[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83132-en":3,"doc-seo-83132-105":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":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":13,"seo_description":14,"update_tm":28,"read_time":29},83132,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","EvoPlan Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees","LLM-based robot planners can produce fluent action plans but cannot inherently guarantee executability or safety, while classical PDDL planners offer formal guarantees only after complete problem specification and may fail to leverage contextual reasoning. EvoPlan introduces a neuro-symbolic pipeline that extracts a single global mobility constraint from demonstrations via Signal Temporal Logic using locally hosted open-weight LLMs, then fits it through evolutionary search. An evolutionary PDDL planner proposes and repairs candidates under symbolic validation, followed by constrained execution with waypoint monitoring and replanning on violations, demonstrated in Gazebo and evaluated on ALFWorld Text.","arXiv :2607 .06724v 1 [ cs .RO] 7 Jul 2026  \nEvoPlan: Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees  \nBhavya Sai Nukapotula Samin Moosavi Haoze Wang Luke Duncan  \nDiya Shakkottai∗ Varun Murali Srinivas Shakkottai  \nTexas A&M University  \nAbstract  \nLLM-based robot planners are fluent but cannot guarantee that their plans are executable or safe.  \nClassical PDDL planners can guarantee these properties, but only after the problem is fully specified, and they make poor use of an LLM’s ability to read context and repair plans. This paper presents aneuro-symbolic framework with three parts. All LLM calls use a locally-hosted open-weight model, so the pipeline can be deployed on-robot with no cloud dependency. First, an offline procedure that mines a single global Signal Temporal Logic (STL) constraint on mobility from demonstration data. The procedure recovers codified rules (e.g., stopping at red lights, mined from nuPlan driving logs) or population preferences (e.g., social-navigation comfort, mined from SCAND teleoperation), depending on what the demonstrations encode. Because the demonstrations are a one-class signal, we generate the missing negatives with counterfactual perturbations and an LLM violation generator and then fit the constraint by evolutionary search. We use the mined constraint to shield a vision-language driving policy on Bench2Drive and two discrete-action navigation policies on HA-VLN-CE. Second, an evolutionary PDDL planner: an LLM proposes and repairs plans, programmatic validators decide which ones survive, and the validated portion of the plan grows over iterations. We test the planner on the open-world ALFWorld Text benchmark, where it beats strong baselines and stays robust when the goal vocabulary does not match the action-model vocabulary. Third, a constrained execution loop: the planner’s plan is compiled into waypoints, the waypoints are checked against the mined constraint, and the planner re-plans on a violation. We illustrate the full pipeline via demonstrations using the Gazebo simulator.  \nKeywords: Neuro-symbolic planning, planning domain description language (PDDL), signal temporal logic (STL), safety guarantees, constrained control  \n1 Introduction  \nLLM and vision-language models can transform natural instructions, images, and demonstrations into plausible action proposals, but a pure LLM-based plan does not by itself guarantee executability or safety. Conversely, classical PDDL planners give machine-checkable guarantees only after a problem is fully formalised, and they underuse LLMs’ ability to read context and propose repairs. This paper takes a best-of-both-worlds view: a neural model generates and repairs candidate plans, while symbolic validation and data-derived temporal-logic constraints decide which candidates may be executed.  \n∗ Student at Westwood High School; work done as an intern at Texas A&M University.  \nOffline constraint extraction  \nEvolutionary PDDL solving and constrained deployment  \nFigure 1: System overview. Offline, expert demonstrations are reduced to kinematic and social signals; counterfactual negatives turn the one-class data into contrastive sets D+/D − , and evolutionary STL fitting produces a single global mobility constraint. Online, a task together with its PDDL domain/state is consumed by an evolutionary PDDL solver and verified by PDDL validation; the resulting plan is then expanded into waypoints by a trajectory planner, which are subjected to the global STL check and executed under online monitoring and replanning.  \nFigure 1 shows the offline mining pipeline (top row) and the online plan-and-check loop (bottom row) . In our framework the LLM is not a standalone planner but a proposal mechanism inside a machine-checkable loop. All LLM calls run on a locally-hosted open-weight model (Qwen3-32B in our experiments), supporting on-robot deployment with no cloud dependency. We instantiate this view with three contributions. The ","cbCaipXtYyIOnlzP","https://ap.wps.com/l/cbCaipXtYyIOnlzP","pdf",2613168,2,1,24,"English","en",105,"# Introduction\n# Offline Constraint Extraction\n# Evolutionary PDDL Solving\n# Constrained Deployment","[{\"question\":\"Why can LLM-based robot planners struggle to guarantee safety and executability?\",\"answer\":\"They can generate plausible plans from language or context, but they do not inherently provide machine-checkable guarantees that the resulting actions are executable and safe.\"},{\"question\":\"How does EvoPlan derive safety constraints from demonstration data?\",\"answer\":\"It mines a single global Signal Temporal Logic (STL) mobility constraint from one-class acceptable demonstrations, synthesizing missing negatives using counterfactual perturbations and an LLM violation generator, then fits the constraint with evolutionary search.\"},{\"question\":\"How does the system handle constraint violations during execution?\",\"answer\":\"The plan is compiled into waypoints, checked against the mined STL constraint, and when a violation occurs the system rejects the action, commits the verified prefix, updates the initial state, and re-plans.\"}]",1784185507,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"evoplan-evolutionary-neuro-symbolic-robot-planning-with-spatio-temporal-guarantees","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/evoplan-evolutionary-neuro-symbolic-robot-planning-with-spatio-temporal-guarantees/83132/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why can LLM-based robot planners struggle to guarantee safety and executability?","Question",{"text":75,"@type":76},"They can generate plausible plans from language or context, but they do not inherently provide machine-checkable guarantees that the resulting actions are executable and safe.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does EvoPlan derive safety constraints from demonstration data?",{"text":80,"@type":76},"It mines a single global Signal Temporal Logic (STL) mobility constraint from one-class acceptable demonstrations, synthesizing missing negatives using counterfactual perturbations and an LLM violation generator, then fits the constraint with evolutionary search.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the system handle constraint violations during execution?",{"text":84,"@type":76},"The plan is compiled into waypoints, checked against the mined STL constraint, and when a violation occurs the system rejects the action, commits the verified prefix, updates the initial state, and re-plans.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"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":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]