Fundamental Challenges in Deep Learning for Stiff Contact Dynamics

被引:17
|
作者
Parmar, Mihir [1 ]
Halm, Mathew [1 ]
Posa, Michael [1 ]
机构
[1] Univ Penn, Grasp Lab, Philadelphia, PA 19104 USA
基金
美国国家科学基金会;
关键词
D O I
10.1109/IROS51168.2021.9636383
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Frictional contact has been extensively studied as the core underlying behavior of legged locomotion and manipulation, and its nearly-discontinuous nature makes planning and control difficult even when an accurate model of the robot is available. Here, we present empirical evidence that learning an accurate model in the first place can be confounded by contact, as modern deep learning approaches are not designed to capture this non-smoothness. We isolate the effects of contact's non-smoothness by varying the mechanical stiffness of a compliant contact simulator. Even for a simple system, we find that stiffness alone dramatically degrades training processes, generalization, and data-efficiency. Our results raise serious questions about simulated testing environments which do not accurately reflect the stiffness of rigid robotic hardware. Significant additional investigation will be necessary to fully understand and mitigate these effects, and we suggest several avenues for future study.
引用
收藏
页码:5181 / 5188
页数:8
相关论文
共 50 条
  • [1] On integrating stiff multibody dynamics with contact and friction
    Anitescu, M
    Potra, FA
    CONTACT MECHANICS, 2002, : 83 - 90
  • [2] Opportunities and challenges for deep learning in cell dynamics research
    Chai, Binghao
    Efstathiou, Christoforos
    Yue, Haoran
    Draviam, Viji M.
    TRENDS IN CELL BIOLOGY, 2024, 34 (11) : 955 - 967
  • [4] DEEP WELL CONDITIONS POSE STIFF CHALLENGES FOR ELASTOMERS
    WATKINS, MJ
    PETROLEUM ENGINEER INTERNATIONAL, 1983, 55 (05): : 50 - &
  • [5] Identification of Contact Dynamics Parameters for Stiff Robotic Payloads
    Verscheure, Diederik
    Sharf, Inna
    Bruyninckx, Herman
    Swevers, Jan
    De Schutter, Joris
    IEEE TRANSACTIONS ON ROBOTICS, 2009, 25 (02) : 240 - 252
  • [6] MANIPULATORS CONSTRAINED BY STIFF CONTACT - DYNAMICS, CONTROL, AND EXPERIMENTS
    FAESSLER, H
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 1990, 9 (04): : 40 - 58
  • [7] Deep Learning-Based Modulation Recognition for MIMO Systems: Fundamental, Methods, Challenges
    Zhang, Xueqin
    Luo, Zhongqiang
    Xiao, Wenshi
    Feng, Li
    IEEE ACCESS, 2024, 12 : 112558 - 112575
  • [8] Deep Learning for Channel Estimation in Physical Layer Wireless Communications: Fundamental, Methods, and Challenges
    Lv, Chaoluo
    Luo, Zhongqiang
    ELECTRONICS, 2023, 12 (24)
  • [9] Deep Learning or Fundamental Descriptors? Response
    Bahl, Manisha
    Barzilay, Regina
    Lehman, Constance D.
    RADIOLOGY, 2018, 287 (02) : 728 - 729
  • [10] Fundamental Fluid Dynamics Challenges in Inkjet Printing
    Lohse, Detlef
    ANNUAL REVIEW OF FLUID MECHANICS, 2022, 54 : 349 - 382