Human-Robot Interaction Control Using Reinforcement Learning

Wen Yu, Adolfo Perrusquia

• Publisher: Wiley-IEEE Press
• Year: 2021
• Print ISBN: 9781119782742
• eBook ISBN: 9781119782766
• Edition: 1
• Topic: Technology & Engineering
• Subtopic: Computer Networking
• Index: Technology & Engineering

A comprehensive exploration of the control schemes of human-robot interactions

In Human-Robot Interaction Control Using Reinforcement Learning, an expert team of authors deliversa concise overview of human-robot interaction control schemes and insightful presentations of novel, model-free and reinforcement learning controllers. The book begins with a brief introduction to state-of-the-art human-robot interaction control and reinforcement learning before moving on to describe the typical environment model. The authors also describe some of the most famous identification techniques for parameter estimation.

Human-Robot Interaction Control Using Reinforcement Learning offers rigorous mathematical treatments and demonstrations that facilitate the understanding of control schemes and algorithms.It also describes stability and convergence analysis of human-robot interaction control and reinforcement learning based control.

The authorsalsodiscussadvanced and cutting-edge topics, like inverse and velocity kinematics solutions, H2 neural control, and likely upcoming developments in the field of robotics.

Readers will also enjoy:

• A thorough introduction to model-based human-robot interaction control
• Comprehensive explorations of model-free human-robot interaction control and human-in-the-loop control using Euler angles
• Practical discussions of reinforcement learning for robot position and force control, as well as continuous time reinforcement learning for robot force control
• In-depth examinations of robot control in worst-case uncertainty using reinforcement learning and the control of redundant robots using multi-agent reinforcement learning

Perfect forsenior undergraduate and graduate students, academic researchers, and industrial practitioners studying and working in the fields of robotics, learning control systems, neural networks, and computational intelligence, Human-Robot Interaction Control Using Reinforcement Learning is also an indispensable resource forstudents and professionals studying reinforcement learning.

Part I
Human‐robot Interaction Control

1
Introduction

1.1 Human‐Robot Interaction Control

If we know the robot dynamics, we can use them to design model‐based controllers (See Figure 1.1). The famous linear controllers are: Proportional‐Derivative (PD) [1], linear quadratic regulator (LQR), and Proportional‐Integral‐Derivative (PID) [2]. They use linear system theory, so the robot dynamics are required to be linearized at some point of operation. The LQR [3–5] control has been used as a basis for the design of reinforcement learning approaches [6].

The classic controllers use complete or partial knowledge of the robot's dynamics. In these cases (without considering disturbances), it is possible to design controllers that guarantee perfect tracking performance. By using the compensation or the pre‐compensation techniques, the robot dynamics is canceled and establishes a simpler desired dynamics [7–9]. The control schemes with model compensation or pre‐compensation in joint space can be seen in Figure 1.2. Here

is the desired reference,

is the robot's joint position,

is the joint error,

is the compensator or pre‐compensator of the dynamics,

is the control coming from the controller, and

is the control torque. A typical model‐compensation control is the proportional‐derivative (PD) controller with gravity compensation, which helps to decrease the steady‐state error caused by the gravity terms of th...

Table of contents

• Cover
• Table of Contents
• Title Page
• Copyright
• Dedication
• Author Biographies
• List of Figures
• List of Tables
• Preface
• Part I: Human‐robot Interaction Control
• Part II: Reinforcement Learning for Robot Interaction Control
• A Robot Kinematics and Dynamics
• B Reinforcement Learning for Control
• Index
• End User License Agreement