Gradient-Based Trajectory Optimization With Learned Dynamics

被引:4
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
来源
2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA | 2023年
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
[31]   Gradient-based iterative algorithm for Wiener systems with saturation and dead-zone nonlinearities [J].
Chen, Jing ;
Lu, Xianling ;
Ding, Ruifeng .
JOURNAL OF VIBRATION AND CONTROL, 2014, 20 (04) :634-640
[32]   Distributed load identification for hyperelastic plates using gradient-based and machine learning methods [J].
Khosrowpour, E. ;
Hematiyan, M. R. .
ACTA MECHANICA, 2024, 235 (05) :3271-3291
[33]   A Gradient-Based Neural Network Method for Solving Strictly Convex Quadratic Programming Problems [J].
Nazemi, Alireza ;
Nazemi, Masoomeh .
COGNITIVE COMPUTATION, 2014, 6 (03) :484-495
[34]   A Gradient-Based Neural Network Method for Solving Strictly Convex Quadratic Programming Problems [J].
Alireza Nazemi ;
Masoomeh Nazemi .
Cognitive Computation, 2014, 6 :484-495
[35]   Stochastic gradient-based hyperbolic orthogonal neural networks for nonlinear dynamic systems identification [J].
Ahmadi, Ghasem .
JOURNAL OF MATHEMATICAL MODELING, 2022, 10 (03) :529-547
[36]   Recovery trajectory optimization for UAV towed aerial recovery based on trajectory mapping [J].
Wang H. ;
Wang Y. ;
Liu Y. .
Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica, 2023, 44 (20)
[37]   On the Use of Gradient-Based Solver and Deep Learning Approach in Hierarchical Control: Application to Grand Refrigerators [J].
Pham, Xuan-Huy ;
Bonne, Francois ;
Alamir, Mazen .
CYBERNETICS AND SYSTEMS, 2023,
[38]   Stochastic gradient-based particle filtering method for ARX models with nonlinear communication output submodel [J].
Feng, Jianxia ;
Lu, Donglei .
INTERNATIONAL JOURNAL OF MODELLING IDENTIFICATION AND CONTROL, 2019, 31 (04) :331-336
[39]   A Conjugate Gradient-Based Efficient Algorithm for Training Single-Hidden-Layer Neural Networks [J].
Gong, Xiaoling ;
Wang, Jian ;
Wang, Yanjiang ;
Zurada, Jacek M. .
NEURAL INFORMATION PROCESSING, ICONIP 2016, PT IV, 2016, 9950 :470-478
[40]   NNTesting: Neural Network Fault Attacks Detection Using Gradient-Based Test Vector Generation [J].
Wang, Antian ;
Zhao, Bingyin ;
Tan, Weihang ;
Lao, Yingjie .
2023 60TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC, 2023,