[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84944-en":3,"doc-seo-84944-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"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},84944,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","A Continual Learning Framework for Adaptive Control of Modular Soft Robots","A continual learning inspired control framework (SMPL) enables modular soft robot controllers to adapt incrementally when robot morphology changes due to module attachment or detachment, while preserving previously acquired knowledge. The framework sequentially learns new MSR configurations without forgetting earlier ones. For fixed configurations, SMPL can operate in a distributed manner to learn module-specific dynamics, yielding localized control and improved precision. Validation includes closed-loop trajectory tracking in simulation and on a real three-module pneumatic soft robotic arm, plus adaptive module activation for reaching tasks.","Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.  \nDigital Object Identifier 10.1109/ACCESS.2024.0429000  \nA Continual Learning Framework for Adaptive Control of Modular Soft Robots  \n[ cs .RO] 7  \ning class of robotic systems with highly deformable and reconfigurable structures capable of performing complex tasks. However, designing controllers for MSRs remains challenging due to their nonlinear dynamics, modeling complexity, and hyper-redundant nature. Existing approaches typically require controllers to be retrained from scratch whenever the robot morphology changes because of module attachment or detachment. Furthermore, for MSRs with fixed morphology, many methods rely on a single centralized controller trained across all modules, which limits modularity, reduces scalability, and can lead to error propagation across the system over time. In this work, we address these challenges through a continual learning inspired control framework capable of incrementally adapting to changes in robot morphology while  \npreserving previously acquired knowledge. Specifically, the proposed framework enables the controller to sequentially learn new MSR configurations without forgetting previously learned ones. In addition, forMSRs with fixed configurations, the same framework can be employed in a distributed manner to learn modulespecific dynamics, enabling localized control and improved precision. The proposed approach is validated through closed-loop trajectory tracking experiments in simulation using a tendon-driven soft robot, as well as on a real-world three-module pneumatic soft robotic arm. Furthermore, we demonstrate the adaptive capabilities of the framework through a reaching experiment in which the controller selectively activates only the necessary modules to reach a virtual target position, thereby reducing computational overhead.  \nINDEX TERMS Continual Learning, Incremental Learning, Modular Soft Robot, Distributed Control, Progressive Neural Networks, Pose Control, Modular Control  \nINTRODUCTION MSRs offers enhanced flexibility and adaptability to diverse  \nTaking inspiration from the morphology of biological organisms, modular soft robots (MSRs) [1] are designed tobe flexible and compliant, enabling effective operation in unstructured environments [2] . Due to inherent compliance and safe interaction with the environment, soft robots have found applications across diverse domains such as medical interventions, wearable technologies, navigation, and agriculture [3], [4] . The modular and reconfigurable design of  \ntask requirements. Compared to single-module robots, MSRs possess a higher number of active degree of freedom (DOFs), allowing them to access larger workspaces and jointly perform more complex tasks. However, their hyper-redundancy, non-linear material properties, and complex dynamics make  \naccurate modeling and control particularly challenging [5] .  \nA wide range of modeling and control strategies have been proposed in the literature, broadly categorized into model-  \nFIGURE 1. SMPL architecture for the Exp1S experiment. Sub-networks are incrementally added and trained on motor babbling data for different MSR configurations, with lateral connections enabling knowledge transfer during sequential learning. The framework is evaluated across five MSR configurations.  \nbased and model-free approaches [6] . While model-based methods often provide faster and, in many cases, guaranteed convergence, their performance degrades when the robot operates in unpredictable environments [7] or when system dynamics evolve over time [8] . Moreover, the non-linear and hysteretic behavior of soft materials, coupled with the increased dimensionality of input variables in modular configurations, further complicates the modeling process [9] . To overcome these limitations, a variety of learning-based approaches have been explored in the literature to capture the kinematics and dynamics of soft robots [5] . Tra","cbCaivE1Q9tWZWcd","https://ap.wps.com/l/cbCaivE1Q9tWZWcd","pdf",4338238,1,12,"English","en",105,"# Introduction\n## Challenges in Modular Soft Robot Control\n## Modeling and Learning Approaches\n## Continual Learning-Based Adaptive Control Framework","[{\"question\":\"What problem does the proposed continual learning framework address for modular soft robots?\",\"answer\":\"It addresses the need for controllers to adapt to changing robot morphology without retraining from scratch and without forgetting previously learned behaviors.\"},{\"question\":\"How does the SMPL framework handle new robot configurations?\",\"answer\":\"SMPL sequentially adds and trains components so the controller can learn new MSR configurations while retaining knowledge from earlier configurations.\"},{\"question\":\"How is adaptive module activation used in the reaching experiment?\",\"answer\":\"The controller selectively activates only the modules necessary to reach a virtual target position, reducing computational overhead.\"}]",1784199624,30,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"a-continual-learning-framework-for-adaptive-control-of-modular-soft-robots","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"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":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/a-continual-learning-framework-for-adaptive-control-of-modular-soft-robots/84944/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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},"What problem does the proposed continual learning framework address for modular soft robots?","Question",{"text":75,"@type":76},"It addresses the need for controllers to adapt to changing robot morphology without retraining from scratch and without forgetting previously learned behaviors.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the SMPL framework handle new robot configurations?",{"text":80,"@type":76},"SMPL sequentially adds and trains components so the controller can learn new MSR configurations while retaining knowledge from earlier configurations.",{"name":82,"@type":73,"acceptedAnswer":83},"How is adaptive module activation used in the reaching experiment?",{"text":84,"@type":76},"The controller selectively activates only the modules necessary to reach a virtual target position, reducing computational overhead.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]