Gradient-Based Trajectory Optimization With Learned Dynamics

被引:1
|
作者
Sukhija, Bhavya [1 ]
Kohler, Nathanael [1 ]
Zamora, Miguel [1 ]
Zimmermann, Simon [1 ]
Curi, Sebastian [1 ]
Krause, Andreas [1 ]
Coros, Stelian [1 ]
机构
[1] ETH, Dept Comp Sci, Zurich, Switzerland
关键词
MODEL-PREDICTIVE CONTROL; SYSTEM-IDENTIFICATION; NEURAL-NETWORK;
D O I
10.1109/ICRA48891.2023.10161574
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Trajectory optimization methods have achieved an exceptional level of performance on real-world robots in recent years. These methods heavily rely on accurate analytical models of the dynamics, yet some aspects of the physical world can only be captured to a limited extent. An alternative approach is to leverage machine learning techniques to learn a differentiable dynamics model of the system from data. In this work, we use trajectory optimization and model learning for performing highly dynamic and complex tasks with robotic systems in absence of accurate analytical models of the dynamics. We show that a neural network can model highly nonlinear behaviors accurately for large time horizons, from data collected in only 25 minutes of interactions on two distinct robots: (i) the Boston Dynamics Spot and an (ii) RC car. Furthermore, we use the gradients of the neural network to perform gradient-based trajectory optimization. In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car, and gives good performance in combination with trajectory optimization methods.
引用
收藏
页码:1011 / 1018
页数:8
相关论文
共 50 条
  • [41] Gradient-based history matching with a global optimization method
    Gomez, S
    Gosselin, O
    Barker, JW
    SPE JOURNAL, 2001, 6 (02): : 200 - 208
  • [42] Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
    Lee, Yoonho
    Choi, Seungjin
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [43] Gradient-based optimizer: A new metaheuristic optimization algorithm
    Ahmadianfar, Iman
    Bozorg-Haddad, Omid
    Chu, Xuefeng
    INFORMATION SCIENCES, 2020, 540 : 131 - 159
  • [44] Gradient-Based Fast Source Mask Optimization (SMO)
    Yu, Jue-Chin
    Yu, Peichen
    OPTICAL MICROLITHOGRAPHY XXIV, 2011, 7973
  • [45] Gradient-Based Source and Mask Optimization in Optical Lithography
    Peng, Yao
    Zhang, Jinyu
    Wang, Yan
    Yu, Zhiping
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (10) : 2856 - 2864
  • [46] ACOUSTIC CLOAK DESIGN VIA GRADIENT-BASED OPTIMIZATION
    Avina, Angel
    Gerges, Samer
    Amirkulova, Feruza A.
    Du, Winncy
    PROCEEDINGS OF ASME 2023 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, IMECE2023, VOL 4, 2023,
  • [47] Gradient-based aerothermodynamic optimization of a hypersonic wing profile
    Xia, Chenchao
    Chen, Weifang
    FRONTIERS IN FLUID MECHANICS RESEARCH, 2015, 126 : 189 - 193
  • [48] Gradient-based simulation optimization under probability constraints
    Andrieu, Laetitia
    Cohen, Guy
    Vazquez-Abad, Felisa J.
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2011, 212 (02) : 345 - 351
  • [49] Gradient-based optimization of a rotating algal biofilm process
    Lamare, Pierre-Olivier
    Aguillon, Nina
    Sainte-Marie, Jacques
    Grenier, Jerome
    Bonnefond, Hubert
    Bernard, Olivier
    AUTOMATICA, 2019, 105 : 80 - 88
  • [50] Gradient-based Optimization of Kernel Polarization for RBF Kernels
    Xu, Jianfeng
    Liu, Lan
    PROCEEDINGS OF THE 2009 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND NATURAL COMPUTING, VOL I, 2009, : 85 - +