Включает полное и систематизированное изложение материала по учебной программе курса «Интеллектуальные системы управления роботами». Включает темы, посвященные введению в нейронные сети, их применению, основам обучения нейронных сетей, многослойным нейронным сетям с прямой связью, передовым методам
Neural Network Perception for Mobile Robot Guidance
✍ Scribed by Dean A. Pomerleau (auth.)
- Publisher
- Springer US
- Year
- 1993
- Tongue
- English
- Leaves
- 198
- Series
- The Springer International Series in Engineering and Computer Science 239
- Edition
- 1
- Category
- Library
No coin nor oath required. For personal study only.
✦ Synopsis
Dean Pomerleau's trainable road tracker, ALVINN, is arguably the world's most famous neural net application. It currently holds the world's record for distance traveled by an autonomous robot without interruption: 21.2 miles along a highway, in traffic, at speedsofup to 55 miles per hour. Pomerleau's work has received worldwide attention, including articles in Business Week (March 2, 1992), Discover (July, 1992), and German and Japanese science magazines. It has been featured in two PBS series, "The Machine That Changed the World" and "By the Year 2000," and appeared in news segments on CNN, the Canadian news and entertainment program "Live It Up", and the Danish science program "Chaos". What makes ALVINN especially appealing is that it does not merely drive - it learns to drive, by watching a human driver for roughly five minutes. The training inputstothe neural networkare a video imageoftheroad ahead and thecurrentposition of the steering wheel. ALVINN has learned to drive on single lane, multi-lane, and unpaved roads. It rapidly adapts to other sensors: it learned to drive at night using laser reflectance imaging, and by using a laser rangefinder it learned to swerve to avoid obstacles and maintain a fixed distance from a row of parked cars. It has even learned to drive backwards.
✦ Table of Contents
Front Matter....Pages i-xv
Introduction....Pages 1-8
Network Architecture....Pages 9-32
Training Networks “On-The-Fly”....Pages 33-50
Training Networks With Structured Noise....Pages 51-69
Driving Results and Performance....Pages 71-83
Analysis of Network Representations....Pages 85-106
Rule-Based Multi-network Arbitration....Pages 107-116
Output Appearance Reliability Estimation....Pages 117-131
Input Reconstruction Reliability Estimation....Pages 133-150
Other Applications - The SM 2 ....Pages 151-159
Other Vision-based Robot Guidance Methods....Pages 161-171
Conclusion....Pages 173-177
Back Matter....Pages 179-191
✦ Subjects
Control, Robotics, Mechatronics;Statistical Physics, Dynamical Systems and Complexity;Computer Imaging, Vision, Pattern Recognition and Graphics;Artificial Intelligence (incl. Robotics)
📜 SIMILAR VOLUMES
These volumes explore recent research in neural networks that has advanced our understanding of human and machine perception. Contributions from international researchers address both theoretical and practical issues related to the feasibility of neural network models to explain human perception and
This book provides guidance on the verification and validation of neural networks/adaptive systems. Considering every process, activity, and task in the lifecycle, it supplies methods and techniques that will help the developer or V&V practitioner be confident that they are supplying an adaptive/neu