Академический Документы
Профессиональный Документы
Культура Документы
Autonomous Mobile
Robots
Lecture: Monday 14.15 - 16.00, HG D 3.2
Exercises: Monday 16.15 - 18.00, HG K32 (VisDome)
(ONLY lecture of 26 April, 14.15 – 18.00, HG D2.1)
Roland Siegwart
Davide Scaramuzza
Service and
Personal Robots
Cyborgs
Exponential increase of complexity
© R. Siegwart, ETH Zurich - ASL
1 - Introduction
1
3 Autonomous Mobile Robots
The three key questions in Mobile Robotics
Where am I ?
Where am I going ? ?
How do I get there ?
Service Robots
Autonomous Robots/Cars
for Inner City Environments
Inspection Robots
Swimming Robots
2. Locomotion
4. Perception
Applications
Lecture Notes:
Introduction to Autonomous Mobile Robots
Roland Siegwart, Illah Nourbakhsh, Davide Scaramuzza
• Intelligent Robotics and Autonomous Agents series
• The MIT Press
• Massachusetts Institute of Technology
• Cambridge, Massachusetts 02142
• ISBN 0-262-19502-X
http://www.mobilerobots.org
What is the
difference
in brightness?
http://web.mit.edu/persci/people/adelson/checkershadow_downloads.html
© R. Siegwart, ETH Zurich - ASL
1
10 “Connecting” with the world
Tactility, key for controlling the real world
Knowledge, Mission
Data Base Commands
Localization Cognition
"Position"
Map Building Path Planning
Global Map
Information Path
Extraction Execution
Motion Control
Perception
Sensing Acting
Real World
Environment
mining
transportation
industry & service space sewage tubes
Newest generation of
Automatic Guided Vehicle
of VOLVO used to
transport motor blocks
from on assembly station
to an other. It is guided by
an electrical wire installed
in the floor but it is also
able to leave the wire to
avoid obstacles. There are
over 4000 AGV only at
VOLVO‟s plants.
Knowledge, Mission
Data Base Commands
Localization Cognition
"Position"
Map Building Path Planning
Global Map
Information Path
Extraction Execution
Motion Control
Perception
Sensing Acting
Real World
Environment
Control Loop
dynamically changing Two Approaches
no compact model available Classical AI
• complete modeling
many sources of uncertainty
• function based
• horizontal decomposition
"Position"
New AI, AL
Localization Cognition
Global Map • sparse or no modeling
• behavior based
Environment Model Path
Local Map • vertical decomposition
• bottom up
Perception Real World Motion Control
Environment
Classical AI
(model based navigation)
complete modeling
function based
horizontal
decomposition
New AI, AL
(behavior based navigation)
sparse or no modeling
behavior based
vertical decomposition
bottom up
Possible Solution
Combine Approaches
Environment Representation
Continuos Metric -> x,y,
Discrete Metric -> metric grid
Discrete Topological -> topological grid
Environment Modeling
Raw sensor data, e.g. laser range data, grayscale images
• large volume of data, low distinctiveness
• makes use of all acquired information
Low level features, e.g. line other geometric features
• medium volume of data, average distinctiveness
• filters out the useful information, still ambiguities
High level features, e.g. doors, a car, the Eiffel tower
• low volume of data, high distinctiveness
• filters out the useful information, few/no ambiguities, not enough information
Courtesy K. Arras
Metric Topological Maps Fully Metric Maps (continuos or
discrete)
y
200 m
50 km
2 km
100 km
x
{W}
© R. Siegwart, ETH Zurich - ASL
1 - Introduction
1
26 Methods for Navigation: Approaches with Limitations
Courtesy K. Arras
Odometric or initial sensors (gyro)
not applicable
expensive, inflexible
Believe state
Courtesy K. Arras
wy lw
r r
{W} wx
r x
4. Position Estimation:
2. Feature Extraction (e.g. line segments) e.g. Kalman filter, Markov
Odometry Observation
representation of uncertainties
optimal weighting acc. to a priori statistics
Courtesy K. Arras
e.g. disappearing position of robot -> position of wall
cupboard