Mobile Robotics: A Practical Introduction
Mobile Robotics: A Practical Introduction is an excellent introduction to the foundations and methods used for designing completely autonomous mobile robots. In this book you are introduced to the fundamental concepts of this complex field via twelve detailed case studies which show how to build and program real working robots. This book provides a very practical introduction to mobile robotics for a general scientific audience, and is essential reading for final year undergraduate students and postgraduate students studying Robotics, Artificial Intelligence, Cognitive Science and Robot Engineering. Its update and overview of core concepts in mobile robotics will assist and encourage practitioners of the field, and set challenges to explore new avenues of research in this exciting field.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Making Sense of Raw Sensor Data
7 other sections not shown
achieved actual ART category ART2 artificial neural network autonomous mobile robots behaviour-based boxes classified clustering compass contingency table corner dead reckoning detected determine drift error environment equation example experimental experiments exploration FortyTwo function Further Reading hypothesis implement infrared infrared sensors input vector instinct rules intelligent landmarks layer learning steps localisation system machine learning map-building McCulloch and Pitts mean measure method motor action move Multilayer Perceptron Nehmzow neuron node object obstacle avoidance obtained odometry operation parameters path Perceptron perceptual aliasing performance physical symbol system Pitts neurons position predict Q-learning range real robot reinforcement learning representation robot behaviour robot control robot learning robot navigation systems robot-environment interaction route self-organising self-organising feature map sensor readings sensor signals sensory perception shown in figure simulation SOFM sonar sensors supervised learning task tion Training visits required truth table values wall following weight vector world model