Autonomous Forest Machines

ISBN-13: 9783639043433 / Angielski / Miękka / 2008 / 160 str.

Ola Ringdahl

Opis

With continued development of forest machines the operators risk becoming a bottleneck, due to the ever increasing pace they have to work in. Different kind of aids for the operators will become necessary to lessen the workload. Development of autonomous forest machines aims at meeting this demand. This book describes an ongoing project of which the purpose is designing and developing techniques and algorithms for such a vehicle. The focus is on some of the components necessary to accomplish autonomous navigation, which involves sensing and moving safely along a user-defined path in a dynamic forest environment. A new path-tracking algorithm is introduced and demonstrated as superior to standard algorithms, such as Follow the Carrot and Pure Pursuit. Localization is accomplished by a neural network that fuses data from a GPS, a gyro, and wheel odometry. Results from successful field tests on a full-size forest machine with autonomous path tracking, including obstacle avoidance, are presented. The book will be of interest to students and researchers in the area of autonomous vehicles and artificial intelligence.

O autorze

Ringdahl, Ola Ola Ringdahl works as a PHD-student at the Department of Computing Science at Umeå University, Sweden. He received his Lic. Eng. from the same department in 2007. His research interests are in autonomous vehicles, path tracking, obstacle avoidance and system integration.