From Manipulators to Mobile Robots

1
From Manipulators to Mobile Robots
1
2
General Control Scheme for Mobile Robot Systems
1
Knowledge,
Mission
Data Base
Commands
Cognition
Localization
"Position"
Path Planning
Map Building
Global Map
Environment Model
Path
Local Map
Information
Path
Extraction
Execution
Perception
Motion Control
Raw data
Actuator Commands
Sensing
Acting
Real World
Environment
3
Applications of Mobile Robots
1

• Indoor Outdoor
• Structured Environments Unstructured Environments

4
Automatic Guided Vehicles
1

• Newest generation of Automatic Guided Vehicle
  (AGV) of VOLVO used to transport motor blocks
  from one 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
  VOLVOs plants.

5
Helpmate
1

• HELPMATE is a mobile robot used in hospitals for
  transportation tasks. It has various on board
  sensors for autonomous navigation in the
  corridors. The main sensor for localization is a
  camera looking to the ceiling. It can detect the
  lamps on the ceiling as reference (landmark).
  http//www.ntplx.net/helpmate/

6
BR700 Cleaning Robot
1

• BR 700 cleaning robot developed and sold by
  Kärcher Inc., Germany. Its navigation system is
  based on a very sophisticated sonar system and a
  gyro. http//www.kaercher.de

7
ROV Tiburon Underwater Robot
1

• Picture of robot ROV Tiburon for underwater
  archaeology (teleoperated)- used by MBARI for
  deep-sea research, this autonomous underwater
  vehicle (AUV) provides autonomous hovering
  capabilities for the human operator.

8
The Pioneer
1

• Picture of Pioneer, the teleoperated robot that
  is supposed to explore the Sarcophagus at
  Chernobyl

9
The Pioneer
1

• PIONEER 1 is a modular mobile robot offering
  various options like a gripper or an on board
  camera. It is equipped with a sophisticated
  navigation library developed at Stanford Research
  Institute (SRI). http//www.activmedia.com/robots

10
The B21 Robot
1

• B21 of Real World Interface is a sophisticated
  mobile robot with up to three Intel Pentium
  processors on board. It has all different kinds
  of on board sensors for high performance
  navigation tasks.http//www.rwii.com

11
The Khepera Robot
1

• KHEPERA is a small mobile robot for research and
  education. It sizes only about 60 mm in diameter.
  Additional modules with cameras, grippers and
  much more are available. http//diwww.epfl.ch/lami
  /robots/K-family/ K-Team.html

12
Forester Robot
1

• Pulstech developed the first industrial like
  walking robot. It is designed moving wood out of
  the forest. The leg coordination is automated,
  but navigation is still done by the human
  operator on the robot.http//www.plustech.fi/

13
Robots for Tube Inspection
1

• HÄCHER robots for sewage tube inspection and
  reparation. These systems are still fully
  teleoperated. http//www.haechler.ch

• EPFL / SEDIREP Ventilation inspection robot

14
Sojourner First Robot on Mars
1

• The mobile robot Sojourner was used during the
  Pathfinder mission to explore the mars in summer
  1997. It was nearly fully teleoperated from
  earth. However, some on board sensors allowed for
  obstacle detection.http//ranier.oact.hq.nasa.gov
  /telerobotics_page/telerobotics.shtm

15
NOMAD, Carnegie Mellon / NASA
1
http//img.arc.nasa.gov/Nomad/
16
The Honda Walking Robot
1
http//world.honda.com/ASIMO/
17
Toy Robot Aibo ERS-7 from Sony
1
stereo microphones
3 joints for the head
WLan (802.11b)
infrared sensor
576 MHz Mips CPU 64 MB RAM
CMOS camera 208 x 160 pixel
3 joints per leg
loudspeaker
Li-ion battery pack 7.4V, 2200mAh
memorystick reader
18
General Control Scheme for Mobile Robot Systems
1
Knowledge,
Mission
Data Base
Commands
Cognition
Localization
"Position"
Path Planning
Map Building
Global Map
Environment Model
Path
Local Map
Information
Path
Extraction
Execution
Perception
Motion Control
Raw data
Actuator Commands
Sensing
Acting
Real World
Environment
19
Two Approaches
1

• 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

20
Mixed Approach Depicted into the General Control
Scheme
1
21
Environment Representation and Modeling
1

• Odometry
• not applicable

• Modified Environments
• expensive, inflexible

• Feature-based Navigation
• still a challenge for artificial systems

Corridor crossing
Elevator door
Entrance
How to find a treasure
Courtesy K. Arras
Landing at night
Eiffel Tower
22
Map Categories
1

• Recognizable Locations

• Topological Maps

Courtesy K. Arras

• Metric Topological Maps

• Fully Metric Maps (continuous or discrete)

23
Human Navigation
1
Courtesy K. Arras
Topological with imprecise metric information
24
Navigation Approaches with Limitations
1

• Incrementally
• (dead reckoning)
• Odometric or initial sensors (gyro)
• not applicable

• Modifying the environments
• (artificial landmarks / beacons)
• Inductive or optical tracks (AGV)
• Reflectors or bar codes
• expensive, inflexible

Courtesy K. Arras
25
Quantitative Metric Approach for Localization
1

• 1. A priori Map Graph, metric
• 2. Feature Extraction (e.g. line segments)

• 3. Matching
• Find correspondence
• of features
• 4. Position Estimation
• e.g. Kalman filter, Markov
• representation of uncertainties
• optimal weighting acc. to a priori statistics

Courtesy K. Arras
26
Gaining Information through Motion
1
Believe state
Multi-hypotheses tracking
Courtesy S. Thrun, W. Burgard
27
Grid-Based Metric Approach
1

• Grid Map of the Smithsonians National Museum of
  American History in Washington DC. (Courtesy of
  Wolfram Burger et al.)
• Grid 400 x 320 128000 points

Courtesy S. Thrun, W. Burgard
28
Quantitative Topological Approach for Localization
1

• 1. A priori Map Graph
• locally unique
• points
• edges
• 2. Method for determining the local uniqueness
• e.g. striking changes on raw data level or
  highly distinctive features

3. Library of driving behaviors e.g. wall or
midline following, blind step, enter door,
application specific behaviors Example
Video-based navigation with natural
landmarks
Courtesy of Lanser et al. 1996
29
The Problems of Map Building
1
1. Map Maintaining Keeping track of changes in
the environment e.g. disappearing cupboard
- e.g. measure of belief of each environment
feature

• 2. Representation and Reduction of Uncertainty
• position of robot -gt position of wall
• position of wall -gt position of robot
• probability densities for feature positions
• additional exploration strategies

Courtesy K. Arras
30
Exploration and Graph Construction
1
1. Exploration

• 2. Graph Construction

Courtesy K. Arras
31
Control of Mobile Robots
1
global
local
32
Museum Tour Guide Robot
1
Thrun, Stanford University
33
Autonomous Indoor Navigation
1
Thrun, CMU
34
Tour-Guide Robot
1
EPFL _at_ expo.02
35
Autonomous Indoor Navigation
1

• very robust on-the-fly localization
• one of the first systems with probabilistic
  sensor fusion
• 47 steps,78 meter length, realistic office
  environment,
• conducted 16 times gt 1km overall distance
• partially difficult surfaces (laser), partially
  few vertical edges (vision)

Pygmalion EPFL
36
Autonomous Robot for Planetary Exploration
1
ASL EPFL
37
Humanoid Robots
1
Sony
38
GuideCane, University of Michigan
1
http//www.engin.umich.edu/research/mrl/
39
LaserPlans Architectural Tool
1
ActivMedia Robotics
40
Autonomous Indoor Mapping
1
Courtesy of Sebastian Thrun
41
Outdoor Mapping without GPS
1
map (trees) and path
University of Sydney
Courtesy of Eduardo Nebot
42
Real-Time Multi Robot Exploration
1
43
The Dyson Vacuum Cleaner Robot
1
44
The Cye Personal Robot
1

• Two-wheeled differential drive robot
• Controlled by remote PC (19.2 kb)
• Options
• vacuum cleaner
• trailer

45
Cyes Navigation Concept
1