dynamicslab / MultiArm-Pendulum

This repository is for our paper: "The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control." It contains all the CAD files we used to build the pendulum hardware, their corresponding user's manual, and data set we collected from our hardware, which is useful for Machine Learning and AI community.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The Experimental Multi-Arm Pendulum on a Cart

Overview:

This repository is for our paper: "The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control." The following figure shows an overview of the experimental system.

This repository contains the following files:

  • All the CAD files needed to build the pendulum hardware.
  • Link to the user's manuals that correspond to some of the parts we used.
  • The experimental data sets of the single, double, and triple pendulum with and without external excitation. We believe this data set will be extremely useful for the Machine Learning and AI community to test their modeling algorithm. The slow-motion video data for the double pendulum can be accessed using this Link.
  • A demo file for setting up the hardware system and using it for data collection.
  • Demo files for parameter estimation of the single, double, and triple pendulum.

Cite:

If you find our data set or hardware useful for your research, please kindly cite it as:

@misc{kaheman2022experimental, title={The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control}, author={Kadierdan Kaheman and Urban Fasel and Jason J. Bramburger and Benjamin Strom and J. Nathan Kutz and Steven L. Brunton}, year={2022}, eprint={2205.06231}, archivePrefix={arXiv}, primaryClass={nlin.CD} }

About

This repository is for our paper: "The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control." It contains all the CAD files we used to build the pendulum hardware, their corresponding user's manual, and data set we collected from our hardware, which is useful for Machine Learning and AI community.

License:MIT License


Languages

Language:MATLAB 100.0%