Frank C. Park

Written by experts in the field, this text provides a modern introduction to three-dimensional dynamics for multibody systems. It covers rotation matrices, the twist-wrench formalism for multibody dynamics and Lagrangian dynamics, an approach that is often overlooked at the undergraduate level. The only prerequisites are differential equations and linear algebra as covered in a first-year engineering mathematics course. The text focuses on obtaining and understanding the equations of motion, featuring a rich set of examples and exercises that are drawn from real-world scenarios. Readers develop a reliable physical intuition that can then be used to apply dynamic analysis software tools, and to develop simplified approximate models. With this foundation, they will be able to confidently use the equations of motion in a variety of applications, ranging from simulation and design to motion planning and control.

This book provides a concise survey and description of recent collision detection methods for robot manipulators. Beginning with a review of robot kinodynamic models and preliminaries on basic statistical learning methods, the book covers fundamental aspects of the collision detection problem, from collision types and collision detection performance criteria to model-free versus model-based methods, and the more recent data-driven learning-based approaches to collision detection. Special effort has been given to describing and evaluating existing methods with a unified set of notation, systematically categorizing these methods according to a basic set of criteria, and summarizing the advantages and disadvantages of each method. This book is the first to comprehensively organize the growing body of learning-based collision detection methods, ranging from basic supervised learning methods to more advanced approaches based on unsupervised learning and transfer learning techniques. Step-by-step implementation details and pseudocode descriptions are provided for key algorithms. Collision detection performance is measured with respect to both conventional criteria such as detection delay and the number of false alarms, as well as criteria that measure generalization capability for learning-based methods. Whether it be for research or commercial applications, in settings ranging from industrial factories to physical human–robot interaction experiments, this book can help the reader choose and successfully implement the most appropriate detection method that suits their robot system and application.

This book provides a concise survey and description of recent collision detection methods for robot manipulators. Beginning with a review of robot kinodynamic models and preliminaries on basic statistical learning methods, the book covers fundamental aspects of the collision detection problem, from collision types and collision detection performance criteria to model-free versus model-based methods, and the more recent data-driven learning-based approaches to collision detection. Special effort has been given to describing and evaluating existing methods with a unified set of notation, systematically categorizing these methods according to a basic set of criteria, and summarizing the advantages and disadvantages of each method. This book is the first to comprehensively organize the growing body of learning-based collision detection methods, ranging from basic supervised learning methods to more advanced approaches based on unsupervised learning and transfer learning techniques. Step-by-step implementation details and pseudocode descriptions are provided for key algorithms. Collision detection performance is measured with respect to both conventional criteria such as detection delay and the number of false alarms, as well as criteria that measure generalization capability for learning-based methods. Whether it be for research or commercial applications, in settings ranging from industrial factories to physical human–robot interaction experiments, this book can help the reader choose and successfully implement the most appropriate detection method that suits their robot system and application.

This introduction to robotics offers a distinct and unified perspective of the mechanics, planning and control of robots. Ideal for self-learning, or for courses, as it assumes only freshman-level physics, ordinary differential equations, linear algebra and a little bit of computing background. Modern Robotics presents the state-of-the-art, screw-theoretic techniques capturing the most salient physical features of a robot in an intuitive geometrical way. With numerous exercises at the end of each chapter, accompanying software written to reinforce the concepts in the book and video lectures aimed at changing the classroom experience, this is the go-to textbook for learning about this fascinating subject.