Accurate Vision-based Manipulation through Contact Reasoning

被引:0
|
作者
Kloss, Alina [1 ]
Bauza, Maria [2 ]
Wu, Jiajun [2 ,3 ]
Tenenbaum, Joshua B. [2 ]
Rodriguez, Alberto [2 ]
Bohg, Jeannette [1 ,3 ]
机构
[1] Max Planck Inst Intelligent Syst, Stuttgart, Germany
[2] MIT, Cambridge, MA 02139 USA
[3] Stanford Univ, Stanford, CA 94305 USA
关键词
D O I
10.1109/icra40945.2020.9197409
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Planning contact interactions is one of the core challenges of many robotic tasks. Optimizing contact locations while taking dynamics into account is computationally costly and, in environments that are only partially observable, executing contact-based tasks often suffers from low accuracy. We present an approach that addresses these two challenges for the problem of vision-based manipulation. First, we propose to disentangle contact from motion optimization. Thereby, we improve planning efficiency by focusing computation on promising contact locations. Second, we use a hybrid approach for perception and state estimation that combines neural networks with a physically meaningful state representation. In simulation and real-world experiments on the task of planar pushing, we show that our method is more efficient and achieves a higher manipulation accuracy than previous vision-based approaches.
引用
收藏
页码:6738 / 6744
页数:7
相关论文
共 50 条
  • [41] An Automatic Vision-based Monitoring System for Accurate Vojta-Therapy
    Khan, Muhammad Hassan
    Helsper, Julien
    Yang, Cong
    Grzegorzek, Marcin
    2016 IEEE/ACIS 15TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE (ICIS), 2016, : 379 - 384
  • [42] Large scale vision-based navigation without an accurate global reconstruction
    Segvic, Siniga
    Remazeilles, Anthony
    Diosi, Albert
    Chaumette, Francois
    2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 2007, : 422 - +
  • [43] Vision-Based Fall Detection Through Shape Features
    Lin, Chih-Yang
    Wang, Shang-Ming
    Hong, Jia-Wei
    Kang, Li-Wei
    Huang, Chung-Lin
    2016 IEEE SECOND INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM), 2016, : 237 - 240
  • [44] Robotic wheelchair controlled through a vision-based interface
    Perez, Elisa
    Soria, Carlos
    Nasisi, Oscar
    Bastos, Teodiano Freire
    Mut, Vicente
    ROBOTICA, 2012, 30 : 691 - 708
  • [45] Efficient Vision-Based Face Image Manipulation Identification Framework Based on Deep Learning
    Minh Dang
    ELECTRONICS, 2022, 11 (22)
  • [46] NormalFlow: Fast, Robust, and Accurate Contact-Based Object 6DoF Pose Tracking With Vision-Based Tactile Sensors
    Huang, Hung-Jui
    Kaess, Michael
    Yuan, Wenzhen
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2025, 10 (01): : 452 - 459
  • [47] Vision-based Hand Representation and Intuitive Virtual Object Manipulation in Mixed Reality
    Bach, F.
    Cakmak, H.
    Maass, H.
    BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK, 2012, 57 : 462 - 465
  • [48] DESIGN OF AN AFFORDABLE PROSTHETIC ARM EQUIPPED WITH DEEP LEARNING VISION-BASED MANIPULATION
    Imran, Alishba
    Escobar, William
    Barez, Fred
    PROCEEDINGS OF ASME 2021 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION (IMECE2021), VOL 6, 2021,
  • [49] Vision-Based Solutions for Robotic Manipulation and Navigation Applied to Object Picking and Distribution
    Roa-Garzon, Maximo A.
    Gambaro, Elena F.
    Florek-Jasinska, Monika
    Endres, Felix
    Ruess, Felix
    Schaller, Raphael
    Emmerich, Christian
    Muenster, Korbinian
    Suppa, Michael
    KUNSTLICHE INTELLIGENZ, 2019, 33 (02): : 171 - 180
  • [50] Construction of Vision-based Manipulation System for 3D Industrial Objects
    Zhao, Guangtao
    Jia, Ying
    Ou, Zhicai
    2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO 2009), VOLS 1-4, 2009, : 1051 - +