Robotics In which agents are endowed with physical effectors with which to do mischief.

Robotics

In which agents are endowed with physical effectors with which to do mischief.

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?•Manufacturing and materials handling

What are robots good for?•Gofer robots

Bell & Howell Mailmobile

What are robots good for?•Gofer robots

Carnegie Mellon’s Nomad

What are robots good for?•Hazardous environments

Lunokhod Moon Robot

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

ArchitecturesThe 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 SpacesConfiguration 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