Probabilistic Robotics (Intelligent Robotics and Autonomous Agents series)

Just went through this book in a week for my own research. This was a nice read and a great reference book for all the probabilistic theory and algorithms that are essential to robotics and AI these days, in cutting edge research. Strongly recommended as a book that you will want to keep on your closest shelf or desk corner. Be warned that this is definitely a graduate-level textbook, so don't see this as a "robotics for dummies" kind of book, be prepared with at least some prior basis in probabilistic methods, estimation, and/or machine learning. This book will be a great jump forward into robotics for a finishing undergraduate, or a firm reference book for graduate students or researchers. The amount of mathematical derivations is just about perfect (doesn't break readability, but provides just enough to avoid any "mathemagical" leaps in the formulations). Algorithms are concise, concrete and pertinent (as opposed to many other probabilistic texts that present algorithms that are often written in very high-level pseudo-code that makes it hard to understand what a concrete implementation really involves doing). Lots of concrete examples that make it really clear why this paradigm for robotics software is necessary and by far the most powerful (although a real computational challenge!).

I work in avionics, not robotics, but I ordered this book because it seemed to cover a lot of the subjects that are now making their way into avionics systems. In particular, I was interested in its coverage of Kalman Filters and POMDPs.I have to say that the other positive reviews are well-warranted. I have not before encountered such clear explanations of Bayes filtering, Kalman Filters (including EKFs and UKFs), even in spite of having encountered many books and papers on these subjects. The authors seem to go out of their way to present the material with a logical and clear-cut progression that doesn't skip essential steps with the typical "the reader can clearly see that..." kinds of hand-waiving I have seen in other texts.To be honest, I can't comment on the parts related to robot dynamics and SLAM, but as for chapters 1-4 and the chapters on POMDPs, I would have to say that this book presents the material in a better and more clear way than I have ever seen it presented before.

As someone with a multi-discipline background that includes some control theory, I am always frustrated by the "explanations" that control theorists attempt to put forward for the Kalman filter, and find that the best explanations actually come from other fields. Prior to stumbling upon this book, the best explanation of the Kalman filter I had read actually came from a book on Bayesian statistics. It makes sense that this book would have the same basic Bayesian approach, but would also extend the technique in exactly the manner needed to properly do controls and robotics. Further it fits the technique into a larger, cross-disciplinary, landscape of estimation, sensing and modeling techniques from both "controls" and "robotics" (which, despite sounding like two forms of the same field, tend to actually have distinct and disparate communities which have surprising trouble talking to one another).

This textbook is the standard reference for probabilistic robotics in the areas of navigation and mapping. One of the authors is the director of the Stanford AI lab and headed the winning entry in the DARPA Grand Challenge in 2007, which needless to say means he understands and has developed many of the techniques in the book. The algorithms are laid out and explained at different depths of understanding, which sometimes allows them to be used without reading the rigorous mathematical derivations that are included. Within the first week of having this book, I found that my method of estimating odometry in the prediction step of a Kalman filter could be improved with a different estimation. In addition, since the book provided a mathematical derivation, I could compare the two techniques and explain under what assumptions my approximation fails to do well.

This is a brilliant book, must read and must have on a desk of a robotics engineer, especially on the software side.One can tell how much effort and hard work the authors put into writing the book.Very clean and concise text.The book not just teaches the subject, but gives a lot of ideas on further research topics.It might sound like the authors have been primarily concerned with SLAM and motion planning problems. The truth is that the methods they describe can be applied in many other areas, just use your brain.Wish there were more books like that.

This book gives good theoretical foundation for modern algorithms usedin the field of robotics, state estimation, SLAM, motion planning.May be used as good undergrad or graduation level study material.

Short of writing your code for you, this tolme, provides general algorithms that can be applied to any sensor or configuration. It is not comprehensive in the number of variations on the basic algorithm, but allows sufficient background understanding to allow users to research specific variations from other publications with a modest chance of understanding the theory behind it.

Excellent book for master degree students in robotics, it contains a large variety of topics which are just explored enough to understand and to allow you for further research. The conditions of the book were great, just a small scratch on a corner probably due to the delivery process. The book is totally recommended. Greetings.