Robotics

                                                            Robotics

                                                                                  Pic1

Introduction
  •Robot Institute of America defines robot as a reprogrammable, multifunction manipulator
  designed to move material, parts, tools or specific devices through variable programmed motions for
  the performance of a variety of tasks.
  •Russell and Norvig: an active, artificial agent whose environment is the physical world.
  •Robots differ from Softbots whose environment consists of computer systems, databases and
  networks.

The Physical World
  •The physical world is very demanding, it is:
  •inaccessible - sensors are imperfect, only stimuli that are near the agent can be perceived.
  •nondeterministic - a robot needs to deal with uncertainty
  •nonepisodic - effects of an action change over time
  •dynamic - robot needs to decide when to think and when to act immediately
  •continuous - states and actions are drawn from a continuum of physical configurations and motions

 

What are robots good for?
•Gofer robots
PIC3

Bell & Howell Mailmobile
These mailmobile robots  respond to requests from a computer terminal and carry documents or supplies to a destination somewhere else in the building. The robot negotiates hallways and elevators, and avoids collision with other obstacles such as humans and furniture.

What are robots good for?
•Gofer robots
PIC4
Carnegie Mellon’s Nomad
Nomad is a robot recently deployed in Antartica. It is designed to find meteorites in a remote area called Elephant Moriane. As Nomad explores an area, it must choose which rocks to examine and in what order. The robot has to decide whether it should drive, use its arm or employ both capabilities to reach its goal.

What are robots good for?
•Hazardous environments
PIC5
Lunokhod Moon Robot
During the cleanup of the Chernobyl disaster, several Lunokhod lunar explorer robots were converted to remote-controlled cleaning vehicles. In Japan and France, robots are used for routine maintenance of nuclear plants. In such cases a human operator is often available to guide the robot, but it also needs autononmy to recognize and respond to hazards of its own and other’s well-being.

 

What are robots good for?
•Hazardous environments
Dante II Frame Walking Robot

What are robots good for?
•Telepresence and virtual reality
The Wheelbarrow, a bomb disposal robot

What are robots good for?
•Telepresence and virtual reality
Advanced Tethered Vehicle (ATV)

What are robots good for?
•Telepresence and virtual reality
Advanced Robot and Telemanipulator System for Minimal Invasive Surgery
(ARTEMIS)

What are robots good for?
•Augmentation of human abilities
Sigourney Weaver in the movie Aliens

What are robots good for?
•Augmentation of human abilities
General Electric’s Walking Truck

What are robots made of?
•Effectors: Tools for Action
•Locomotion
•Manipulation
•Sensors: Tools for perception
•Proprioception
•Force Sensing
•Tactile Sensing
•Sonar
•Camera Data

What are robots made of?
•Effectors: Locomotion
Carnegie Mellon’s Ambler

What are robots made of?
•Effectors: Locomotion
MIT’s 3D Hopper

What are robots made of?
•Effectors: Manipulation
Degrees of Freedom

What are robots made of?
•Sensors: Proprioception
MIT’s Spring Flamingo

What are robots made of?
•Sensors: Force Sensing
MIT’s Phantom

What are robots made of?
•Sensors: Tactile Sensing
MIT’s Planar Grasper

What are robots made of?
•Sensors: Sonar
ActivMedia’s Peoplebot

What are robots made of?
•Sensors: Light Sensors
Grey Walter’s Tortoise

What are robots made of?
•Sensors: Camera Data
The Johns Hopkins Beast

What are robots made of?
•Sensors: Camera Data
MIT’s Fast Eye Gimbals

Architectures
The architecture of a robot defines how the job of
generating actions from percepts is organized. It is
basically the control mechanism of the robot.
•Classical Architecture
•Situated Automata

Architectures
•Classical Architecture
A robot with classical architecture is given a
number of low-level actions (LLAs). It then uses
these LLAs to reason about the effects of
performing a sequence of these LLAs.
The problem with this is that due to things like
wheel slippage and measurement errors any
lengthy sequence of actions is prone to fail.

Architectures
•Classical Architecture
SRI’s Shakey

Architectures
•Situated Automata
The process of deliberating is often too expensive
to generate real-time behavior. Situated automata
do not explicitly reason, they operate by reflex.
A situated automata has two parts. The first
collects sensor inputs and updates the state
register accordingly, the second looks at the state
register and calculates output (actions). Thus a
situated automata does not plan, it just does
whatever it knows to do given the state it is in.

Architectures
•Situated Automata
SRI’s Flakey

Configuration Spaces
Configuration Space is the path where robot
can move from one position to another.
•Generalized configuration space
•Recognizable sets

Generalized configuration space
Configuration Spaces
• Generalized configuration space includes other
objects as part of the configuration, which could be
movable, variable in shapes (i.e. scissors or staples), or
deformable (i.e.string or paper).

Recognizable Sets
Configuration Spaces
• Includes envelope of possible configurations

Navigation and Motion Planning
• Cell decomposition
• Skeletonization
•Fine-motion (Bounder-error) planning
• Landmark-based navigation
• Online algorithms

Navigation and Motion Planning
•Cell decomposition
• Breaks continuous space into a finite number of
discrete search problems
Bell & Howell Mailmobile

Navigation and Motion Planning
• Skeletonization methods
• Computes a one-directional “skeleton” (subset) of
the configuration space, yielding an equivalent graph
search problem

Navigation and Motion Planning
• Fine-motion (Bounded-error) Planning
• This methods assume bounds on sensor and actuator
uncertainty, and in some cases can compute plans that are
guaranteed to succeed even in the face of severe actuator
• partial knowledge of the environment is known to the system
• most of the planning is done offline
• used for planning small, precise motions of assembly

Navigation and Motion Planning
• Landmark-based navigation
• This method assumes that there exists some regions in
which the robot location can be pinpointed using
landmarks, whereas outside those regions it may have only
orientation information
• This method is both sound and complete
• The plan have at most n steps if there are n landmarks

Navigation and Motion Planning
• Online algorithm
• The robot makes decision at run time (no need for offline
planning
•This method assumes that the environment is completely
unknown
•The robot cannot see anything. It can only sense a boundary
• The robot is equipped with a position sensor and knows the
location of its goal.

The End