Hanoi University of Science and Technology

Industrial Robot
Dr. Le Duc Do
Email: do.leduc@hust.edu.vn
 Goal of this course

 Study the structure of the industrial robot:

mechanical systems, power, motors, controls.
 Study the method of investigation of kinematic
and dynamic of industrial robot.
 Study the control system.
 Learn how to design mechanical structure of
industrial robot.
 Hands-on experience
 Motivation
 Intelligent Environments are aimed at improving
the inhabitants’ experience and task
performance
 Automate functions in the home
 Provide services to the inhabitants
 Decisions coming from the decision maker(s) in
the environment have to be executed.
 Decisions require actions to be performed on devices
 Decisions are frequently not elementary device
interactions but rather relatively complex commands
 Decisions define set points or results that have to be
achieved
 Decisions can require entire tasks to be performed
 Automation and Robotics in
Intelligent Environments
 Control of the physical environment
 Automated blinds
 Thermostats and heating ducts
 Automatic doors
 Automatic room partitioning
 Personal service robots
 House cleaning
 Lawn mowing
 Assistance to the elderly and handicapped
 Office assistants
 Security services
 Some Favorite Robots

HAL 9000. 2001, A Space Odyssey: 1968

Data. Star Trek: TNG: 1987

Robby. Forbidden Planet: 1956

Wall-e: 2008 Optimus Prime: 2007-current

 Some 21st century robots

https://www.nasa.gov/mis http://www.irobot.com/en/ http://asimo.honda.com/ASIMO

http://www.irobot.com/ _DCTM/News/images/highres/A
sion_pages/msl/multimed us/robots/defense/packb
SIMO_offers_tea.jpg
ia/pia16763b.html ot.aspx

http://www.airforce- http://www.pleoworld
technology.com/project .com/pleo_rb/eng/life
s/predator-uav/ form.php
http://www.cmu.edu/cm
http://www.toyota-
global.com/innovation/partn news/020906/020906_g
er_robot/concept.html race.html
 What is a robot?

 Definition:
 “A robot is a reprogrammable, multifunctional
manipulator designed to move material,
parts, tools, or specialized devices through
variable programmed motions for the
performance of a variety of tasks.” (Robot
Institute of America)
 Alternate definition: “A robot is a one-armed,
blind idiot with limited memory and which
cannot speak, see, or hear.”
 Robots
 Robota (Czech) = A worker of forced labor
From Czech playwright Karel Capek's 1921 play “R.U.R”
(“Rossum's Universal Robots”)
 Japanese Industrial Robot Association (JIRA) :
“A device with degrees of freedom that can be
controlled.”
 Class 1 : Manual handling device

 Class 2 : Fixed sequence robot

 Class 3 : Variable sequence robot

 Class 4 : Playback robot

 Class 5 : Numerical control robot

 Class 6 : Intelligent robot

 A Brief History of Robotics
 Mechanical Automata
 Ancient Greece & Egypt
 Water powered for ceremonies
 14th – 19th century Europe
 Clockwork driven for entertainment
 Motor driven Robots Maillardet’s Automaton
 1928: First motor driven automata
 1961: Unimate
 First industrial robot
 1967: Shakey
 Autonomous mobile research robot
 1969: Stanford Arm
 Dextrous, electric motor driven robot arm Unimate
Categories of Robots
 Manipulators
 Anchored somewhere: factory assembly lines,
International Space Station, hospitals.
 Common industrial robots
 Mobile Robots
 Move around environment
 UGVs, UAVs, AUVs, UUVs
 Mars rovers, delivery bots, ocean explorers
 Mobile Manipulators
 Both move and manipulate
 Packbot, humanoid robots
 Robots
 Robot Manipulators

 Mobile Robots
 Robots
 Walking Robots

 Humanoid Robots
What subsystems make up a
robot?
 Robots have:
 Sensors
 Stationary base
 Mobile
 Effectors
 Control/Software
 Very similar to an agent!
 Autonomous Robots
 The control of autonomous robots involves a
number of subtasks
 Understanding and modeling of the mechanism
 Kinematics, Dynamics, and Odometry
 Reliable control of the actuators
 Closed-loop control
 Generation of task-specific motions
 Path planning
 Integration of sensors
 Selection and interfacing of various types of sensors
 Coping with noise and uncertainty
 Filtering of sensor noise and actuator uncertainty
 Creation of flexible control policies
 Control has to deal with new situations
 Traditional Industrial Robots
 Traditional industrial robot control uses robot
arms and largely pre-computed motions
 Programming using “teach box”
 Repetitive tasks
 High speed
 Few sensing operations
 High precision movements
 Pre-planned trajectories and
task policies
 No interaction with humans
In-class Exercise
 As a group, discuss an activity that you
think could be automated by using a
robot.
 Define the tasks that the robot will
perform.
 What kind of special tooling is required?
Sketch if you will use any.
 Can the activity be justified
economically? Show your development
– do not simply say yes or no.
What are robots good at?
 What is hard for humans is easy for robots.
 Repetitive tasks.
 Continuous operation.
 Complicated calculations.
 Refer to huge databases.
 What is easy for a human is hard for robots.
 Reasoning.
 Adapting to new situations.
 Flexible to changing requirements.
 Integrating multiple sensors.
 Resolving conflicting data.
 Synthesizing unrelated information.
 Creativity.
What tasks would you give
robots?
 Dangerous
 space exploration
 chemical spill cleanup
 disarming bombs
 disaster cleanup
 Boring and/or repetitive
 welding car frames
 part pick and place
 manufacturing parts.
 High precision or high speed
 electronics testing
 surgery
 precision machining.
 Problems
 Traditional programming techniques for
industrial robots lack key capabilities necessary
in intelligent environments
 Only limited on-line sensing
 No incorporation of uncertainty
 No interaction with humans
 Reliance on perfect task information
 Complete re-programming for new tasks
 Requirements for Robots in
Intelligent Environments
 Autonomy
 Robots have to be capable of achieving task
objectives without human input
 Robots have to be able to make and execute their
own decisions based on sensor information
 Intuitive Human-Robot Interfaces
 Use of robots in smart homes can not require
extensive user training
 Commands to robots should be natural for
inhabitants
 Adaptation
 Robots have to be able to adjust to changes in the
environment
 Robots for Intelligent
Environments
 Service Robots
 Security guard
 Delivery
 Cleaning
 Mowing
 Assistance Robots
 Mobility
 Services for elderly and
People with disabilities
 Autonomous Robot Control
 To control robots to perform tasks
autonomously a number of tasks have to be
addressed:
 Modeling of robot mechanisms
 Kinematics, Dynamics
 Robot sensor selection
 Active and passive proximity sensors
 Low-level control of actuators
 Closed-loop control
 Control architectures
 Traditional planning architectures
 Behavior-based control architectures
 Hybrid architectures
 Modeling the Robot Mechanism
 Forward kinematics describes how the robots
joint angle configurations translate to locations
in the world
2 (x, y, z)
1

(x, y, )

 Inverse kinematics computes the joint angle

configuration necessary to reach a particular
point in space.
 Jacobians calculate how the speed and
configuration of the actuators translate into
velocity of the robot
 Mobile Robot Odometry
 In mobile robots the same configuration in
terms of joint angles does not identify a unique
location
 To keep track of the robot it is necessary to
incrementally update the location (this process is
called odometry or dead reckoning)
t  t t
 x  x   vx 
     
 y   y    v y t
      
     
 Example: A differential drive robot
r (L  R ) r (L  R ) L R
v x  cos( ) , v y  sin( )
2 2 (x, y, )
r

  L  R
d

 Actuator Control
 To get a particular robot actuator to a particular
location it is important to apply the correct
amount of force or torque to it.
 Requires knowledge of the dynamics of the robot
 Mass, inertia, friction
 For a simplistic mobile robot: F = m a + B v
 Frequently actuators are treated as if they were
independent (i.e. as if moving one joint would not
affect any of the other joints).
 The most common control approach is PD-control
(proportional, differential control)
 For the simplistic mobile robot moving in the x direction:
F  K P  xdesired  xactual   K D vdesired  vactual 
 Robot Navigation
 Path planning addresses the task of computing
a trajectory for the robot such that it reaches
the desired goal without colliding with obstacles
 Optimal paths are hard to compute in particular for
robots that can not move in arbitrary directions (i.e.
nonholonomic robots)
 Shortest distance paths can be dangerous since they
always graze obstacles
 Paths for robot arms have to take into account the
entire robot (not only the endeffector)
Sensors
 Perceive the world
 Passive sensors capture signals generated by environment.
Background, lower power. E.G.: cameras.
 Active sensors probe the environment. Explicitly triggered,
more info, higher power consumption. E.G. sonar
 What are they sensing
 The environment: e.g. range finders, obstacle detection
 The robot’s location: e.g., gps, wireless stations
 Robot’s own internals: proprioceptive sensors. e.g.: shaft
decoders
 Stop and think about that one for a moment. Close your eyes - where’s
your hand? Move it - where is it now?
What use are sensors?
 Uses sensors for feedback
 Closed-loop robots use sensors in
conjunction with actuators to gain higher
accuracy – servo motors.
 Uses include mobile robotics, telepresence,
search and rescue, pick and place with
machine vision, anything involving human
interaction
 Sensor-Driven Robot Control
 To accurately achieve a task in an intelligent
environment, a robot has to be able to react
dynamically to changes ion its surrounding
 Robots need sensors to perceive the environment
 Most robots use a set of different sensors
 Different sensors serve different purposes
 Information from sensors has to be integrated
into the control of the robot
Some typical sensors
 Optical
 Laser / radar
 3D
 Color spectrum
 Pressure
 Temperature
 Chemical
 Motion & Accelerometer
 Acoustic
 Ultrasonic
 E-field Sensing
 Robot Sensors
 Internal sensors to measure the robot
configuration
 Encoders measure the rotation angle of a joint

 Limit switches detect when the joint has reached the

limit
 Robot Sensors
 Proximity sensors are used to measure the distance or
location of objects in the environment. This can then be
used to determine the location of the robot.
 Infrared sensors determine the distance to an object by
measuring the amount of infrared light the object reflects back
to the robot
 Ultrasonic sensors (sonars) measure the time that an ultrasonic
signal takes until it returns to the robot

 Laser range finders determine distance by

measuring either the time it takes for a laser
beam to be reflected back to the robot or by
measuring where the laser hits the object
 Robot Sensors
 Computer Vision provides robots with the
capability to passively observe the environment
 Stereo vision systems provide complete location
information using triangulation

 However, computer vision is very complex

 Correspondence problem makes stereo vision even more
difficult
Effectors
 Take some kind of action in the world
 Involve movement of robot or subcomponent
of robot
 Robot actions could include
 Pick and place: Move items between points
 Continuous path control: Move along a
programmable path
 Sensory: Employ sensors for feedback (e-field
sensing)
 Some kinds of Actuators
 Actuators
 pneumatic
 hydraulic
 electric solenoid
 Motors
 Analog (continuous)
 Stepping (discrete increments)
 Gears, belts, screws, levers
Mobility
 Legs
 Wheels
 Tracks
 Crawls
 Rolls
 How do robots move?

 Simple joints (2D)

 Translation/Prismatic
 sliding along one axis
 square cylinder in square tube
 Rotation.Revolute — rotating
about one axis
 Compound joints (3D)
 ball and socket = 3 revolute
joints
 round cylinder in tube = 1
prismatic, 1 revolute
 Degrees of Freedom (DOF)
 Degrees of freedom = Number of independent directions a
robot or its manipulator can move
 3 degrees of freedom: 2 translation, 1 rotation
 6 degrees of freedom: 3 translation, 3 rotation
 How many degrees of freedom does your knee have? Your
elbow?
 Effective DOF vs controllable DOF:
 Underwater explorer might have up or down, left or right, rolling. 3
controllable DOF.
 Position includes x,y,z coordinates, yaw, roll, pitch. (together the pose or
kinematic state). 6 effective DOF.
 Holonomic: effective DOF = controllable DOF.
 Control - the Brain
 Open loop, i.e., no feedback,
deterministic
 Instructions
 Rules
 Closed loop, i.e., feedback
 Learn
 Adapt
 What are some problems with
control of robot actions?
 Joint play, compounded through… joints.
 Accelerating masses produce vibration, elastic
deformations in links.
 Torques, stresses transmitted depending on end
actuator loads.
 Feedback loop creates instabilities.
 Delay between sensing and reaction.
 Firmware and software problems
 Especially with more intelligent approaches
 Robotic Perception
 Sensing isn’t enough: need to act on data sensed
 Hard because data are noisy; environment is
dynamic and partially observable.
 Must be mapped into an internal representation
 state estimation
 Good representations
 contain enough information for good decisions
 structured for efficient updating
 natural mapping between representation and real
world.
Some Perception Problems
 Localization: where is the robot, where are
other things in the environment
 landmarks
 range scans
 Mapping: no map given, robot must
determine both environment and position.
 Simultaneous localization and mapping
 Probabilistic approaches typical, but
cumbersome
Software Architectures
 Low-level, reactive control
 bottom-up, sensor results directly trigger
actions
 Model-based, deliberative planning
 top-down, actions are triggered based on
planning around a state model
 Low-Level, Reactive Control
 Augmented finite state machines (AFSMs)
 Sensed inputs and a clock determine next state
 Build bottom up, from individual motions
 Subsumption architecture synchronizes AFSMs, combines
values from separate AFSMs.
 Advantages: simple to develop, fast
 Disadvantages: Fragile for bad sensor data, don’t support
integration of complex data over time.
 Typically used for simple tasks, like following a wall or
moving a leg.
 Model-Based Deliberative
Planning
 Belief State model
 Current State, Goal State
 Any of planning techniques
 Typically use probabilistic methods
 Advantages: can handle uncertain measurements and
complex integrations, can be responsive to change or
problems.
 Disadvantages: slow; current algorithms can take minutes.
Developing models for the number of actions involved in
driving a complex robot too cumbersome.
 Typically used for high-level actions such as whether to
move and in which direction.
 Deliberative
Robot Control Architectures
 In a deliberative control architecture the robot
first plans a solution for the task by reasoning
about the outcome of its actions and then
executes it

 Control process goes through a sequence of sencing,

model update, and planning steps
 Deliberative
Control Architectures
 Advantages
 Reasons about contingencies
 Computes solutions to the given task
 Goal-directed strategies
 Problems
 Solutions tend to be fragile in the presence of
uncertainty
 Requires frequent replanning
 Reacts relatively slowly to changes and unexpected
occurrences
 Behavior-Based
Robot Control Architectures
 In a behavior-based control architecture the
robot’s actions are determined by a set of
parallel, reactive behaviors which map sensory
input and state to actions.
 Behavior-Based
Robot Control Architectures
 Reactive, behavior-based control combines
relatively simple behaviors, each of which
achieves a particular subtask, to achieve the
overall task.
 Robot can react fast to changes
 System does not depend on complete knowledge of
the environment
 Emergent behavior (resulting from combining initial
behaviors) can make it difficult to predict exact
behavior
 Difficult to assure that the overall task is achieved
 Complex Behavior from Simple
Elements: Braitenberg Vehicles
 Complex behavior can be achieved using very
simple control mechanisms
 Braitenberg vehicles: differential drive mobile robots
with two light sensors

+ + + + - - - -

“Coward” “Aggressive” “Love” “Explore”

 Complex external behavior does not necessarily require a

complex reasoning mechanism
 Behavior-Based Architectures:
Subsumption Example
 Subsumption architecture is one of the earliest
behavior-based architectures
 Behaviors are arranged in a strict priority order
where higher priority behaviors subsume lower
priority ones as long as they are not inhibited.
 Reactive, Behavior-Based
Control Architectures
 Advantages
 Reacts fast to changes
 Does not rely on accurate models
 “The world is its own best model”
 No need for replanning
 Problems
 Difficult to anticipate what effect combinations of
behaviors will have
 Difficult to construct strategies that will achieve
complex, novel tasks
 Requires redesign of control system for new tasks
 Hybrid Architectures
 Usually, actually doing anything requires both
reactive and deliberative processing.
 Typical architecture is three-layer:
 Reactive Layer: low-level control, tight senso-action
loop, decision cycle of milliseconds
 Deliberative layer: global solutions to complex tasks,
model-based planning, decision cycle of minutes
 Executive layer: glue. Accepts directions from
deliberative layer, sequences actions for reactive layer,
decision cycle of a second
 Hybrid Control Architectures
 Hybrid architectures combine
reactive control with abstract
task planning
 Abstract task planning layer
 Deliberative decisions
 Plans goal directed policies
 Reactive behavior layer
 Provides reactive actions
 Handles sensors and actuators
Hybrid Control Policies

Task Plan:

Behavioral
Strategy:
Example Task:
Changing a Light Bulb

https://www.youtube.com/watch?v=xMrk0efv6SE
 Hybrid Control Architectures
 Advantages
 Permits goal-based strategies
 Ensures fast reactions to unexpected changes
 Reduces complexity of planning
 Problems
 Choice of behaviors limits range of possible tasks
 Behavior interactions have to be well modeled to be
able to form plans
 Robot Configurations
Some of the commonly used configurations in Robotics are

 Cartesian/Rectangular Gantry(3P) : These Robots are made of

3 Linear joints that orient the end effector, which are usually
followed by additional revolute joints.
Cartesian Robot - Work
Envelope
Robot Configurations (cont’d)
 Cylindrical (R2P): Cylindrical coordinate Robots have 2
prismatic joints and one revolute joint.
Cylindrical Robot - Work
Envelope
Robot Configurations (cont’d)
 Spherical joint (2RP): They follow a spherical coordinate
system, which has one
Spherical Robot - Work
Envelope
Robot Configurations (cont’d)
 Articulated/anthropomorphic(3R) :An articulated robot’s
joints are all revolute, similar to a human’s arm.
Robot Configurations (cont’d)
 Selective Compliance Assembly Robot Arm (SCARA)
(2R1P): They have two revolute joints that are parallel and
allow the Robot to move in a horizontal plane, plus an additional
prismatic joint that moves vertically
Robot Configurations
Reference Frames
 World Reference Frame which is a universal coordinate frame,
as defined by the x-y-z axes. In this case the joints of the robot
move simultaneously so as to create motions along the three
major axes.

 Joint Reference Frame which is used to specify movements of

each individual joint of the Robot. In this case each joint may be
accessed individually and thus only one joint moves at a time.

 Tool Reference Frame which specifies the movements of the

Robots hand relative to the frame attached to the hand. The
x’,y’and z’ axes attached to the hand define the motions of the
hand relative to this local frame. All joints of the Robot move
simultaneously to create coordinated motions about the Tool
frame.
Robot Reference Frames
Work Envelope concept
 Depending on the configuration and size of
the links and wrist joints, robots can reach a
collection of points called a Workspace.

 Alternately Workspace may be found

empirically, by moving each joint through its
range of motions and combining all space it
can reach and subtracting what space it
cannot reach
Pure Spherical Jointed Arm - Work
envelope
2) Parallelogram Jointed
 Exercise
Readiness Assessment Test
AS A INDIVIDUAL, prepare a
detailed response for the following
Readiness Assessment test
What type of Robot Configuration does
the ABB 140 Robot or KUKA IR300
have?
Can you find out its Work
Space?
WRIST
 typically has 3 degrees of freedom
 Roll involves rotating the wrist about the
arm axis
 Pitch up-down rotation of the wrist
 Yaw left-right rotation of the wrist
 End effector is mounted on the wrist
WRIST MOTIONS
End-effector: The tool, gripper, or other device mounted
at the end of a manipulator, for accomplishing useful
tasks.

75
The Hand of a Robot: End-
Effector
The end-effector (commonly known as
robot hand) mounted on the wrist
enables the robot to perform specified
tasks. Various types of end-effectors are
designed for the same robot to make it
more flexible and versatile. End-
effectors are categorized into two major
types: grippers and tools.

76
The Hand of a Robot: End-
Effector
Grippers are generally used to grasp
and hold an object and place it at a
desired location.
 mechanical grippers
 vacuum or suction cups
 magnetic grippers
 adhesive grippers
 hooks, scoops, and so forth
77
The Hand of a Robot: End-
Effector
At times, a robot is required to
manipulate a tool to perform an
operation on a workpiece. In such
applications the end-effector is a tool
itself
 spot-welding tools
 arc-welding tools
 spray-painting nozzles
 rotating spindles for drilling
 rotating spindles for grinding 78
Power Sources for Robots
 An important element of a robot is the
drive system. The drive system supplies
the power, which enable the robot to
move.
 The dynamic performance of a robot
mainly depends on the type of power
source.

79
There are basically three types of
power sources for robots:

1. Hydraulic drive
 Provide fast movements

 Preferred for moving heavy parts

 Preferred to be used in explosive

environments
 Occupy large space area

 There is a danger of oil leak to the shop

floor
80
2. Electric drive
 Slower movement compare to the
hydraulic robots
 Good for small and medium size robots

 Better positioning accuracy and

repeatability
 stepper motor drive: open loop control

 DC motor drive: closed loop control

 Cleaner environment

 The most used type of drive in industry

81
3. Pneumatic drive
 Preferred for smaller robots

 Less expensive than electric or hydraulic

robots
 Suitable for relatively less degrees of
freedom design
 Suitable for simple pick and place
application
 Relatively cheaper

82
 Robotics Terminology

Position: The translational (straight-line)

location of something.

Orientation: The rotational (angle) location

of something. A robot’s orientation is
measured by roll, pitch, and yaw angles.

Link: A rigid piece of material connecting

joints in a robot.

Joint: The device which allows relative A robot joint

motion between two links in a robot.
83
 Robotics Terminology
Speed
•The amount of distance per unit time at which the
robot can move, usually specified in inches per
second or meters per second.
•The speed is usually specified at a specific load or
assuming that the robot is carrying a fixed weight.
•Actual speed may vary depending upon the weight
carried by the robot.

Load Bearing Capacity

•The maximum weight-carrying capacity of the robot.
•Robots that carry large weights, but must still be
precise are expensive.

84
 Robotics Terminology
Accuracy
•The ability of a robot to go to the specified position
without making a mistake.
•It is impossible to position a machine exactly.
•Accuracy is therefore defined as the ability of the
robot to position itself to the desired location with the
minimal error (usually 25 mm).

Repeatability
•The ability of a robot to repeatedly position itself
when asked to perform a task multiple times.
•Accuracy is an absolute concept, repeatability is
relative.
•A robot that is repeatable may not be very accurate,
visa versa.
85
Robot Movement and
Precision
Speed of response and stability are
two important characteristics of robot
movement.
 Speed defines how quickly the robot
arm moves from one point to another.
 Stability refers to robot motion with
the least amount of oscillation. A good
robot is one that is fast enough but at
the same time has good stability.
86
 Robot Movement and
Precision
Speed and stability are often conflicting
goals. However, a good controlling system
can be designed for the robot to facilitate
a good trade-off between the two
parameters.

87
The precision of robot movement is
defined by three basic features:

1. Spatial resolution:
The spatial resolution of a robot is the
smallest increment of movement into
which the robot can divide its work
volume.
It depends on the system’s control
resolution and the robot's mechanical
inaccuracies.
88
2. Accuracy: Accuracy can be defined as the
ability of a robot to position its wrist end at a
desired target point within its reach. In terms
of control resolution, the accuracy can be
defined as one-half of the control resolution.
This definition of accuracy applies in the worst
case when the target point is between two
control points.The reason is that displacements
smaller than one basic control resolution unit
(BCRU) can be neither programmed nor
measured and, on average, they account for
one-half BCRU.
89
The accuracy of a robot is affected by
many factors. For example, when the
arm is fully stretched out, the
mechanical inaccuracies tend to be
larger because the loads tend to cause
deflection.

90
3. Repeatability: It is the ability of the robot
to position the end effector to the
previously positioned location.
A
C + +
+
+ ++
+ + + +
++ B + +
+
+ + + ++

x xx x x
x xx x
xxx

xx
xx
xx x x x x

x x

91
CONTROL METHODS
 Non Servo Control
 implemented by setting limits or
mechanical stops for each joint and
sequencing the actuation of each joint to
accomplish the cycle
 end point robot, limited sequence robot,
bang-bang robot
 No control over the motion at the
intermediate points, only end points are
known 92
 Programming accomplished by
 setting desired sequence of moves
 adjusting end stops for each axis accordingly
 the sequence of moves is controlled by a
“squencer”, which uses feedback received from
the end stops to index to next step in the program
 Low cost and easy to maintain, reliable
 relatively high speed
 repeatability of up to 0.01 inch
 limited flexibility
 typically hydraulic, pneumatic drives
 Servo Control
 Point to point Control
 Continuous Path Control
 Closed Loop control used to monitor
position, velocity (other variables) of
each joint
Point-to-Point Control
 Only the end points are programmed,
the path used to connect the end points
are computed by the controller
 user can control velocity, and may
permit linear or piece wise linear motion
 Feedback control is used during motion
to ascertain that individual joints have
achieved desired location
 Often used hydraulic drives, recent
trend towards servomotors
 loads up to 500lb and large reach
 Applications
 pick and place type operations
 palletizing
 machine loading
Continuous Path Controlled
 in addition to the control over the
endpoints, the path taken by the end
effector can be controlled
 Path is controlled by manipulating the
joints throughout the entire motion, via
closed loop control
 Applications:
 spray painting, polishing, grinding, arc
welding
ROBOT PROGRAMMING
 Typically performed using one of the
following
 On line
 teach pendant
 lead through programming
 Off line
 robot programming languages
 task level programming
Use of Teach Pendant
 hand held device with switches used to
control the robot motions
 End points are recorded in controller
memory
 sequentially played back to execute
robot actions
 trajectory determined by robot
controller
 suited for point to point control
applications
 Easy to use, no special programming
skills required
 Useful when programming robots for
wide range of repetitive tasks for long
production runs
 RAPID
Lead Through Programming
 lead the robot physically through the
required sequence of motions
 trajectory and endpoints are recorded,
using a sampling routine which records
points at 60-80 times a second
 when played back results in a smooth
continuous motion
 large memory requirements
Programming Languages
 Motivation
 need to interface robot control system to
external sensors, to provide “real time”
changes based on sensory equipment
 computing based on geometry of
environment
 ability to interface with CAD/CAM systems
 meaningful task descriptions
 off-line programming capability
 Large number of robot languages
available
 AML, VAL, AL, RAIL, RobotStudio, etc.
(200+)
 Each robot manufacturer has their own
robot programming language
 No standards exist
 Portability of programs virtually non-
existent
 How do you measures of
performance of robot?
 Speed and acceleration
 Resolution
 Working volume
 Accuracy
 Cost
 Plus all the kinds of evaluation functions
we have talked about for any AI system.
 Measures of Performance
 Speed and acceleration
 Faster speed often reduces resolution or increases cost
 Varies depending on position, load.
 Speed can be limited by the task the robot performs (welding,
cutting)
 Resolution
 Often a speed tradeoff
 The smallest movement the robot can make
 Working volume
 The space within which the robot operates.
 Larger volume costs more but can increase the capabilities of a
robot
 Tomorrow’s problems
 Mechanisms
 Morphology: What should robots look like?
 Novel actuators/sensors
 Estimation and Learning
 Reinforcement Learning
 Graphical Models
 Learning by Demonstration
 Manipulation (grasping)
 What does the far side of an object look like? How heavy
is it? How hard should it be gripped? How can it rotate?
Regrasping?
And more...
 Medical robotics
 Autonomous surgery
 Eldercare
 Biological Robots
 Biomimetic robots
 Neurobotics
 Navigation
 Collision avoidance
 SLAM/Exploration
 Self-X Robots
 Self-feeding
 Literally
 Electrically
 Self-replicating
 Self-repairing
 Self-assembly
 Self-organization
 Self-reconfiguration
 Traditional Human-Robot
Interface: Teleoperation
Remote Teleoperation: Direct
operation of the robot by the
user
 User uses a 3-D joystick or an
exoskeleton to drive the robot
 Simple to install
 Removes user from dangerous areas
 Problems:
 Requires insight into the mechanism
 Can be exhaustive
 Easily leads to operation errors
Human-Robot Interaction
 Social robots
 In care contexts
 In home contexts
 In industrial contexts
 Comprehension
 Natural language
 Grounded knowledge acquisition
 Roomba: “Uh-oh”
 Motivations
 Robots are getting smaller, cheaper, and more ubiquitous
 Humans need to interact with and instruct them, naturally
 Language, gesture, demonstration, …
 Key requirements:
 Language understanding learned from data
 Follow instructions in a previously unseen world
 Learn to parse natural language into robot-usable commands
Human-Robot Interaction
 Social robots
 Safety/security
 Ubiquitous Robotics
 Small, special-purpose robots
 More Human-Robot Interaction
 How do humans handle it?
 Assumptions about retention and understanding
 Anthropomorphization
 How do robots make it easier?
 Apologize vs. back off
 Convey intent
 Cultural context (implicit vs. explicit
communication)
 Human-Robot Interaction in
Intelligent Environments
 Personal service robot
 Controlled and used by untrained users
 Intuitive, easy to use interface
 Interface has to “filter” user input
 Eliminate dangerous instructions
 Find closest possible action
 Receive only intermittent commands
 Robot requires autonomous capabilities
 User commands can be at various levels of complexity
 Control system merges instructions and autonomous
operation
 Interact with a variety of humans
 Humans have to feel “comfortable” around robots
 Robots have to communicate intentions in a natural way
Example: Minerva the Tour
Guide Robot (CMU/Bonn)

© CMU Robotics Institute

http://www.cs.cmu.edu/~thrun/movies/minerva.mpg
 Intuitive Robot Interfaces:
Command Input
 Graphical programming interfaces
 Users construct policies form elemental blocks
 Problems:
 Requires substantial understanding of the robot
 Deictic (pointing) interfaces
 Humans point at desired targets in the world or
 Target specification on a computer screen
 Problems:
 How to interpret human gestures ?
 Voice recognition
 Humans instruct the robot verbally
 Problems:
 Speech recognition is very difficult
 Robot actions corresponding to words has to be defined
 Intuitive Robot Interfaces:
Robot-Human Interaction
 He robot has to be able to communicate its
intentions to the human
 Output has to be easy to understand by humans
 Robot has to be able to encode its intention
 Interface has to keep human’s attention without
annoying her
 Robot communication devices:
 Easy to understand computer screens
 Speech synthesis
 Robot “gestures”
Example: The Nursebot Project

© CMU Robotics Institute

http://www/cs/cmu.edu/~thrun/movies/pearl_assist.mpg
 Human-Robot Interfaces
 Existing technologies
 Simple voice recognition and speech synthesis
 Gesture recognition systems
 On-screen, text-based interaction
 Research challenges
 How to convey robot intentions ?
 How to infer user intent from visual observation (how
can a robot imitate a human) ?
 How to keep the attention of a human on the robot ?
 How to integrate human input with autonomous
operation ?
 Integration of Commands and
Autonomous Operation
 Adjustable Autonomy
 The robot can operate at
varying levels of autonomy
 Operational modes:
 Autonomous operation
 User operation / teleoperation
 Behavioral programming
 Following user instructions
 Imitation
 Types of user commands:
 Continuous, low-level
instructions (teleoperation)
 Goal specifications
Task demonstrations
Example System

"Social" Robot Interactions
 To make robots acceptable to average users
they should appear and behave “natural”
 "Attentional" Robots
 Robot focuses on the user or the task
 Attention forms the first step to imitation
 "Emotional" Robots
 Robot exhibits “emotional” responses
 Robot follows human social norms for behavior
 Better acceptance by the user (users are more forgiving)
 Human-machine interaction appears more “natural”
 Robot can influence how the human reacts
"Social" Robot Example: Kismet

© MIT AI Lab
http://www.ai.mit.edu/projects/cog/Video/kismet/kismet_face_30fps.mpg
"Social" Robot Interactions
 Advantages:
 Robots that look human and that show “emotions”
can make interactions more “natural”
 Humans tend to focus more attention on people than on
objects
 Humans tend to be more forgiving when a mistake is
made if it looks “human”
 Robots showing “emotions” can modify the way in
which humans interact with them
 Problems:
 How can robots determine the right emotion ?
 How can “emotions” be expressed by a robot ?
 Human-Robot Interfaces for
Intelligent Environments
 Robot Interfaces have to be easy to use
 Robots have to be controllable by untrained users
 Robots have to be able to interact not only with their
owner but also with other people
 Robot interfaces have to be usable at the
human’s discretion
 Human-robot interaction occurs on an irregular basis
 Frequently the robot has to operate autonomously
 Whenever user input is provided the robot has to react to it
 Interfaces have to be designed human-centric
 The role of the robot is it to make the human’s life
easier and more comfortable (it is not just a tech toy)
 Adaptation and Learning for
Robots in Smart Homes
 Intelligent Environments are non-stationary and
change frequently, requiring robots to adapt
 Adaptation to changes in the environment
 Learning to address changes in inhabitant preferences
 Robots in intelligent environments can frequently
not be pre-programmed
 The environment is unknown
 The list of tasks that the robot should perform might
not be known beforehand
 No proliferation of robots in the home
 Different users have different preferences
 Adaptation and Learning
In Autonomous Robots
 Learning to interpret sensor information
 Recognizing objects in the environment is difficult
 Sensors provide prohibitively large amounts of data
 Programming of all required objects is generally not
possible
 Learning new strategies and tasks
 New tasks have to be learned on-line in the home
 Different inhabitants require new strategies even for
existing tasks
 Adaptation of existing control policies
 User preferences can change dynamically
 Changes in the environment have to be reflected
Learning Approaches for
Robot Systems
 Supervised learning by teaching
 Robots can learn from direct feedback from the
user that indicates the correct strategy
 The robot learns the exact strategy provided by the user
 Learning from demonstration (Imitation)
 Robots learn by observing a human or a robot
perform the required task
 The robot has to be able to “understand” what it observes
and map it onto its own capabilities
 Learning by exploration
 Robots can learn autonomously by trying different
actions and observing their results
 The robot learns a strategy that optimizes reward
Learning Sensory Patterns
 Learning to Identify Objects
 How can a particular object be
recognized ?
 Programming recognition strategies is
difficult because we do not fully
understand how we perform recognition

:
 Learning techniques permit the robot
system to form its own recognition

:
strategy
 Supervised learning can be used by

:
giving the robot a set of pictures and
the corresponding classification
Chair
 Neural networks
 Decision trees
Learning Task Strategies by
Experimentation
 Autonomous robots have to be able to learn
new tasks even without input from the user
 Learning to perform a task in order to optimize the
reward the robot obtains (Reinforcement Learning)
 Reward has to be provided either by the user or the
environment
 Intermittent user feedback
 Generic rewards indicating unsafe or inconvenient actions or
occurrences
 The robot has to explore its actions to determine what
their effects are
 Actions change the state of the environment
 Actions achieve different amounts of reward
 During learning the robot has to maintain a level of safety
 Example: Reinforcement
Learning in a Hybrid Architecture
 Policy Acquisition Layer
 Learning tasks without
supervision
 Abstract Plan Layer
 Learning a system model
 Basic state space compression

 Reactive Behavior Layer

 Initial competence and
reactivity
 Scaling Up: Learning Complex
Tasks from Simpler Tasks
 Complex tasks are hard to learn since they
involve long sequences of actions that have to
be correct in order for reward to be obtained
 Complex tasks can be learned as shorter
sequences of simpler tasks
 Control strategies that are expressed in terms of
subgoals are more compact and simpler
 Fewer conditions have to be considered if simpler
tasks are already solved
 New tasks can be learned faster
 Hierarchical Reinforcement Learning
 Learning with abstract actions
 Acquisition of abstract task knowledge
 The Future of Robotics.
 Robots that can learn.
 Robots that interact smoothly with people.
 Robots with artificial intelligence.
 Robots that make other robots.
 Swarms.
 Conclusions
 Robots are an important component in Intelligent
Environments
 Automate devices
 Provide physical services
 Robot Systems in these environments need particular
capabilities
 Autonomous control systems
 Simple and natural human-robot interface
 Adaptive and learning capabilities
 Robots have to maintain safety during operation
 While a number of techniques to address these
requirements exist, no functional, satisfactory solutions
have yet been developed
 Only very simple robots for single tasks in intelligent
environments exist
 Some good robotics videos
 Swimming fish:
 http://www.aa.washington.edu/research/ndcl/videos/ThreeFishAndShark.m4v
 http://www.newscientist.com/article/dn14101-shoal-of-robot-fish-casts-a-wider-
data-net.html
 Robot games:
 http://robogames.net/videos.php
 https://www.grasp.upenn.edu
 Social robots:
 http://www.ai.mit.edu/projects/humanoid-robotics-group/kismet/kismet.html
 Swarms
 http://www.eecs.harvard.edu/ssr/projects/cons/termes.html
 http://www.swarmanoid.org/
 https://www.youtube.com/watch?v=YQIMGV5vtd4
 Miscellaneous Robots:
 Bigdog: http://www.aaaivideos.org/2008/big_dog/
 Laundry: http://www.eecs.berkeley.edu/~pabbeel/
 Will robots take over the
world?
 Which decisions can the machine make without human
supervision?
 May machine-intelligent systems make mistakes (at the
same level as humans)?
 May intelligent systems gamble when uncertain (as
humans do)?
 Can (or should) intelligent systems exhibit personality?
 Can (or should) intelligent systems express emotion?
 How much information should the machine display to the
human operator?