• Corpus ID: 244130159

Analysis of Model-Free Reinforcement Learning Control Schemes on self-balancing Wheeled Extendible System

  title={Analysis of Model-Free Reinforcement Learning Control Schemes on self-balancing Wheeled Extendible System},
  author={Kanishk and Rushil K. Kumar and Vikas Rastogi and Ajeet Kumar},
Traditional linear control strategies have been extensively researched and utilized in many robotic and industrial applications and yet they don’t respond to the total dynamics of the systems. To avoid tedious calculations for nonlinear control schemes like H-infinity control and predictive control, the application of Reinforcement Learning(RL) can provide alternative solutions. This article presents the implementation of RL control with Deep Deterministic Policy Gradient and Proximal Policy… 

Figures and Tables from this paper



A Parametric Study of a Deep Reinforcement Learning Control System Applied to the Swing-Up Problem of the Cart-Pole

The nonlinear swing-up problem associated with the cart-pole system modeled as a multibody dynamical system is solved by developing a deep Reinforcement Learning (RL) controller and a post-training of the agent in the modified environment takes only thirty-nine episodes to find the optimal control policy.

Adaptive Reinforcement Learning Strategy with Sliding Mode Control for Unknown and Disturbed Wheeled Inverted Pendulum

This paper develops a novel adaptive integral sliding-mode control (SMC) technique to improve the tracking performance of a wheeled inverted pendulum (WIP) system, which belongs to a class of

A Modified SQP-based Model Predictive Control Algorithm: Application to Supercritical Coal-fired Power Plant Cycling

In this paper, a modified sequential quadratic programming (SQP)-based model predictive control (MPC) algorithm is developed and implemented for power plant cycling applications. These applications...

Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments

This paper proposes a new federated reinforcement learning architecture where each agent working on its independent device shares their learning experience with each other, and transfers a mature policy model parameters into other agents.

Modeling and Control of a Hybrid Wheeled Jumping Robot

This paper studies a wheeled robot with a prismatic extension joint and proposes a template model for the class of two-wheeled jumping robots, which can be considered as the simplest wheeled-legged system.

Continuous Control with Deep Reinforcement Learning for Mobile Robot Navigation

A deep reinforcement learning method, i.e. soft actor critic, is used to navigate in a mapless environment and shows that this learning-based end-to-end autonomous navigation method can accomplish tasks as well as traditional methods.

A Study on PD-like Fuzzy Logic Control Based Active Noise Control for Narrowband Noise Cancellation with Acoustic Feedback and Distance Ratio

The simulation results reveal that the TSK-type PD-like FLC performs better and the effects of different distance ratios on the degree of cancellation is significant while the optimal configuration is to place both transducers close to the secondary source.

Ascento: A Two-Wheeled Jumping Robot

Ascento is introduced, a compact wheeled bipedal robot that is able to move quickly on flat terrain, and to overcome obstacles by jumping, as well as the development of various controllers for different scenarios.

Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy optimization

A deep reinforcement learning (DRL) controller to handle the nonlinear attitude control problem, enabling extended flight envelopes for fixed-wing UAVs and generalize well to unseen disturbances in the form of wind and turbulence, even in severe disturbance conditions.

Control of a Two-wheeled Machine with Two-directions Handling Mechanism Using PID and PD-FLC Algorithms

This paper presents a novel five degrees of freedom (DOF) two-wheeled robotic machine (TWRM) that delivers solutions for both industrial and service robotic applications by enlarging the vehicle’s