testing.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does CARLA-GS decouple representation, reasoning, and physics in its pipeline?",{"text":79,"@type":75},"It reconstructs an editable Gaussian scene for visual representation, uses a multiagent LLM for semantic reasoning and intent-level waypoint trajectories, and delegates low-level feasible control to CARLA with PID ensuring kinematic and dynamic feasibility.",{"name":81,"@type":72,"acceptedAnswer":82},"How does CARLA-GS improve physical realism and spatiotemporal consistency compared with prior approaches?",{"text":83,"@type":75},"It avoids purely end-to-end diffusion generation by separating semantic intent generation from physics-consistent execution, then reprojects simulated vehicle states into the Gaussian scene for ego-centric photorealistic rendering.","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":20,"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"]