Manuel Bianchi Bazzi, Asad Ali Shahid, Christopher Agia, John Alora, Marco Forgione, Dario Piga, Francesco Braghin, Marco Pavone, Loris Roveda
{"title":"机器人变形:机器人动力学建模的上下文元学习","authors":"Manuel Bianchi Bazzi, Asad Ali Shahid, Christopher Agia, John Alora, Marco Forgione, Dario Piga, Francesco Braghin, Marco Pavone, Loris Roveda","doi":"arxiv-2409.11815","DOIUrl":null,"url":null,"abstract":"The landscape of Deep Learning has experienced a major shift with the\npervasive adoption of Transformer-based architectures, particularly in Natural\nLanguage Processing (NLP). Novel avenues for physical applications, such as\nsolving Partial Differential Equations and Image Vision, have been explored.\nHowever, in challenging domains like robotics, where high non-linearity poses\nsignificant challenges, Transformer-based applications are scarce. While\nTransformers have been used to provide robots with knowledge about high-level\ntasks, few efforts have been made to perform system identification. This paper\nproposes a novel methodology to learn a meta-dynamical model of a\nhigh-dimensional physical system, such as the Franka robotic arm, using a\nTransformer-based architecture without prior knowledge of the system's physical\nparameters. The objective is to predict quantities of interest (end-effector\npose and joint positions) given the torque signals for each joint. This\nprediction can be useful as a component for Deep Model Predictive Control\nframeworks in robotics. The meta-model establishes the correlation between\ntorques and positions and predicts the output for the complete trajectory. This\nwork provides empirical evidence of the efficacy of the in-context learning\nparadigm, suggesting future improvements in learning the dynamics of robotic\nsystems without explicit knowledge of physical parameters. Code, videos, and\nsupplementary materials can be found at project website. See\nhttps://sites.google.com/view/robomorph/","PeriodicalId":501031,"journal":{"name":"arXiv - CS - Robotics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling\",\"authors\":\"Manuel Bianchi Bazzi, Asad Ali Shahid, Christopher Agia, John Alora, Marco Forgione, Dario Piga, Francesco Braghin, Marco Pavone, Loris Roveda\",\"doi\":\"arxiv-2409.11815\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The landscape of Deep Learning has experienced a major shift with the\\npervasive adoption of Transformer-based architectures, particularly in Natural\\nLanguage Processing (NLP). Novel avenues for physical applications, such as\\nsolving Partial Differential Equations and Image Vision, have been explored.\\nHowever, in challenging domains like robotics, where high non-linearity poses\\nsignificant challenges, Transformer-based applications are scarce. While\\nTransformers have been used to provide robots with knowledge about high-level\\ntasks, few efforts have been made to perform system identification. This paper\\nproposes a novel methodology to learn a meta-dynamical model of a\\nhigh-dimensional physical system, such as the Franka robotic arm, using a\\nTransformer-based architecture without prior knowledge of the system's physical\\nparameters. The objective is to predict quantities of interest (end-effector\\npose and joint positions) given the torque signals for each joint. This\\nprediction can be useful as a component for Deep Model Predictive Control\\nframeworks in robotics. The meta-model establishes the correlation between\\ntorques and positions and predicts the output for the complete trajectory. This\\nwork provides empirical evidence of the efficacy of the in-context learning\\nparadigm, suggesting future improvements in learning the dynamics of robotic\\nsystems without explicit knowledge of physical parameters. Code, videos, and\\nsupplementary materials can be found at project website. See\\nhttps://sites.google.com/view/robomorph/\",\"PeriodicalId\":501031,\"journal\":{\"name\":\"arXiv - CS - Robotics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Robotics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11815\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11815","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling
The landscape of Deep Learning has experienced a major shift with the
pervasive adoption of Transformer-based architectures, particularly in Natural
Language Processing (NLP). Novel avenues for physical applications, such as
solving Partial Differential Equations and Image Vision, have been explored.
However, in challenging domains like robotics, where high non-linearity poses
significant challenges, Transformer-based applications are scarce. While
Transformers have been used to provide robots with knowledge about high-level
tasks, few efforts have been made to perform system identification. This paper
proposes a novel methodology to learn a meta-dynamical model of a
high-dimensional physical system, such as the Franka robotic arm, using a
Transformer-based architecture without prior knowledge of the system's physical
parameters. The objective is to predict quantities of interest (end-effector
pose and joint positions) given the torque signals for each joint. This
prediction can be useful as a component for Deep Model Predictive Control
frameworks in robotics. The meta-model establishes the correlation between
torques and positions and predicts the output for the complete trajectory. This
work provides empirical evidence of the efficacy of the in-context learning
paradigm, suggesting future improvements in learning the dynamics of robotic
systems without explicit knowledge of physical parameters. Code, videos, and
supplementary materials can be found at project website. See
https://sites.google.com/view/robomorph/