The practice of robotics and computer vision each involve the application of computational algorithms to data. The research community has developed a very large body of algorithms but for a newcomer to the field this can be quite daunting. For more than 10 years the author has maintained two open-source MATLAB® Toolboxes, one for robotics and one for vision. They provide implementations of many important algorithms and allow users to work with real problems, not just trivial examples.
This new book makes the fundamental algorithms of robotics, vision and control accessible to all. It weaves together theory, algorithms and examples in a narrative that covers robotics and computer vision separately and together. Using the latest versions of the Toolboxes the author shows how complex problems can be decomposed and solved using just a few simple lines of code. The topics covered are guided by real problems observed by the author over many years as a practitioner of both robotics and computer vision. It is written in a light but informative style, it is easy to read and absorb, and includes over 1000 MATLAB®and Simulink® examples and figures. The book is a real walk through the fundamentals of mobile robots, navigation, localization, arm-robot kinematics, dynamics and joint level control, then camera models, image processing, feature extraction and multi-view geometry, and finally bringing it all together with an extensive discussion of visual servo systems.
Preface to the second edition
It seems only yesterday that I turned in the manuscript for the first edition of this book, but it was in fact December 2010, the end of 20 months of writing. So the oldest parts of the book are over 6 years old – it’s time for an update!
The revision principle was to keep the good (narrative style, code as a first-class citi- zen, soft plastic cover) and eliminate the bad (errors and missing topics). I started with the collected errata for the first edition and pencilled markup from a battered copy of the first edition that I’ve carried around for years. There were more errors than I would have liked and I thank everybody who submitted errata and suggested improvements.
The first edition was written before I taught in the university classroom or created the MOOCs, which is the inverse of the way books are normally developed. Preparing for teaching gave me insights into better ways to present some topics, particularly around pose representation, robot kinematics and dynamics so the presentation has been adjusted accordingly.
New content includes matrix exponential notation; the basics of screw theory and Lie algebra; inertial navigation; differential steer and omnidirectional mobile robots; a deeper treatment of SLAM systems including scan matching and pose graphs; greater use of MATLAB computer algebra; operational space control; deeper treatment of ma- nipulator dynamics and control; visual SLAM and visual odometry; structured light; bundle adjustment; and light-field cameras.
In the first edition I shied away from Lie algebra, matrix exponentials and twists but I think it’s important to cover them. The topic is deeply mathematical and I’ve tried to steer a middle ground between hardcore algebraic topology and the homog- enous transformation only approach of most other texts, while also staying true to the overall approach of this book.
All MATLAB generated figures have been regenerated to reflect recent improve- ments to MATLAB graphics and all code examples have been updated as required and tested, and are available as MATLAB Live Scripts.
The second edition of the book is matched by new major releases of my Toolboxes: Robotics Toolbox (release 10) and the Machine Vision Toolbox (release 4). These newer versions of the toolboxes have some minor incompatibilities with previous releases of the toolboxes, and therefore also with the code examples in the first edition of the book.