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
  • [1] A review of flexible multibody dynamics for gradient-based design optimization
    Gufler, Veit
    Wehrle, Erich
    Zwoelfer, Andreas
    MULTIBODY SYSTEM DYNAMICS, 2021, 53 (04) : 379 - 409
  • [2] A review of flexible multibody dynamics for gradient-based design optimization
    Veit Gufler
    Erich Wehrle
    Andreas Zwölfer
    Multibody System Dynamics, 2021, 53 : 379 - 409
  • [3] Improved Gradient-Based Algorithm for Solving Aeroassisted Vehicle Trajectory Optimization Problems
    Chai, Runqi
    Savvaris, Al
    Tsourdos, Antonios
    Chai, Senchun
    Xia, Yuanqing
    JOURNAL OF GUIDANCE CONTROL AND DYNAMICS, 2017, 40 (08) : 2093 - 2101
  • [4] Gradient-based optimization of hyperparameters
    Bengio, Y
    NEURAL COMPUTATION, 2000, 12 (08) : 1889 - 1900
  • [5] Gradient-based learning and optimization
    Cao, XR
    PROCEEDINGS OF THE 17TH INTERNATIONAL SYMPOSIUM ON COMPUTER AND INFORMATION SCIENCES, 2003, : 3 - 7
  • [6] Gradient-based simulation optimization
    Kim, Sujin
    PROCEEDINGS OF THE 2006 WINTER SIMULATION CONFERENCE, VOLS 1-5, 2006, : 159 - 167
  • [7] GraphDistNet: A Graph-Based Collision-Distance Estimator for Gradient-Based Trajectory Optimization
    Kim, Yeseung
    Kim, Jinwoo
    Park, Daehyung
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) : 11118 - 11125
  • [8] SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning
    Lee, JunHoo
    Yoo, Jayeon
    Kwak, Nojun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [9] A skeletonization algorithm for gradient-based optimization
    Menten, Martin J.
    Paetzold, Johannes C.
    Zimmer, Veronika A.
    Shit, Suprosanna
    Ezhov, Ivan
    Holland, Robbie
    Probst, Monika
    Schnabel, Julia A.
    Rueckert, Daniel
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 21337 - 21346
  • [10] Gradient-based optimization of spintronic devices
    Imai, Y.
    Liu, S.
    Akashi, N.
    Nakajima, K.
    APPLIED PHYSICS LETTERS, 2025, 126 (08)