[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126660-en":3,"doc-seo-126660-105":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},126660,549768064778,"Finn","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","AUTONOMOUS ROBOTIC ARM MANIPULATION FOR PLANETARY MISSIONS USING CAUSAL MACHINE LEARNING - Paper abstract","Autonomous robotic arm manipulators can improve the efficiency of planetary exploration and in-situ resource utilization by handling objects and executing goal-specific actions. The work trains a manipulator to study objects without prior knowledge, such as planetary rocks, in a simulated planetary environment. Causal machine learning guides interaction-based classification using causal factors like mass and friction. Reinforcement learning helps the system choose actions that reveal the underlying parameters, achieving performance without prior knowledge or previously collected training data, using realistic manipulator models under exploration-like conditions.","In: ASTRA 2023: 17th Symposium on Advanced Space Technologies in Robotics and Automation, Leiden, 18-20 October 2023 .  \nDOI:TBC  \nAUTONOMOUS ROBOTIC ARM MANIPULATION FOR PLANETARY MISSIONS USING  \nCAUSAL MACHINE LEARNING  \nCian McDonnell 1 , Miguel Arana-Catania2 , and Saurabh Upadhyay2  \n1 MSc Astronautics and Space Engineering, Cran􀀂eld University, United Kingdom, cian@mcdonnell.eu  \n2 School of Aerospace, Transport and Manufacturing, Cran􀀂eld University, United Kingdom,  \nmiguel.aranacatania@cran􀀂eld.ac.uk, saurabh.upadhyay@cran􀀂eld.ac.uk  \nABSTRACT  \nAutonomous robotic arm manipulators have the potential to make planetary exploration and in-situ resource utilization missions more time ef􀀂cient and productive, as the manipulator can handle the objects itself and perform goal-speci􀀂c actions. We train a manipulator to autonomously study objects of which it has no prior knowledge, such as planetary rocks. This is achieved using causal machine learning in a simulated planetary environment. Here, the manipulator interacts with objects, and classi􀀂es them based on differing causal factors. These are parameters, such as mass or friction coef􀀂 -cient, that causally determine the outcomes of its interactions. Through reinforcement learning, the manipulator learns to interact in ways that reveal the underlying causal factors. We show that this method works even without any prior knowledge of the objects, or any previouslycollected training data. We carry out the training in planetary exploration conditions, with realistic manipulator models.  \nKey words: Planetary manipulators; reinforcement learning; interaction-based learning; planetary exploration; causal analysis.  \n1. INTRODUCTION  \nAutonomous manipulation has signi􀀂cant potential in planetary missions, as it can increase the amount of time spent exploring the environment and doing science activities. We review current methods for autonomous manipulation of objects, both on Earth and in planetary exploration environments. We see that approaches to manipulation of unknown objects usually must leverage a large amount of training data to work.  \nReinforcement learning is commonly used to teach a robot manipulator certain skills, such as pick and place operations on objects, to solve speci􀀂c tasks. In [1] the manipulator chooses its policy from a set of actions, andover time learns to use more of those actions that gave the  \nbest results in the past. These are scored based on how close the object gets to a target position. Here we follow a different causal approach [2] using reinforcement learning to 􀀂nd which actions give the most information about the “causal factors”, the main parameters that determine the dynamics of the objects, so that this knowledge can be used to carry out any general task. The manipulator learns which actions produce the most distinguishable interactions for each factor. For example, it may learn about an object’s frictional properties by pushing it along the ground, and studying the distance travelled, which is directly affected by the friction.  \nThere are relatively few papers on autonomous manipulators in planetary environments. Typically, two types of objects are considered in the existing literature: known objects where the robot has prior knowledge (e.g. size, shape, mass of a known scienti􀀂c device), and objects which are completely unknown to the robot, e.g. planetary rocks. In [3], the authors present a design for a light-weight rover that can pick up and assemble known objects. The objects are detected based on machine-learning classi􀀂cation by colour. The same rover is used in [4] to demonstrate the placement, testing and collection of payload instruments, in a simulated lunar environment on Earth.  \nMore sophisticated techniques are required to learn to manipulate unknown objects. In [5], the authors train a robot to grasp objects on the Moon, using 3D octree representations of the environment. A convolutional neural network is used in conju","cbCaifWkh8PckUbv","https://ap.wps.com/l/cbCaifWkh8PckUbv","pdf",474794,1,9,"English","en",105,"# Abstract\n# 1. Introduction\n## Autonomous manipulation in planetary missions\n## Reinforcement learning and causal approaches\n## Prior work on planetary manipulators\n## Challenges and research gaps","[{\"question\":\"What problem does the paper address for planetary missions?\",\"answer\":\"It addresses how to perform autonomous manipulation in planetary environments when the robot has little or no prior knowledge about the target objects.\"},{\"question\":\"How does the approach differ from standard reinforcement learning methods?\",\"answer\":\"Instead of focusing only on task success, it uses a causal approach to learn which actions provide the most information about causal factors that determine object dynamics.\"},{\"question\":\"What causal factors does the manipulator learn to infer?\",\"answer\":\"It can infer parameters such as an object’s mass or friction coefficient, based on how outcomes change under different interactions.\"}]","AUTONOMOUS ROBOTIC ARM MANIPULATION FOR PLANETARY MISSIONS USING CAUSAL MACHINE LEARNING - Paper abstract | PDF",1785934083,23,{"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},"autonomous-robotic-arm-manipulation-for-planetary-missions-using-causal-machine-learning-paper-abstract","",{"@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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/autonomous-robotic-arm-manipulation-for-planetary-missions-using-causal-machine-learning-paper-abstract/126660/",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","2026-08-05",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},"What problem does the paper address for planetary missions?","Question",{"text":75,"@type":76},"It addresses how to perform autonomous manipulation in planetary environments when the robot has little or no prior knowledge about the target objects.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the approach differ from standard reinforcement learning methods?",{"text":80,"@type":76},"Instead of focusing only on task success, it uses a causal approach to learn which actions provide the most information about causal factors that determine object dynamics.",{"name":82,"@type":73,"acceptedAnswer":83},"What causal factors does the manipulator learn to infer?",{"text":84,"@type":76},"It can infer parameters such as an object’s mass or friction coefficient, based on how outcomes change under different interactions.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]