An Integral System for Assisted

spectacularscarecrowAI and Robotics

Nov 17, 2013 (3 years and 6 months ago)

54 views

An Integral System for Assisted
Mobility

Manuel Mazo & the Research group
of the SIAMO Project

Yuchi Ming, IC LAB

Contents


Overview.


System Architecture


HMI(Human
-
Machine Interface).


Environment Perception.


Navigation and Control.











Summary

Overview


The SIAMO(Spanish acronym for Integral
System for Assisted Mobility) project began
at the end of 1996.


Motivation:

Design autonomous
wheelchairs as an assistance device for the
disabled or the elderly.


Goal:

Safety, Comfort and Modularity.

System

Architecture

Human
-
Machine Interface


Breath expulsion


Head Movements.


Electro
-
oculography(EOG).


User
-
dependent voice recognition.


Joystick.


Display & voice synthesizer.

Guidance by Breath Expulsion


A

differential

air
-
flow

sensor

with

a

linear

output

is

used,

so

it

is

possible

to

detect

both

strength

and

direction

of

breathing
.


With

an

“easy
-
to

use”

breath

code

it

is

possible

to

obtain

the

references

of

linear

and

angular

velocities

and

to

stop

the

chair

in

case

of

trouble
.


This

driving

aid

allows

commanding

the

chair

in

broad

corridors

and

halls

as

well

as

crossing

through

doors

of

1
.
5
m

wide

without

any

other

assistance

or

sensory

system
.


Guidance Head Movements.

Guidance by Electro
-
Oculography



This method allows one to generate simple coder for
controlling the wheelchair using eye placement.



Several biopotential skin electrodes are placed on the
user’s face to detect eye movement.


Guidance by Voice Commands


Instead

of

a

computer,

a

commercial

isolated

word

recognition

chip

has

been

used
.


A

set

of

nine

voice

commands

are

developed
.

Each

command

has

an

associated

driving

function
:

Stop,

Forward,

Back,

Left,

Right,

Plus,

Minus,

Password

and

Track
.


“Plus”

and

“Minus”

means

increase

or

decrease

the

speed
.


“Password”

allows

switch

between

the

voice

control

and

normal

conversation
.


“Track”

allows

switch

between

voice

control

and

Autonomous

control
.

Environment Perception


Ultrasonic sensors.


Infrared sensors.


Active laser sensors.


Passive vision system based on artificial
landmarks.

Ultrasonic Sensors.


Infrared Sensors


The role of the infrared sensors is to detect floor unevenness.


The sensor makes distance reading up to a point marked on
the floor 2m in front of the wheelchair

Active Laser Sensors


This

sensor

module

obtains

3
-
D

positions

of

obstacles
.


A

laser

emitter

projects

a

plane
-
form

bean

over

the

scene
.

From

the

image

captured

by

the

CCD

camera,

the

points

belonging

to

that

bean

are

segmented
.


Expensive
.

Passive Vision System


The

landmarks

are

simple

A
4

paper

sheet

with

a

black
-
white

pattern

printed

on

them
.


Positioning

is

performed

by

measuring

the

landmark

distortion

in

the

captured

image
.


Landmarks

must

be

located

at

heights

over

1
.
5
m(height

of

the

camera,

and

each

entrance

door

must

be

signaled

with

one

landmark

right

over

it
.

Navigation and Control


Automatic Navigation strategy is incorporated in the wheelchair so
that the user only need to indicate the destination point.


Automatic Navigation need a full mapping of of the environment.


One contactless node, equipped with a wireless
drive, can be placed on the main doors and loaded
with a full description of room identification,
landmark location, and routing inside the building.


The wheelchair need not to store all the maps.

Summary


The

system

has

the

characteristic

of

being

modular,

which

allows

it

to

be

easily

adapted

to

each

user’s

specific

requirements,

depending

on

the

type

and

degree

of

disability
.