[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122720-en":3,"doc-seo-122720-105":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":4,"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":27,"seo_description":14,"update_tm":28,"read_time":29},122720,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",6,"Technology","Machine Learning-Driven Burrowing with a Snake-Like Robot - Proof of Concept","Subterranean burrowing is challenging for robots due to extreme contact forces and substantial uncertainty in granular media. To address the difficulty of modeling these forces, the work proposes a machine-learning control strategy for optimal vertical self-burrowing. A snake-like, bio-inspired robot is built with an IMU and dual triple-axis magnetometers, using magnetic field strength as a depth proxy. A deep learning architecture based on sinusoidal and random data learns an efficient control policy that outperforms standard techniques and reaches targeted depths automatically.","Machine Learning-Driven Burrowing with a  \nSnake-Like Robot  \nSean Even*, Holden Gordon*, Hoeseok Yang, Yasemin Ozkan-Aydin  \narXiv :2309 . 10802v1 [ cs .RO] 19 Sep 2023  \nAbstract—Subterranean burrowing is inherently difficult for robots because of the high forces experienced as well as the high amount of uncertainty in this domain. Because of the difficulty in modeling forces in granular media, we propose the use of a novel machine-learning control strategy to obtain optimal techniques for vertical self-burrowing. In this paper, we realize a snake-like bio-inspired robot that is equipped with an IMU and two triple-axis magnetometers. Utilizing magnetic field strength as an analog for depth, a novel deep learning architecture was proposed based on sinusoidal and random data in order to obtain a more efficient strategy for vertical selfburrowing. This strategy was able to outperform many other standard burrowing techniques and was able to automatically reach targeted burrowing depths. We hope these results will serve as a proof of concept for how optimization can be used to unlock the secrets of navigating in the subterranean world more efficiently.  \nI. INTRODUCTION  \nThe task of excavation and subterranean penetration presents substantial challenges owing to the dynamic forces exerted by the subterranean environment [1], [2], [3] . This has driven numerous organisms to evolve specialized mechanisms aimed at reducing energy consumption, thereby enabling them to achieve precise outcomes without resorting to extensive soil displacement[4] . For example, plant roots employ strategies such as tip extension and circumnutationto efficiently gather nutrients from beneath the soil [5] . In the animal kingdom, body structures such as asymmetric head shape and limb movements to create granular fluidization help biological organisms move through the soil more effectively [6] . Furthermore, soft-bodied organisms such as earthworms utilize gaits such as retrograde peristalsis to achieve motion through soil by reappropriating body mass [7] .  \nThe creation of burrowing robots is an emerging field of study that develops systems that can be used for applications like emergency response, soil analysis in agriculture, and exploring other planets. Traversing through subterranean environments is quite difficult as the robot must be able to withstand forces that can be orders of magnitude higher than in air and water [8] .  \nWhile the study of burrowing robots is relatively new, a few important studies have laid the groundwork for fossorial locomotion. These studies largely fall into two classes: softburrowing robots and rigid-body burrowing robots. Softburrowing robots are inspired by earthworm locomotion and  \n* These authors contributed equally.  \nS. Even and Y. Ozkan-Aydin are with the University of Notre Dame  \nH. Gordon and H. Yang are with Santa Clara University  \nFig. 1. Biological and robotic snake burrowing in granular media. A Biological example of snake burrowing in the sand, B Snake robot in a testing environment filled with packing peanuts, C Snake Robot consists of a chain of five Dynamixel 2XL430 servos, two 11.1V batteries located at head and tail, 9-DoF IMU, two 3-DoF magnetometers and an Open-CM controller. The colored stickers show the segments of the robot. The arrows in the first segment of the robot show the direction of the rotation axis of the servo. All the servos at the segments are oriented in the same direction.  \nroot growth in plants. Liu et al. designed a soft robot that combines Kirigami skin and radially expanding pneumatic actuators to mimic earthworm anchoring mechanisms [9] . Naclerio et al. developed a steerable vine robot for subterranean locomotion, achieving significantly faster burrowing speeds and obstacle navigation using granular fluidization [6] .  \nRigid-body burrowing robots have drawn inspiration from animals in nature that dig into the soil such as the mole crab. Russel presented CRABOT, a burrowi","cbCait3iphws5V5S","https://ap.wps.com/l/cbCait3iphws5V5S","pdf",2696967,1,7,"English","en",105,"# Introduction\n## Challenges in subterranean penetration\n## Bio-inspired excavation and locomotion\n## Classes of burrowing robots\n## Machine learning for nonlinear uncertain dynamics","[{\"question\":\"Why is subterranean burrowing difficult for robots?\",\"answer\":\"Burrowing requires handling very high forces and operating under significant uncertainty within granular media, making accurate modeling difficult.\"},{\"question\":\"What sensing approach is used to estimate depth?\",\"answer\":\"The robot uses magnetic field strength from magnetometers as an analog for depth during vertical self-burrowing.\"},{\"question\":\"How does the proposed method improve performance compared with standard techniques?\",\"answer\":\"A deep learning control architecture learns an efficient strategy from sinusoidal and random data, enabling automatic arrival at target depths and outperforming many baseline burrowing approaches.\"}]","Machine Learning-Driven Burrowing with a Snake-Like Robot - Proof of Concept | PDF",1785812524,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-driven-burrowing-with-a-snake-like-robot-proof-of-concept","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-driven-burrowing-with-a-snake-like-robot-proof-of-concept/122720/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is subterranean burrowing difficult for robots?","Question",{"text":75,"@type":76},"Burrowing requires handling very high forces and operating under significant uncertainty within granular media, making accurate modeling difficult.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What sensing approach is used to estimate depth?",{"text":80,"@type":76},"The robot uses magnetic field strength from magnetometers as an analog for depth during vertical self-burrowing.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed method improve performance compared with standard techniques?",{"text":84,"@type":76},"A deep learning control architecture learns an efficient strategy from sinusoidal and random data, enabling automatic arrival at target depths and outperforming many baseline burrowing approaches.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"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":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":114,"show_sort_weight":115,"slug":116},"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",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"]