Introduction to Robotics - Computer and Information...
Transcript of Introduction to Robotics - Computer and Information...
9/6/2005 1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Introduction to Robotics
CSc 84010 Fall 2005Simon ParsonsBrooklyn College
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Textbook
Intelligent Robotics and Autonomous Agents series
The MIT PressMassachusetts Institute of Technology
Cambridge, Massachusetts 02142ISBN 0-262-19502-X
(slides taken from those provided (slides taken from those provided byby Siegwart Siegwart and and Nourbakhsh Nourbakhsh with with a (few) additions)a (few) additions)
9/6/2005 2
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Additional TextAdditional Text
Intelligent Robotics and Autonomous Agents series
The MIT PressMassachusetts Institute of Technology
Cambridge, Massachusetts 02142ISBN 0-262-02578-7
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Autonomous Mobile Robots
The three key questions in Mobile RoboticsWhere am I ?Where am I going ?How do I get there ?
To answer these questions the robot has tohave a model of the environment (given or autonomously built)perceive and analyze the environmentfind its position within the environment plan and execute the movement
This course will deal with Locomotion and Navigation (Perception, Localization, Planning and motion generation)
1
?
9/6/2005 3
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Content of the Course
1. Introduction
2. Locomotion
3. Behaviour-based robotics
4. Mobile Robot Kinematics
5. Perception
6. Mobile Robot Localization
7. Planning and Navigation
Other Aspects of Autonomous Mobile Systems
Applications
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Goal of today’s lecture (1/14)
Introduce the basic problems of mobile roboticsthe basic questionsexamples and challenges
Introduce some basic terminologyEnvironment representation and modeling
Introduce the key challenges of mobile robot navigationLocalization and map-building
Some examples/videos showing the state-of-the-art
1
9/6/2005 4
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
From Manipulators to Mobile Robots
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Raw data
Environment ModelLocal Map
"Position"Global Map
Actuator Commands
Sensing Acting
InformationExtraction
PathExecution
CognitionPath Planning
Knowledge,Data Base
MissionCommands
Path
Real WorldEnvironment
LocalizationMap Building
Mot
ion
Con
trol
Perc
epti
on
General Control Scheme for Mobile Robot Systems
1
9/6/2005 5
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Applications of Mobile Robots
Indoor OutdoorStructured Environments Unstructured Environments
transportationindustry & service
cleaning ..large buildings
customer supportmuseums, shops ..
surveillancebuildings
research,entertainment,
toy underwater
space
forestagriculture
construction
air
demining
mining
sewage tubes
fire fightingmilitary
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Automatic Guided Vehicles
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’splants.
1
9/6/2005 6
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Helpmate
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/
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
BR700 Cleaning Robot
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
1
9/6/2005 7
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
ROV Tiburon Underwater Robot
Picture of robot ROV Tiburon for underwater archaeology (teleoperated)- used by MBARI for deep-sea research, this UAV provides autonomous hovering capabilities for the human operator.
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The Pioneer
Picture of Pioneer, the teleoperated robot that is supposed to explore the Sarcophagus at Chernobyl
1
9/6/2005 8
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The Pioneer
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
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The B21 Robot
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
1
9/6/2005 9
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The Khepera Robot
KHEPERA is a small mobile robot for research and education. It is only about 60 mm in diameter. Additional modules with cameras, grippers and much more are available. More than 700 units were sold by the end of 1998). http://diwww.epfl.ch/lami/robots/K-family/ K-Team.html
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Forester Robot
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.
1
9/6/2005 10
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Robots for Tube Inspection
HÄCHER robots for sewage tube inspection and reparation. These systems are still fully teleoperated. http://www.haechler.ch
EPFL / SEDIREP: Ventilation inspection robot
1
A wide variety of snake robots (Bekey)
(EPFL Inspection video)(EPFL Inspection video)
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
GuideCane, University of Michiganhttp://www.engin.umich.edu/research/mrl/
1
9/6/2005 11
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
LaserPlans Architectural Tool (ActivMedia Robotics)
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Sojourner, First Robot on Mars
The mobile robot Sojourner was used during the Pathfinder mission to explore the mars in summer 1997. It was nearly fully teleoperatedfrom earth. However, some on board sensors allowed for obstacle detection.http://ranier.oact.hq.nasa.gov/telerobotics_page/telerobotics.shtm
1
(NASA Rover Video)(NASA Rover Video)
9/6/2005 12
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
NOMAD, Carnegie Mellon / NASAhttp://img.arc.nasa.gov/Nomad/
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Aibo Entertainment Robot
Sizelength about 25 cm
Sensorscolor camerastereo microphone
1
(2 (2 RoboCupRoboCup Videos)Videos)
9/6/2005 13
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The Honda Walking Robot http://www.honda.co.jp/tech/other/robot.html
1
(Honda video)(Honda video)
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Humanoid Robots (Sony Qrio)
Sony’s latest robotNot yet on sale (target price $10,000)
1
(3 (3 Qrio Qrio videos)videos)
9/6/2005 14
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
General Control Scheme for Mobile Robot Systems
1
Raw data
Environment ModelLocal Map
"Position"Global Map
Actuator Commands
Sensing Acting
InformationExtraction
PathExecution
CognitionPath Planning
Knowledge,Data Base
MissionCommands
Path
Real WorldEnvironment
LocalizationMap Building
Mot
ion
Con
trol
Perc
epti
on
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Control Architectures / Strategies
Control Loopdynamically changingno compact model availablemany sources of uncertainty
Two ApproachesClassical AI
o complete modelingo function basedo horizontal decomposition
New AI, ALo sparse or no modelingo behavior basedo vertical decompositiono bottom up
1
"Position" Global Map
Perception Motion Control
Cognition
Real WorldEnvironment
Localization
PathEnvironment ModelLocal Map
9/6/2005 15
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Two Approaches
Classical AI(model based navigation)
complete modelingfunction basedhorizontal decomposition
New AI, AL(behavior based navigation)
sparse or no modelingbehavior basedvertical decompositionbottom up
Possible Solution
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Mixed Approach Depicted into the General Control Scheme
1
Perception Motion Control
CognitionLocalization
Real WorldEnvironment
Perc
eptio
n to
Actio
n
Obs
tacl
eAv
oida
nce
Posi
tion
Feed
back
Path
Environment Model
Local Map
Local Map
PositionPosition
Local Map
9/6/2005 16
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Environment RepresentationContinuous Metric -> x,y,θDiscrete Metric -> metric gridDiscrete Topological -> topological grid
Environment ModelingRaw sensor data, e.g. laser range data, grayscale images
o large volume of data, low distinctivenesso makes use of all acquired information
Low level features, e.g. lines & other geometric featureso medium volume of data, average distinctivenesso filters out the useful information, still ambiguities
High level features, e.g. doors, a car, the Eiffel towero low volume of data, high distinctivenesso filters out the useful information, few/no ambiguities, not enough information
Environment Representation and Modeling:
The Key for Autonomous Navigation
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Odometry
not applicable
Modified Environments
expensive, inflexible
Feature-based Navigation
still a challenge for artificial systems
Environment Representation and Modeling: How we do it!
121 9534
39
25
Corridorcrossing
Elevator door
Entrance
Eiffel TowerLanding at nightHow to find a treasure
1
Cou
rtesy
K. A
rras
9/6/2005 17
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Environment Representation: The Map CategoriesRecognizable Locations Topological Maps
2 km
100 km
200 m50 km
y
x{W}
Metric Topological Maps Fully Metric Maps (continuous or discrete)
1
Cou
rtesy
K. A
rras
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Environment Models: Continuous <-> Discrete ; Raw data <-> Features
Continuousposition in x,y,θ
Discretemetric gridtopological grid
Raw Dataas perceived by sensor
A feature (or natural landmark) is an environmental structure which is static, always perceptible with the current sensor system and locally unique.
Examplesgeometric elements (lines, walls, column ..)a railway stationa riverthe Eiffel Towera human beingfixed starsskyscraper
1
9/6/2005 18
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Human Navigation: Topological with imprecise metric information
~ 400 m
~ 1 km
~ 200 m
~ 50 m
~ 10 m
1
Cou
rtesy
K. A
rras
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
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
Methods for Navigation: Approaches with Limitations
1
Cou
rtesy
K. A
rras
9/6/2005 19
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Methods for Localization: The Quantitative Metric Approach
1. A priori Map: Graph, metric
2. Feature Extraction (e.g. line segments)
x
y
wxr
wyr
{W}
lwθr
3. Matching: Find correspondence of features
4. Position Estimation:e.g. Kalman filter, Markov
representation of uncertaintiesoptimal weighting acc. to a priori statistics
Odometry Observation
1
Cou
rtesy
K. A
rras
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Gaining Information through motion: (Multi-hypotheses tracking)
Belief state
1
Courtesy S. Thrun, W. Burgard
9/6/2005 20
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Grid-Based Metric ApproachGrid Map of the Smithsonian’s National Museum of American History in Washington DC. (Courtesy of Wolfram Burgard et al.)
Grid: ~ 400 x 320 = 128’000 points
1
Courtesy S. Thrun, W. Burgard
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Methods for Localization: The Quantitative Topological Approach
1. A priori Map: Graphlocally uniquepoints
edges
2. Method for determining the local uniqueness
e.g. striking changes on raw data levelor highly distinctive features
3. Library of driving behaviorse.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]
1
9/6/2005 21
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Autonomous Indoor Navigation (Pygmalion EPFL)
very robust on-the-fly localizationone of the first systems with probabilistic sensor fusion47 steps,78 meter length, realistic office environment,conducted 16 times > 1km overall distancepartially difficult surfaces (laser), partially few vertical edges (vision)
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Autonomous Indoor Navigation (Thrun, CMU)
1
(CMU_(CMU_ThrunThrun_Robots)_Robots)
9/6/2005 22
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Map Building: How to Establish a Map
1. By Hand
2. Automatically: Map Building
The robot learns its environment
Motivation:- by hand: hard and costly- dynamically changing environment- different look due to different
perception
3. Basic Requirements of a Map:a way to incorporate newly sensedinformation into the existing world modelinformation and procedures for estimating the robot’s positioninformation to do path planningand other navigation task (e.g. obstacle avoidance)
Measure of Quality of a maptopological correctnessmetrical correctness
But: Most environments are a mixture of predictable and unpredictable features→ hybrid approachmodel based vs behaviour based
123.5
predictability
1
Cou
rtesy
K. A
rras
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Map Building: The Problems
1. Map Maintaining: Keeping track of changes in the environment
e.g. disappearingcupboard
- e.g. measure of belief of each environment feature
2. Representation and Reduction of Uncertainty
position of robot -> position of wall
position of wall -> position of robot
probability densities for feature positionsadditional exploration strategies
?
1
Cou
rtesy
K. A
rras
9/6/2005 23
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Map Building: Exploration and Graph Construction
1. Exploration
- provides correct topology- must recognize already visited
location- backtracking for unexplored openings
2. Graph Construction
Where to put the nodes?
Topology-based: at distinctive locations
Metric-based: where features disappear or get visible
exploreon stackalreadyexamined
1
Cou
rtesy
K. A
rras
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
High-Speed Explotation and Mapping
Courtesy of Sebastian Thrun
1
((ThrunThrun_Mapping)_Mapping)
9/6/2005 24
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Control of Mobile Robots
Most functions for save navigation are ’local’ not involving localization nor cognition
Localization and global path planning
slower update rate, only when needed
This approach is pretty similar to what human beings do.
global
local
1
Raw data
Environment ModelLocal Map
"Position"Global Map
Actuator Commands
Sensing Acting
InformationExtraction
PathExecution
CognitionPath Planning
Knowledge,Data Base
MissionCommands
Path
Real WorldEnvironment
LocalizationMap Building
Mot
ion
Con
trol
Perc
epti
on
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Tour-Guide Robot (EPFL @ expo.02)
1
(2 Tour guide videos)(2 Tour guide videos)
9/6/2005 25
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Autonomous Robot for Planetary Exploration (ASL –
EPFL)
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Turning Real Reality into Virtual Reality
Courtesy of Sebastian Thrun
1
9/6/2005 26
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Outdoor Mapping (no GPS)
map (trees) and path
University of Sydney
Courtesy of Eduardo Nebot
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
All Terrain Locomotion (Shrimp EPFL)
1
9/6/2005 27
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Kismet (MIT)
Studies in human-robot interaction
1
(Kismet video)(Kismet video)
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Leonardo (MIT)
Collaboration with Stan Winston Studio
9/6/2005 28
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The Cye Personal Robot
Two-wheeled differential drive robotControlled by remote PC (19.2 kb)Options:
vacuum cleanertrailer
1
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Cye’s Navigation Concept
Unexplored Areas
KnownFree
Space
Known Obstacle
s
Danger
Zone
Home Base
Check-In Point Hot Point
1
9/6/2005 29
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Roomba
Commerically successful robotic vaccum cleaner
1 million sold by late 2004.
Simple control algorithmSpirals out to wall, then wall following.
Sophisticated hardwareTouch sensors, sonar.
(Bekey)
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
The Dyson Vacuum Cleaner Robot
1
9/6/2005 30
Autonomous Mobile Robots, Chapter 1
© R. Siegwart, I. Nourbakhsh
Summary
This lecture has introduced:Some of the more important issues in autonomous mobile roboticsSome of the solutions that have been identifiedand…Some of the huge variety of robots that are running around the world (and indeed other planets).Next lecture we start to look at the details.