ROBOTIKA Introduction:

Mobile Robotics
PROFILE
Igi Ardiyanto
Field of Interest :
Robotics
Computer Vision
Intelligent Transportation System
Embedded System
Parallel Computing

More Information ??
http://te.ugm.ac.id/~igi
COURSE DESCRIPTION
• An introduction to mobile robots and current approaches to
robot autonomy.
• Topics include:
 Mobile robot systems and modeling
 Control structures
 Sensors & Estimation
 Localization and Mapping
 Motion planning
 Multi-robot systems.
 COURSE DESCRIPTION
• Required Text:
– “An Introduction to Autonomous Robots”,
Roland Siegwart and Illah R. Nourbakhsh,
MIT Press, 2004
– “Probabilistic Robotics”, S. Thrun, W.
Burgard
• Recommended Texts:
– “Behavior-Based Robotics”,
Ronald C. Arkin, MIT Press, 1998
– “Principles of Robot Motion”, Choset et.
4
Al., MIT Press, 2005
 COURSE OBJECTIVE
• Provide robots with the ability to
accomplish tasks autonomously.

• Autonomously?
– Different levels dependant on application

Tele-Operation Fully Autonomous

5
EVOLUTION OF ROBOTICS RESEARCH
• Robotics has traditionally been an interdisciplinary area among
mechanics, electronics, artificial intelligence, cybernetics, biology,
psychology, computer vision, etc...
• Classic robotics (mid 80’s) assume perfect information
(models, measurements)
• Reactive paradigm (mid-80’s) use no models and rely on a short
connection between sensing and control
• Hybrid approaches (since 90’s) were explored with model-
based decision at higher levels and reactive functions at
lower levels;
• Probabilistic Robotics (since mid-90’s) explores inaccurate
models and imperfect sensors. (G. Hager)
 HISTORICAL EXAMPLES
• The Tortoise (Walter, 1950)

7 Courtesy of Hans Moravec

 HISTORICAL EXAMPLES
• Shakey (SRI 1969)

8 Stanford Research Institute

 HISTORICAL EXAMPLES
• Stanford Cart (Moravec, 1977)

25 Courtesy of Hans Moravec

 APPLICATION EXAMPLES
• Planetary Exploration

26 Image of jpl’s mars rover

 APPLICATION EXAMPLES
• Submersible ROV: Remotely Operated Vehicle

27 MBARI’s ROV Ventana

 APPLICATION EXAMPLES
• Legged Robots

28 jpl’s Lemur robot

 APPLICATION EXAMPLES
• Security Robots

29 ActiveMedia’s PatrolBot
 APPLICATION EXAMPLES
• Multi-Robot Systems

30 USC’s robot platforms

 APPLICATION EXAMPLES
• UAVs: Unmanned Aerial Vehicles

31 AUV “Big Blue” from Advanced Ceramics Research, Inc.

 APPLICATION EXAMPLES
• AGVs: Autonomic Guided Vehicles

32 Volvo’s AGV
 APPLICATION EXAMPLES
• Competitions

33 2002 RoboCup Tournament – Cornell Team

PERSON TRACKING

View from 3rd person View from Robot’s

camera

Stereo Camera Person

Tracking
Robot
PC Laptop
Image
Processing

Navigation
Laser Sensor
PERSON TRACKING

PATH/ MOTION
PLANNING
MAPPING
SIMULTANOUS LOCALIZATION AND MAPPING
OUTDOOR NAVIGATION

Road edge with particle filter Robot navigation

OUTDOOR NAVIGATION

Scene recognition Omnidirectional camera view

Robust position estimation
GRASPING WITH OBJECT POSE ESTIMATION

Object pose estimation

Recognizing object and its pose

HUMAN ROBOT INTERACTION

Copying human activity

ROBOT NAVIGATION
 ROBOT NAVIGATION
• For autonomous behavior, mobile robots
need the ability to navigate:
– Learn the environment-> “Model”
– Estimate where it is in the environment->
“Localize”
– Move to desired locations in the environment

26
 NAVIGATION PROBLEM
• Problem Characteristics
– Environments are Known versus Unknown
– Environments are Static versus Dynamic
– Environments are Structured versus
Unstructured (Indoors versus Outdoors?)

• Most robot navigation systems are

tailored to the problem characteristics.

27
 APPROACHES TO CONTROL
• Open-Loop Control
w
xdesired u x
K G
control plant

• Closed-Loop Control w
xdesired u x
K G
control plant

28
 APPROACHES TO CONTROL
1. Planning Based Control
– Traditional methods born out of AI (1960’s +)

2. Reactive (i.e. Behavior) Based Control

– More recent (mid to late 1980’s)

3. Mixture of Planning and Reactive

– Today

29
 APPROACHES TO CONTROL
Planning Based Control

• Through perception and sensors fusion,

a model of the “real” world is captured in
memory.
• A goal is given and a plan is generated,
assuming the “real” world is not
changing.
• Then, the “plan” is executed, one
(abstract) “operation” at a time.
30
 APPROACHES TO CONTROL
Planning Based Control
• Example: A robot is equipped with a
camera and two arms to perform an
assembly task.
– Goal: put part A into part B
– World: where are A and B?
– Plan:
• move left arm to A;
• move right arm to B;
• grab A; grab B;
• move left and right arm closer;
31
• assemble
 APPROACHES TO CONTROL
Planning Based Control

• Example continued:
– What the camera sees is a world of “pixels”.
– What is “interesting” in the “real” world to be
captured?
– At what level of details should we represent
the “real” world?
– What if during plan execution, the “real” world
changes? e.g., drop part A.
32
 APPROACHES TO CONTROL
Planning Based Control

• Planning-based navigation architecture

33
 APPROACHES TO CONTROL
Planning Based Control

• Perception, modeling and planning are

computationally intensive.
• Our model of the “real” world must be at
all times accurate (consistent and
reliable).
• Sudden changes in the world may not be
reflected instantly in our model.
• This approach works well in a predictable
34 world.
 APPROACHES TO CONTROL
Behavior-Based Control

• Actions are connected to precepts via

“behaviors”.
• No internal model: The real world is our
model.
• A robot reacts to changes and exhibits
complex behaviors due to both internal
and external interactions.
35
 CONTROL STRUCTURES
Behavior-Based Control

• A robot is equipped with many “simple”

behaviors.
• Each behavior defines its own sensor
data and actions.
• Interactions among the behaviors are
resolved by coordination.
• These behaviors are concurrent and
independent; they react to changes
36
instantly.
 CONTROL STRUCTURES
Behavior-Based Control

• Example: A simple roaming mobile robot

is equipped with the following behaviors:

37
 CONTROL STRUCTURES
Behavior-Based Control

• Different behaviors may share same

sensors and/or actuators.
• Noisy sensor data are masked by
redundant behaviors.
• Competitive or cooperative actions are
handled by careful coordination.
• Behaviors may be added or deleted
incrementally.
38
 CONTROL STRUCTURES
Behavior-Based Control

• Subsumption Architecture
– Behavioral coordination can be based on a fixed
priority of suppression.

39
 CONTROL STRUCTURES
Behavior-Based Control

• Subsumption Architecture
– Behavioral coordination can be based on a
fixed priority of suppression.

40
 CONTROL STRUCTURES
Behavior-Based Control

• Each behavior may generate more than

one type of actions.
• Multiple subsumption orderings may
coexist at the same time.
• A behavior may be lower in one ordering,
but be higher in an other.
• Each behavior’s decision “cycle” time is
independent.
41
 CONTROL STRUCTURES
Planning Based Control
Prior Knowledge Operator Commands

Localization Cognition

Perception Motion Control

42
 CONTROL STRUCTURES
Behavior-Based Control
Prior Knowledge Operator Commands

Localization Cognition
Behaviors

Perception Motion Control

43
 MOTION CONTROL
• Software: Low-Level Control (e.g. PID)

• Hardware: Motors, legs, wheels

44
 PERCEPTION
• Hardware: Sensors

• Software: Filtering raw data

45
 LOCALIZATION
• Modeling and Mapping

46
 COGNITION
• Hardware: Processors

• Software: Planning Algorithms

47
 CONTROL ARCHITECTURES
• Today, most robots control systems have
a mixture of planning and behavior-based
control strategies.
• To implement these strategies, a control
architecture is used.
• Control architectures should be:
– Modular

48
 CONTROL ARCHITECTURES
Desired Characteristics

• Code Modularity
– Allows programmers to interchange
environment types sensors, path planners,
propulsion, etc.
• Localization
– Embed specific navigation functions within
modules to allow different levels of control
(e.g. from task planning to wheel velocity
control)

49
 CONTROL ARCHITECTURES
Decomposition

• Decomposition allows us to modularize

our control system based on different
axes:

1. Temporal Decomposition
– Facilitates varying degrees of real-time processes
2. Control Decomposition
– Defines how modules should interact: serial or
parallel?
50
 CONTROL ARCHITECTURES
Temporal Decomposition
Spatial • Factors affecting
Locality
temporal
decomposition:
– Sensor response time
– Temporal memory and
horizon
– Spatial Locality
– Context Specificity

Context T. Memory & Sensor

Specificity Horizon Response Time
51
 CONTROL ARCHITECTURES
Temporal Decomposition
• Example

52
 CONTROL ARCHITECTURES
Tiered Architectures
• A general tiered architecture for episodic planning
• Role of the Executive is:
 Switch behaviors
 Monitor failures
 Call the planner

• Planning only when required (e.g. blockage)

53
 CONTROL ARCHITECTURES
Tiered Architectures
• A tiered architecture for integrated planning

• Planning is fast and is embedded as a behavior.

54
 CONTROL ARCHITECTURES
Tiered Architectures
• An integrated planning architecture
• Role of the Executive is:
– Switch behaviors
– Monitor failures
– Call the planner

55
 CONTROL ARCHITECTURES
Control Decomposition
• An example of a control decomposition using a
mixture of serial and parallel approaches.

56