Modeling of ADLs in
its Environment for
Cognitive Assistance
Jérémy Bauchet and André Mayers
Introduction

Cognitive assistance, in smart homes,
aims at supporting occupants for the
completion of their activities of daily living
(ADLs)
Introduction (2)

Implies for the system a prior knowledge
about the occupant
 its
activities
 its environment

This knowledge is necessary for :
 activity
recognition, as a prior step of cognitive
assistance in smart homes
 finally, for cognitive assistance
Plan


Introduction
A model for the description of ADLs






a hierarchical approach
the environment of completion
Taking into account the specific behavior of the occupant
Implementation of the models
Results and perspectives concerning activity recognition
and cognitive assistance
Conclusion
A hierarchical model for ADLs
description

Two type of nodes : tasks and methods
a
task : a goal
 a method : a way to realize the task
→ a set of subtasks
→ and rules of integration of subtasks :
partial or total sequence
 repetition or necessity constraint

A hierarchical model for ADLs
description (2)
Roots are abstract tasks (ADLs, IADLs)
 Leaves are methods of terminal tasks = an
atomic way to realise a concrete goal


Tasks can be common to several methods
→ if common nodes are duplicate, this model is
a tree
Model of activity
A model of ADLs
in its environment
Environment of activity completion
 Includes all actors of activity completion

 daily
living objects
 furniture
 the occupant, as the actor of his own task
completion
→ e.g. : her/his current position
Description of the environment
of completion

Static description :
 Actors : fridge
 Events concerning
actors
fridge : door opened, door closed

Dynamic description :
Assertions, giving current value of several pieces of
information concerning actors


<fridge, door, opened>
<occupant, position, kitchen>
Links between activities and
the environment

Events concerning actors in the environment
are associated with terminal methods



events are a consequence of the concrete actions
of the occupant
events can be observed via distributed sensors
occurrence of events are used for activity
recognition
Links between activities and
the environment (2)

Tasks and method are considered as
operators of a planning domain
 they
have preconditions and effects
 both concern the environment
Taking into account the specific
behavior of the occupant

The activity model is a support for the
generic description of ADLs and IADLs
→ We need an occupant model to
describe his/her specific comportment
An episodic memory for the
occupant model

Allows to precise how one occupant
usually completes an activity
 the
method used for a given task
 the time slot of completion
 the location
 the sequence of subtasks
Implementation

XML
 library of tasks and methods (activity
 description of the environment
 episodic memory persistence

SVG
 graphical

model)
representation of the environment
Java
 XML parsing
 internal representation
 SVG
management
of the models and treatments
Results and perspectives :
Concerning activity recognition
Goal : to compute the probability of
completion of (I)ADLs given inputs
 Inputs are :

 description
of ADLs
 events
 current
time
 knowledge about the occupant habits of life,
given by the episodic memory
Activity recognition
Results and perspectives (3) :
Concerning cognitive assistance
Description of activities, for step by step or
global assistance
 Preconditions → what has to be done
before, where the activity can take place
 Rules of integration for subtasks → how to
complete correctly the activity
 Episodic memory → anticipation process

Conclusion