Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Peter Yichen, Liu, Chao, Ma, Pingchuan, Eastman, John, Rus, Daniela, Randle, Dylan, Ivanov, Yuri, Matusik, Wojciech
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916646660079616
author Chen, Peter Yichen
Liu, Chao
Ma, Pingchuan
Eastman, John
Rus, Daniela
Randle, Dylan
Ivanov, Yuri
Matusik, Wojciech
author_facet Chen, Peter Yichen
Liu, Chao
Ma, Pingchuan
Eastman, John
Rus, Daniela
Randle, Dylan
Ivanov, Yuri
Matusik, Wojciech
contents Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates object properties by using information from the robot, without relying on data from the object itself. Specifically, we utilize robot joint encoder information, which is commonly available in standard robotic systems. Our key observation is that by analyzing the robot's reactions to manipulated objects, we can infer properties of those objects, such as inertia and softness. Leveraging this insight, we develop differentiable simulations of robot-object interactions to inversely identify the properties of the manipulated objects. Our approach relies solely on proprioception -- the robot's internal sensing capabilities -- and does not require external measurement tools or vision-based tracking systems. This general method is applicable to any articulated robot and requires only joint position information. We demonstrate the effectiveness of our method on a low-cost robotic platform, achieving accurate mass and elastic modulus estimations of manipulated objects with just a few seconds of computation on a laptop.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03920
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction
Chen, Peter Yichen
Liu, Chao
Ma, Pingchuan
Eastman, John
Rus, Daniela
Randle, Dylan
Ivanov, Yuri
Matusik, Wojciech
Robotics
Artificial Intelligence
Computational Engineering, Finance, and Science
Computer Vision and Pattern Recognition
Computational Physics
Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates object properties by using information from the robot, without relying on data from the object itself. Specifically, we utilize robot joint encoder information, which is commonly available in standard robotic systems. Our key observation is that by analyzing the robot's reactions to manipulated objects, we can infer properties of those objects, such as inertia and softness. Leveraging this insight, we develop differentiable simulations of robot-object interactions to inversely identify the properties of the manipulated objects. Our approach relies solely on proprioception -- the robot's internal sensing capabilities -- and does not require external measurement tools or vision-based tracking systems. This general method is applicable to any articulated robot and requires only joint position information. We demonstrate the effectiveness of our method on a low-cost robotic platform, achieving accurate mass and elastic modulus estimations of manipulated objects with just a few seconds of computation on a laptop.
title Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction
topic Robotics
Artificial Intelligence
Computational Engineering, Finance, and Science
Computer Vision and Pattern Recognition
Computational Physics
url https://arxiv.org/abs/2410.03920