Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2

This is a demo model for Reinforcement Learning Control Design. After designing agent, it is deployed to Raspberry Pi and run in hardware.
489 Downloads
Updated Thu, 23 Dec 2021 01:33:03 +0000

Reinforcement Learning: training and deploying a policy to control inverted pendulum with QUBE - Servo2

【日本語の資料はこちら

Objective

This demo models show how to design inverted pendulum controller with "QUBE - Servo 2" of Quanser. And they also show the workflow of plant modeling, control design, code generation, verification, and deployment.

Required Toolboxes

  • MATLAB®
  • Simulink®
  • Stateflow®
  • Simscape™, Simscape Electrical™, Simscape Multibody™
  • Deep Learning Toolbox™
  • Reinforcement Learning Toolbox™
  • MATLAB Coder, Simulink Coder, Embedded Coder®

Required Add-Ons

  • MATLAB Support Package for Raspberry Pi Hardware
  • Simulink Support Package for Raspberry Pi Hardware
  • MATLAB Coder Interface for Deep Learning Libraries
  • MEX Compiler

Note

Live scripts for Reinforcement Learning have some commands to train in parallel. The commands are invalid by default. If you want to use them, Parallel Computing Toolbox™ is required.

1. PID Control

The plant model can be linearized around the operating point where the pendulum is inverted. A feedback controller is designed to keep the pendulum inverted. On the ather hand, when the pendulum angle is downward, a steady controller is desinged to keep the pendulum right under.

Design inverted pendulum with PID controller

2. Reinforcement Learning

Requirements for invert the QUBE - Serve 2:

  1. Oscillate the pendulum whicn is steady at .
  2. Bring up the pendulum around .
  3. Keep the angle of pendulum at .
  4. The motor angle does not exceed the . (Hardware Constraints)

In order to realize the control system satisfying above, Combine the feedback controller created in "1. PID Control", "swing up" reinforcement learing, and "mode select" reinforcement learing.

The reason for building this system is that it is difficult to design a function that meets all the requirements with a single Reinforcement Learning controller. The following document explains the details.

What task is difficult for Deep Reinforcement Learning?

For more information about the modeling, refer to the "RL_multi_control_system.slx".

2.1. "swing up" reinforcement learing

Design SAC agent to get the optimal policy which can swing up the pendulum with the reference for the feedback controller.

Design "swing up" reinforcement learing

2.2. "mode select" reinforcement learing

"mode select" reinforcement learing changes the reference for the feedback controller between constant and the output of "swing up" reinforcement learing. PPO agent is used to get the policy for this "mode select" action.

Design "mode select" reinforcement learing

3. Code generation and verification

Extract the trained policy from the agents, and create a model for deploying controller. Then verify the code execution with SIL and PIL before doing experiment.

Code generation and verification for the controller with RL

4. Experiment

Connect Raspberry Pi and QUBE - Servo 2, and run the Raspberry Pi with External Mode.

Experiment for the controller with RL

Old version

A set of files for past versions can be downloaded from the following link. However, the past files only contain samples created in the old days.

If you have cloned from GitHub, the past version can be obtained by reverting to the corresponding version below.

R2021a: v1.0.1

  • Copyright 2021 The MathWorks, Inc.*

Cite As

Toshinobu Shintai (2024). Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2 (https://github.com/mathworks/Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2/releases/tag/v2.0.3), GitHub. Retrieved .

MATLAB Release Compatibility
Created with R2021b
Compatible with R2021a to R2021b
Platform Compatibility
Windows macOS Linux
Tags Add Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
2.0.3

See release notes for this release on GitHub: https://github.com/mathworks/Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2/releases/tag/v2.0.3

2.0.2

See release notes for this release on GitHub: https://github.com/mathworks/Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2/releases/tag/v2.0.2

2.0.1

See release notes for this release on GitHub: https://github.com/mathworks/Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2/releases/tag/v2.0.1

2.0

See release notes for this release on GitHub: https://github.com/mathworks/Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2/releases/tag/v2.0

1.0.1

See release notes for this release on GitHub: https://github.com/mathworks/Reinforcement-Learning-Inverted-Pendulum-with-QUBE-Servo2/releases/tag/v1.0.1

1.0

To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.