Using a Bayesian-Inference Approach to Calibrating Models for Simulation in Robotics

Using a Bayesian-Inference Approach to Calibrating Models for Simulation in Robotics
复制标题

使用贝叶斯推理方法校准机器人仿真模型

DOI:
10.1115/1.4062199
复制
发表时间:
2023
影响因子:
2
通讯作者:
Negrut, Dan
Negrut, Dan
中科院分区:
工程技术4区
文献类型:
--
作者:
Unjhawala, Huzaifa Mustafa;Zhang, Ruochun;Hu, Wei;Wu, Jinlong;Serban, Radu;Negrut, Dan

文献摘要

参考文献

相似文献

在机器人技术中,仿真有可能减少设计时间和成本,并带来更强大的工程解决方案和更安全的开发过程。然而,模拟器的使用取决于良好模型的可用性。这一贡献涉及通过校准来提高这些模型的质量,这在本文中是在贝叶斯框架中进行的。首先,我们讨论贝叶斯机制参与模型校准。然后,我们在一个例子中演示了它:校准车辆动力学模型,该模型具有低自由度(DOF)计数,可用于状态估计,模型预测控制或路径规划。高保真模拟器用于模拟“实验”并生成用于校准的数据。这项工作的优点并不在于一种新的贝叶斯校准方法,而是在于证明贝叶斯机器如何在计算动力学模型之间建立联系,即使使用的数据是有噪声的。用于生成本文报告的结果的软件可在公共存储库中获得,以供不受限制地使用和分发。
In robotics, simulation has the potential to reduce design time and costs, and lead to a more robust engineered solution and a safer development process. However, the use of simulators is predicated on the availability of good models. This contribution is concerned with improving the quality of these models via calibration, which is cast herein in a Bayesian framework. First, we discuss the Bayesian machinery involved in model calibration. Then, we demonstrate it in one example: calibration of a vehicle dynamics model that has low degree-of-freedom (DOF) count and can be used for state estimation, model predictive control, or path planning. A high fidelity simulator is used to emulate the “experiments” and generate the data for the calibration. The merit of this work is not tied to a new Bayesian methodology for calibration, but to the demonstration of how the Bayesian machinery can establish connections among models in computational dynamics, even when the data in use is noisy. The software used to generate the results reported herein is available in a public repository for unfettered use and distribution.
DOI: 10.1007/s11044-022-09815-2
发表时间: 2022-03
影响因子: 3.4
作者:
Weihua Hu;Zhenhao Zhou;S. Chandler;D. Apostolopoulos;K. Kamrin;R. Serban;D. Negrut
通讯作者: Weihua Hu;Zhenhao Zhou;S. Chandler;D. Apostolopoulos;K. Kamrin;R. Serban;D. Negrut
DOI: 10.3390/pr9101813
发表时间: 2021-10
期刊: Processes
影响因子: 3.5
作者:
Luning Fang;Ruochun Zhang;Colin Vanden Heuvel;R. Serban;D. Negrut
通讯作者: Luning Fang;Ruochun Zhang;Colin Vanden Heuvel;R. Serban;D. Negrut
Chrono::Vehicle:基于模板的地面车辆建模和仿真
DOI: --
发表时间: 2019
影响因子: --
作者:
R. Serban;Michael Taylor;D. Negrut;A. Tasora
通讯作者: A. Tasora
地面车辆在变形地形上的实时仿真
DOI: --
发表时间: 2022
期刊: Volume 9: 18th International Conference on Multibody Systems, Nonlinear Dynamics, and Control (MSNDC)
影响因子: --
作者:
R. Serban;Jay Taves;Zhenhao Zhou
通讯作者: Zhenhao Zhou
用于在仿真和现实中研究和比较机器人自主算法的软件工具包和硬件平台
DOI: 10.48550/arxiv.2206.06537
发表时间: 2022
期刊: ArXiv
影响因子: --
作者:
A. Elmquist;Aaron Young;Ishaan Mahajan;Kyle Fahey;Abhiraj Dashora;Sriram Ashokkumar;Stefan Caldararu;Victor Freire;Xiangru Xu;R. Serban;D. Negrut
通讯作者: D. Negrut