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
  • [1] Vision-Based Foothold Contact Reasoning using Curved Surface Patches
    Kanoulas, Dimitrios
    Zhou, Chengxu
    Anh Nguyen
    Kanoulas, Georgios
    Caldwell, Darwin G.
    Tsagarakis, Nikos G.
    2017 IEEE-RAS 17TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTICS (HUMANOIDS), 2017, : 121 - 128
  • [2] Vision-based stratified robotic manipulation
    Wei, YJ
    Skaar, SB
    Goodwine, B
    2002 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-3, PROCEEDINGS, 2002, : 1638 - 1644
  • [3] Kinematics of stratified vision-based manipulation
    Wei, YJ
    Goodwine, B
    Skaar, SB
    ELEVENTH WORLD CONGRESS IN MECHANISM AND MACHINE SCIENCE, VOLS 1-5, PROCEEDINGS, 2004, : 1900 - 1905
  • [4] Vision-Based Contact Point Selection for the Fully Non-Fixed Contact Manipulation of Deformable Objects
    Han, Lijun
    Zhang, Yuyou
    Wang, Hesheng
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02): : 4368 - 4375
  • [5] A Vision-Based Micro-Manipulation System
    Vismanis, Oskars
    Arents, Janis
    Subaciute-Zemaitiene, Jurga
    Bucinskas, Vytautas
    Dzedzickis, Andrius
    Patel, Brijesh
    Tung, Wei-Cheng
    Lin, Po-Ting
    Greitans, Modris
    APPLIED SCIENCES-BASEL, 2023, 13 (24):
  • [6] Vision-based Belt Manipulation by Humanoid Robot
    Qin, Yili
    Escande, Adrien
    Tanguy, Arnaud
    Yoshida, Eiichi
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 3547 - 3552
  • [7] Reward Machines for Vision-Based Robotic Manipulation
    Camacho, Alberto
    Varley, Jacob
    Deng, Andy
    Jain, Deepali
    Iscen, Atil
    Kalashnikov, Dmitry
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 14284 - 14290
  • [8] Towards vision-based manipulation of plastic materials
    Cherubini, Andrea
    Leitner, Jurgen
    Ortenzi, Valerio
    Corke, Peter
    2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2018, : 485 - 490
  • [9] Vision-Based Robotic Manipulation of Flexible PCBs
    Li, Xiang
    Su, Xing
    Liu, Yun-Hui
    IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2018, 23 (06) : 2739 - 2749
  • [10] Vision-based manipulation with the humanoid robot Romeo
    Claudio, Giovanni
    Spindler, Fabien
    Chaumette, Francois
    2016 IEEE-RAS 16TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), 2016, : 286 - 293