• Home
  • About
  • Featured Articles
  • Editorial Team
  • Announcements
  • Home
  • About
  • Featured Articles
  • Editorial Team
  • Announcements
JOURNAL OF COMPUTATIONAL AND NONLINEAR DYNAMICS
  • Home
  • About
  • Featured Articles
  • Editorial Team
  • Announcements

Featured Articles

    Archives

    April 2025
    January 2025
    December 2024
    October 2024
    September 2024
    August 2024
    February 2024
    October 2023
    September 2023
    July 2023
    May 2023
    March 2023
    February 2023
    September 2022
    August 2022
    April 2022
    March 2022
    December 2021
    October 2021
    September 2021

    Categories

    All
    Actuators
    Approximation
    Artificial Neural Networks
    Attractors
    Bifurcation
    Boundary Conditions
    Boundary-value Problems
    Cables
    Contact
    Continuation Methods
    Control
    Co-simulation
    Co-simulation Interface
    Damping
    Delay Differential Equations
    Delays
    Density
    Displacement
    Dynamic Models
    Dynamics
    Dynamic Systems
    Eigenvalues
    Error Estimator
    Errors
    Exact Mode Shapes
    Exoskeleton Devices
    Friction
    Fuzzy Logic
    Galerkin Method
    Geometry
    Heat
    Heat Transfer
    Homoclinic Orbits
    Kinematics
    Limit Cycles
    Loaded Beam
    Machine Learning
    Manifolds
    Manipulators
    Midplane Stretching
    Multibody Dynamics
    Multibody Systems
    Multiphysics
    Multirate
    Noise
    Nonlinear Dynamical Systems
    Nonlinear Frequency
    Nonlinear Vibration
    Nonlinear Vibration Absorber
    NVA
    Origami
    Parallelization
    Parametrization
    Pendulum
    Perturbation Methods
    Probability
    Prostheses
    Railroad Dynamics
    Real-time Dynamics Simulation
    Reinforcement Learning
    Resonance
    Robots
    Ships
    Simulation
    Solver Coupling
    Space
    Stability
    Time Delay Systems
    Topology
    Variable Macro-step Size
    Vehicular Dynamics
    Vibration
    Waves

    RSS Feed

Back to Blog

Cable SCARA Robot Controlled by a Neural Network Using Reinforcement Learning

9/6/2023

 
Eduardo Okabe, Victor Paiva, Luis Silva-Teixeira, Jaime Izuka
J. Comput. Nonlinear Dynam. Oct 2023, 18(10): 104501 
https://doi.org/10.1115/1.4063222
The industry and the scientific community have shown interest in SCARA (Selective Compliance Assembly Robot Arm) robots due to their high accuracy. In this paper, a two-link SCARA has its end-effector pulled by three cables that generate a triangular-shaped workspace. Moving the end-effector in this region is a relatively straightforward task, but placing the end-effector outside it requires a nonlinear dynamic model and a state-of-the-art controller. To address this problem in a simpler, more efficient and innovative manner, the equations of motion are derived and three reinforcement learning algorithms are employed: Proximal Policy Optimization (the same used by the chatbot ChatGPT), Soft Actor-Critic and Twin Delayed Deep Deterministic Policy Gradient. Three targets outside the triangular workspace are considered and the trained networks have their results compared in terms of displacement error, velocity and standard deviation. The Twin Delayed Deep Deterministic Policy Gradient provides creative trajectories, the Soft Actor-Critic presents better solutions for two out of three targets, while the Proximal Policy Algorithm appears to be the most consistent considering all targets under analysis.
Picture
Full Article
0 Comments
Read More
Picture
JOURNAL OF COMPUTATIONAL and
​NONLINEAR DYNAMICS
COMPANION

QUICK LINKS

Submit Paper
Author Resources
Digital Collection
Indexing Information
Order Journal
Announcements and Call for Papers
Picture
Copyright © 2021 Journal of Computational and Nonlinear Dynamics