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
[41]   Inverse dynamics trajectory optimization for contact-implicit model predictive control [J].
Kurtz, Vince ;
Castro, Alejandro ;
Onol, Aykut Ozgun ;
Lin, Hai .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2025,
[42]   TOAST: Trajectory Optimization and Simultaneous Tracking Using Shared Neural Network Dynamics [J].
Kim, Taekyung ;
Lee, Hojin ;
Hong, Seongil ;
Lee, Wonsuk .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) :9747-9754
[43]   Modeling ultrasonic welding of polymers using an optimized artificial intelligence model using a gradient-based optimizer [J].
Elsheikh, Ammar H. ;
Abd Elaziz, Mohamed ;
Vendan, Arungalai .
WELDING IN THE WORLD, 2022, 66 (01) :27-44
[44]   One-Shot Simple Pattern Detection without Pre-Training and Gradient-Based Strategy [J].
Su, Jun ;
He, Wei ;
Wang, Yingguan ;
Ma, Runze .
SENSORS, 2023, 23 (22)
[45]   Gradient projection-based trajectory tracking control for automatic guided vehicle [J].
Liu, Wei ;
Wang, Rongjun ;
Chen, Linfeng ;
Wan, Yidong .
JOURNAL OF CONTROL AND DECISION, 2024,
[46]   Closed Loop Trajectory Optimization Based on Reverse Time Tree [J].
Kim, Chyon Hae ;
Sugano, Shigeki .
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2016, 14 (06) :1404-1412
[47]   Physics-based trajectory optimization with automatic time warping [J].
Han, Daseong ;
Noh, Junyong ;
Shin, Joseph S. .
COMPUTER ANIMATION AND VIRTUAL WORLDS, 2018, 29 (3-4)
[48]   Study on Trajectory Optimization of Hypersonic Vehicle Based on Neural Network [J].
Cai, Feichao ;
Huang, Xing .
FRONTIERS IN ENERGY RESEARCH, 2022, 10
[49]   Computation of Solution Spaces for Optimization-Based Trajectory Planning [J].
Schaefer, Lukas ;
Manzinger, Stefanie ;
Althoff, Matthias .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2023, 8 (01) :216-231
[50]   Energy-efficiency-oriented Gradient-based Economic Predictive Control of Multiple-Chiller Cooling Systems [J].
Nadales, J. M. ;
Ordonez, Joaquin G. ;
Coronel, Juan F. ;
Limon, D. .
IFAC PAPERSONLINE, 2020, 53 (02) :6656-6661