Deformable Linear Object Prediction Using Locally Linear Latent Dynamics

被引:15
|
作者
Zhang, Wenbo [1 ]
Schmeckpeper, Karl [1 ]
Chaudhari, Pratik [1 ]
Daniilidis, Kostas [1 ]
机构
[1] Univ Penn, GRASP Lab, Philadelphia, PA 19104 USA
关键词
ROBOTIC MANIPULATION;
D O I
10.1109/ICRA48506.2021.9560955
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We propose a framework for deformable linear object prediction. Prediction of deformable objects (e.g., rope) is challenging due to their non-linear dynamics and infinite-dimensional configuration spaces. By mapping the dynamics from a non-linear space to a linear space, we can use the good properties of linear dynamics for easier learning and more efficient prediction. We learn a locally linear, action-conditioned dynamics model that can be used to predict future latent states. Then, we decode the predicted latent state into the predicted state. We also apply a sampling-based optimization algorithm to select the optimal control action. We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.
引用
收藏
页码:13503 / 13509
页数:7
相关论文
共 50 条
  • [41] Identification of latent variables using, factor analysis and multiple linear regression for software fault prediction
    Deepak Sharma
    Pravin Chandra
    International Journal of System Assurance Engineering and Management, 2019, 10 : 1453 - 1473
  • [43] INERTIAL EFFECTS ON LINEAR AND LOCALLY LINEAR FLOWS
    DELAMORA, JF
    AEROSOL SCIENCE AND TECHNOLOGY, 1985, 4 (03) : 339 - 349
  • [44] Non-Prehensile Object Transport by Nonholonomic Robots Connected by Linear Deformable Elements
    Zhi, Hui
    Zhang, Bin
    Qi, Jiaming
    Romero, Jose Guadalupe
    Shao, Xiaodong
    Yang, Chenguang
    Navarro-Alarcon, David
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (10): : 8651 - 8658
  • [45] Prediction of effective porosity from seismic attributes using locally linear model tree algorithm
    Talkhestani, Ahmad Ashtari
    GEOPHYSICAL PROSPECTING, 2015, 63 (03) : 680 - 693
  • [46] A HYBRID BUSINESS FAILURE PREDICTION MODEL USING LOCALLY LINEAR EMBEDDING AND SUPPORT VECTOR MACHINES
    Lin, Fengyi
    Yeh, Ching-Chiang
    Lee, Meng-Yuan
    ROMANIAN JOURNAL OF ECONOMIC FORECASTING, 2013, 16 (01): : 82 - 97
  • [47] Learning-Based MPC With Safety Filter for Constrained Deformable Linear Object Manipulation
    Tang, Yunxi
    Chu, Xiangyu
    Huang, Jing
    Samuel Au, K. W.
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (03) : 2877 - 2884
  • [48] Vibration damping for manipulating deformable linear object robotic operation based on fuzzy control
    Ding, F. (dingfeng@hust.edu.cn), 1600, Huazhong University of Science and Technology (41):
  • [49] A Practical Solution to Deformable Linear Object Manipulation: A Case Study on Cable Harness Connection
    Zhou, Hang
    Li, Shunchong
    Lu, Qi
    Qian, Jinwu
    2020 5TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS AND MECHATRONICS (ICARM 2020), 2020, : 329 - 333
  • [50] Using linear autoregression model for dynamics prediction of stock-exchange quotations
    Savchenko, V.V.
    Avtometriya, 2004, 40 (04): : 117 - 128