FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: He, Zihao, Fang, Hongjie, Chen, Jingjing, Fang, Hao-Shu, Lu, Cewu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912357378162688
author He, Zihao
Fang, Hongjie
Chen, Jingjing
Fang, Hao-Shu
Lu, Cewu
author_facet He, Zihao
Fang, Hongjie
Chen, Jingjing
Fang, Hao-Shu
Lu, Cewu
contents Contact-rich tasks present significant challenges for robotic manipulation policies due to the complex dynamics of contact and the need for precise control. Vision-based policies often struggle with the skill required for such tasks, as they typically lack critical contact feedback modalities like force/torque information. To address this issue, we propose FoAR, a force-aware reactive policy that combines high-frequency force/torque sensing with visual inputs to enhance the performance in contact-rich manipulation. Built upon the RISE policy, FoAR incorporates a multimodal feature fusion mechanism guided by a future contact predictor, enabling dynamic adjustment of force/torque data usage between non-contact and contact phases. Its reactive control strategy also allows FoAR to accomplish contact-rich tasks accurately through simple position control. Experimental results demonstrate that FoAR significantly outperforms all baselines across various challenging contact-rich tasks while maintaining robust performance under unexpected dynamic disturbances. Project website: https://tonyfang.net/FoAR/
format Preprint
id arxiv_https___arxiv_org_abs_2411_15753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation
He, Zihao
Fang, Hongjie
Chen, Jingjing
Fang, Hao-Shu
Lu, Cewu
Robotics
Contact-rich tasks present significant challenges for robotic manipulation policies due to the complex dynamics of contact and the need for precise control. Vision-based policies often struggle with the skill required for such tasks, as they typically lack critical contact feedback modalities like force/torque information. To address this issue, we propose FoAR, a force-aware reactive policy that combines high-frequency force/torque sensing with visual inputs to enhance the performance in contact-rich manipulation. Built upon the RISE policy, FoAR incorporates a multimodal feature fusion mechanism guided by a future contact predictor, enabling dynamic adjustment of force/torque data usage between non-contact and contact phases. Its reactive control strategy also allows FoAR to accomplish contact-rich tasks accurately through simple position control. Experimental results demonstrate that FoAR significantly outperforms all baselines across various challenging contact-rich tasks while maintaining robust performance under unexpected dynamic disturbances. Project website: https://tonyfang.net/FoAR/
title FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2411.15753