Unmanned Wood shuttle - PowerPoint PPT Presentation

About This Presentation
Title:

Unmanned Wood shuttle

Description:

Unmanned. Wood shuttle. Takes the trees out of the forest. Manned Harvester ... Autonomously tracking the path while accounting for. Unplanned deviations from the path ... – PowerPoint PPT presentation

Number of Views:57
Avg rating:3.0/5.0
Slides: 2
Provided by: thomash60
Category:

less

Transcript and Presenter's Notes

Title: Unmanned Wood shuttle


1
Autonomous Navigation in Forest Environment
THE VISION OF FORESTRY 2015?
  • GOALS FOR THE PILOT PROJECT
  • A prototype for a forest vehicle, capable of
  • Learning a path run by a human operator
  • Autonomously tracking the path while accounting
    for
  • Unplanned deviations from the path
  • Obstacles such as trees, human beings and
    animals
  • Manned Harvester
  • Hard to make autonomous
  • The driver supervises one or severalautonomous
    wood shuttles
  • Unmanned Wood shuttle
  • Takes the trees out of the forest

The work has been conducted on three different
target machines, each with increased complexity.
This approach greatly simplifies the research and
development of both hardware and software.
TESTS WITH VALMET 830
A NEW PATH-TRACKING ALGORITHM Follow-the-Past
The resulting set steering angle is the sum of
Fa, Fß and F?.When the distance to the path has
been reduced close to zero, the set steering
angle essentially equals F?, i.e. the forest
machine tries to mimic the recorded steering
commands of the human driver.
The forest machine initially started 15 meters
away from the recorded path
Well known problem of cutting the corners with
traditional algorithms
Follow the Past consists of three reactive
behaviors, which are then fused into a single
steering command Fa Move towards path Fß
Turn towards the recorded orientation F? Mimic
the recorded steering
(a) Follow the Past
(b) Follow the Carrot
(c) Pure Pursuit
SYSTEM ARCHITECTURE
SENSOR FUSION
Overview of the architecture of the developed
system. The high- and low-level parts are split
between two computers. The forest machine shown
is a vision of what a future autonomous shuttle
could look like.
Since the GPS position may be incorrect when the
vehicle tilts, the fused position is corrected
with respect to vehicle roll and pitch.
Position from Laser odometry is fused with other
sensors to get a better estimate of the position
when the GPS does not work. The position error
from the laser is less than 0.5 m in this example.
Department of Computing Science Umeå
University Sweden
Project sponsored by Carl Tryggers Stiftelse,
Kempe Foundations, Komatsu, Land
SystemsHägglunds, LKAB, Umeå University, VINNOVA
Thomas Hellström thomash_at_cs.umu.se
Ola Ringdahl ringdahl_at_cs.umu.se
Write a Comment
User Comments (0)
About PowerShow.com