=Paper=
{{Paper
|id=Vol-2142/paper9
|storemode=property
|title=Autonomous adaptation of software agents in the support of human activities
|pdfUrl=https://ceur-ws.org/Vol-2142/paper9.pdf
|volume=Vol-2142
|authors=Esteban Guerrero,Ming-Hsin Lu,Hsiu-Ping Yueh,Helena Lindgren
|dblpUrl=https://dblp.org/rec/conf/ijcai/GuerreroLYL18
}}
==Autonomous adaptation of software agents in the support of human activities==
https://ceur-ws.org/Vol-2142/paper9.pdf
Autonomous adaptation of software agents in
the support of human activities
Esteban Guerrero1 , Ming-Hsin Lu2 , Hsiu-Ping Yueh2 , and Helena Lindgren1
1
Computing Science Department, Umeå University, Sweden
{esteban, helena}@cs.umu.se
2
Human Performance and Technology Lab., National Taiwan University, Taiwan
{f01630002,yueh}@ntu.edu.tw
Abstract. This paper is aimed at formalizing the interplay among a
person to be assisted, an assistive agent-based software, and a caregiver.
We propose principles that agents should follow in such interplay, this
principles may have impact in different agent-based assistive technology.
We propose a mechanism to integrate individual’s information into the
final decision-making process of an agent. Moreover, we endow agents
with mechanisms for evaluating the distance between independent and
supported activity execution, the so called zone of proximal development
(ZPD) in four scenarios: I) independent activity execution by a person;
II) ZP DH activity performance of a person supported by another person
(e.g. a therapist); III) the ZP DS representing a potential activities when
a person is supported by a software agent; and IV) the ZP DH+S when
a person is supported by a caregiver and a software agent. Formal argu-
mentation theory is used as foundation. Our formal models were tested
using a prototype using augmented reality as assistive software. A pilot
study with older adults and health-care personnel was performed and
formal and empirical results are presented.
Keywords: Argumentation theory · Rational agents · Assistive technol-
ogy · Human activity · Activity theory.
1 Introduction
This paper is aimed at investigating assistive technology using argumentation-
based agents and the interplay with individuals that require physical assistance
and their caregivers.
We present formal and empirical results on how intelligent software adapts
to support activities of individuals including, those who need assistance and care
givers. The focus of the paper is on the provision of human-like characteristics
to software agents in order to provide adaptable support, namely common-sense
and reflection on action decision. The proposed agent model is oriented to reason
about human activities, i.e., identify and interpret activities, and support indi-
viduals during the execution of physical activities. To this end, representations
of complex activities from Activity Theory [15] were utilized to characterize the
2 Guerrero et al.
knowledge of software agents about human activities and model their decision-
making process. Formal argumentation theory is used to provide non-monotonic
reasoning to the agents. Moreover, we present a novel information model oriented
at how an agent3 may reflect on their actions. In human learning literature, re-
flection enables a person to correct distortions in her/his beliefs and errors in
problem-solving [17]. We contribute with a first step on how rational software
agents may reflect during the support of human activities.
Finally, as core of our research, we propose a model of adaptation of a support
level for agents, based on a computation version of the so-called zone of proximal
development (ZPD) [23]. Our model of adaptation is formally presented and
empirically tested.
The research questions (RQ) addressed in this paper are the following:
– RQ1: how an agent may infer potential activities that an individual needs
and performs with and without its assistance?
– RQ2: in a smart environment scenarios, where individuals require support
from others to execute an activity, how an agent-based software may adapt
autonomously to team-up with humans to enhance such support?
– RQ3: how rational agents can “reflect” on decision to make when a human
is in the loop?
This paper is structured as follows: Section 2 presents definitions about how
human activities are structured, we also introduce some definitions about formal
argumentation theory and argument-based reasoning. In Section 3 our main
contributions are presented trying to solve RQ1-3. Using a medical scenario, we
developed a prototype to test empirically the level of assistance, some results
are presented in Section 4. Conclusions and a discussion is presented in Section
5.
2 Background
In this paper, the human perspective is investigated using Activity Theory [15],
which is a social sciences framework oriented to understand human complex ac-
tivities. On the other hand, formal argumentation theory is used to characterize
precisely the internal reasoning of agent software.
2.1 Activity theory
In this paper, activity theory is used with two purposes: 1) for structuring the
knowledge of an agent following a hierarchical model; and 2) to understand the
potential level of activity achievement of a person.
Activity as structure. An activity consists of a set of actions. At the lowest
level, an action consists of a set of operations. Actions are oriented to goals and
are executed by the actor at a conscious level, in contrast with operations which
3
Hereinafter we will identify a rational software agent as just an agent.
Assistive agents and human activities 3
do not have a goal of their own and which are executed at the lowest level as
automated, unconscious processes. An activity model (AT) (see Definition 1)
corresponds to information of a person that an agent uses to reason about an
activity.
Definition 1 (Activity model). Let P be a logic program capturing the behav-
ior rules of an activity. LP denotes the set of atoms which appear in a program
P . An AT model is a tuple of the form hAx, Go, Opi in which:
– Ax = {ax1 , . . . , axj }(j > 0) is a set of atoms such that Ax ⊆ LP . Ax denotes
the set of actions in an AT model.
– Go = {g1 , . . . , gk }(k > 0) is a set of atoms such that Go ⊆ LP . Go denotes
the set of goals in an AT model.
– Op = {o1 , . . . , ol }(l > 0) is a set of atoms such that Op ⊆ LP . Op denotes
the set of goals in an AT model.
In artificial intelligence literature, this hierarchical structure has been used
as framework to represent knowledge of software agents, e.g. in [8,10,11,18].
An activity framework corresponds to the goals, observations and actions of
an agent oriented to assist a human during the execution of an activity, which
in turn is represented by the AT model. To capture the knowledge of an agent
about its environment, we use extended logic programs [7] . An extended normal
program P is a finite set of extended normal clauses. By LP , we denote the set
of atoms which appear in a program P. ELP use both strong negation ¬ and
not, representing common-sense knowledge through logic programs.
Definition 2 (Activity framework). An activity framework ActF is a tuple
of the form hP, HA , G, O, ATi in which:
– P is a logic program. LP denotes the set of atoms which appear in P .
– HA = {h1 , . . . , hi } is a set of atoms such that HA ⊆ LP . HA denotes the set
of hypothetical actions which an agent can perform in a world.
– G = {g1 , . . . , gj } is a set of atoms such that G ⊆ LP . G denotes a set of goals
of an agent.
– O = {o1 , . . . , ok } is a set of atoms such that O ⊆ LP . O denotes a set of
world observations of an agent.
– AT is an activity model of the form: hAx, Go, Opi, following Definition 1.
ActF according to Definition 2 defines the space of knowledge of assistive
agents without considering external assistance, for example from other assistive
agents (human or software) actions. In this knowledge space, an argument-based
process (see Figure 1) can be performed to obtain sets (or sets of sets) of ex-
plainable structures support-conclusion for what is the best assistive action to
take.
Potential level of activity achievement. Vygotsky in [23] proposed to mea-
sure the level of development not through the level of current performance, but
through the difference (“the distance”) between two performance indicators: 1)
4 Guerrero et al.
an indicator of independent problem solving, and 2) an indicator of problem solv-
ing in a situation in which the individual is provided with support from other
people [14]. This indicator was coined as a zone of proximal development ZPD
and it has been used extensively in social sciences (see [1,4,13,21]) to understand
changes of individuals during assisted learning processes.
ICF qualifiers. The notion of qualifier to specify the extent of the func-
tioning or disability of an individual was introduced by the International Clas-
sification of Functioning, Disability and Health (ICF)4 [19] proposing two main
quantifiers: performance and capacity. In general, a qualifier specifies informa-
tion about functioning status: the magnitude, the location and the nature of any
activity-related problem [20].
2.2 Formal argumentation theory
Argumentation-based systems, have become influential in artificial intelligence
particularly in multi-agent systems design (see [3] for a systematic review).
Formal argumentation process
Activity Acceptability Argument-based
Knowledge Conflict Justified
fragments of activity Conclusions
base analysis conclusions
construction fragments
Activity Argument
Extensions
fragments framework
STEP 1 STEP 2 STEP 3 STEP 4
Fig. 1. Inference of an argument-based conclusion using a formal argumentation pro-
cess
Reasoning about human activities may be performed using a bottom-up man-
ner, building fragments of an activity explaining the current situation of a person.
This process compresses the STEP 1 in Figure 1.
Definition 3 (Hypothetical fragments). Let ActF = hP, HA , G, O, ATi
be an activity framework. A hypothetical fragment of an activity is of the form
0 0 0
HF = hS, O , h, gi such that: 1) S ⊆ P, O ⊆ O, h ∈ HA , g ∈ G; 2) S ∪O ∪{h}
0 0
is consistent; 3) g ∈ T such that ASP (S ∪ O ∪ {h}) = hT, F i; and 4) S and O
are minimal w.r.t. set inclusion. ASP (S) is a function that returns an answer-set
solution of an ELP program, i.e., it provides a common-sense reasoning process
given a program as input.
In short, an hypothetical fragment is a consistent manner to explain (inter-
connected) parts of an activity. Some of these fragments may be contradictory
given inconsistent information in the AT model or/and defeasible information
captured by an agent (STEP 2 in Figure 1).
4
http://www.who.int/classifications/icf/en/
Assistive agents and human activities 5
Definition 4 (Contradictory relationships among fragments).
Let ActF = hP, HA , G, O, Actsi be an activity framework. Let HF1 =
0 0
hS1 , O1 , a1 , g1 i, HF2 = hS2 , O2 , a2 , g2 i be two fragments such that HF1 , HF2 ∈
HF. ASP (Supp(HF1 )) = hT1 , F1 i and ASP (Supp(HF2 )) = hT2 , F2 i denote the
semantic evaluation of the support, then HF1 attacks HF2 if one of the following
conditions hold: 1) α ∈ T1 and ¬α ∈ T2 .; 2) α ∈ T1 and α ∈ F2 .
An argumentation framework is a pair hArgs, atti in which Args is a finite
set of arguments and att ⊆ Args × Args. In [10] an argumentation-based ac-
tivity framework for reasoning about activities was proposed, by considering
argumentation as inference method:
Definition 5 (Activity argumentation framework). Let ActF be an activ-
ity framework of the form hP, HA , G, O, Actsi; let HF be the set of fragments
w.r.t. ActF and AttHF or simply Att the set of all the attacks among HF.
An activity argumentation framework AAF with respect to ActF is of the form:
AAF = hActF, HF, Atti
Dung in his seminal work [6] introduced a set of patterns of selection of
arguments called argumentation semantics. An argumentation semantics SEM
is a formal method to identify conflict outcomes from argumentation frameworks
(AF).
Definition 6. Let AAF = hActF, HF, Atti be an activity argumentation frame-
work AAF with respect to ActF = hP, HA , G, O, Actsi An admissible set of frag-
ments S ⊆ HF is stable extension if and only if S attacks each argument which
does not belong to S. preferred extension if and only if S is a maximal (w.r.t.
inclusion) admissible set of AAF. complete extension if and only if each argu-
ment, which is acceptable with respect to S, belongs to S. grounded extension if
and only if it is a minimal (w.r.t. inclusion) complete extension. ideal extension
if and only if it is contained in every preferred set of AAF.
The sets of arguments suggested by an argumentation semantics are called
extensions. Let SEM () be a function returning a set of extensions, given an AF
such as an AAF. We denote SEM (AAF ) = {Ext1 , . . . , Extk } as the set of k
extensions generated by an argumentation semantics w.r.t. an activity argumen-
tation framework AAF .
Definition 7. 1) An fragment HFA ∈ HF is acceptable w.r.t. a set S of frag-
ments iff for each fragment HFB ∈ HF: if HFB attacks HFA , then HFB is
attacked by S. 2) conflict-free set of fragments S in an activity is admissible iff
each fragment in S is acceptable w.r.t. S.
Using these notions of fragment admissibility, different argumentation se-
mantics can draw given an activity argumentation framework (STEP 3 Figure
1):
6 Guerrero et al.
Definition 8. Let AAF = hActF, HF, Atti be an activity argumentation frame-
work following Definition 5. An admissible set of fragments S ⊆ HF is: 1) stable
if and only if S attacks each fragment which does not belong to S; 2) preferred if
and only if S is a maximal ( w.r.t. inclusion) admissible set of AAF ; 3) complete
if and only if each fragment, which is acceptable with respect to S, belongs to S;
and 4) the grounded extension of AAF if and only if S is the minimal ( w.r.t.
inclusion) complete extension of AAF .
Conclusions of an argument-based reasoning about an activity (see STEP 4
in Figure 1) may be obtained using a skeptical perspective, i.e., accepting only
irrefutable conclusions as follows:
Definition 9 (Justified conclusions). Let P be an extended logic program,
AFP = hArgP , At(ArgP )i be the resulting argumentation framework from P and
SEMArg be an argumentation semantics. If SEMArg (AFP ) = {E T1 , . . . , En }(n ≥
1), then Concs(Ei ) = {Conc(A) | A ∈ Ei }(1 ≤ i ≤ n). Output = i=1...n Concs(Ei ).
Where Ei are sets of fragments called extensions. The set of all the extensions
generated by SEMArg (AFP ) are denoted as E
3 Reflection on decisions about human activity
In this section, we report formal results to understand how autonomous agents
may change the level of assistance in different scenarios. Two main formal results
are presented in this section: 1) a mechanism for agent’s decision-making based
on the individual’s information analyzing consequences of hypothetical actions
a mechanism that we called reflection; and 2) a formalism to determine the
potential of activity performance in four different cases: independence, supported
by another person, supported by a software agent and supported by a team
person-agent.
3.1 Reflection on decisions about human activity
Conclusions of an argument-based process (Definition 9) about an activity, may
contain sets of goal-based conclusions sets, indicating that the agent has different
available decision alternatives which are consistent. We propose adding a mech-
anism for selecting an appropriate decision but considering those agent’s actions
that maximize humans’ goals (Go) in an activity model (AT model Definition 1).
An AT model captures all the information necessary to define a human activity.
We condensed this process in Algorithm 1.
In short, Algorithm 1 takes as input the AT model and the set of extensions
from a previous common-sense reasoning output. In lines 8-15 of Algorithm 1
a qualifier is calculated (line 12) over sets of sets of fragments (the so-called
extensions in argumentation theory, see Appendix 2). This qualifier calculation
is based on computing a similarity function between the current achievement
of human goals in AT (OGo ) w.r.t. a set of goal reference (Ref Go line 12). The
Assistive agents and human activities 7
Algorithm 1: Goal-based action reflection
input : E, AT
output : h ∈ HA
1 H ←− ∅ // list of agent’s decisions
2 Go ←− ∅ // list of human’s goals
3 Ref ←− ∅ // list of human’s reference goals
4 numExt = |E| // number of extensions
5 numArg = |A| // number of arguments per extension
6 α ←− 0 // numeric value of a qualifier (0 ≤ α ≤ 4)
7 decisionLat < α, h >= // lattice of decisions
8 for i ← 0 to numExt do
9 for j ←− 0 to numArg do
10 h ←−Act (hfj )
11 O ←−Obs (hfj )
12 α ←−Q(OGo , RefGo ) // Qualifier function considering
observations and a reference value w.r.t. person goals Go
13 decisionLat ←− (α, h)hfj // decision tuple is qualifier and an
agent’s decision w.r.t the current fragment
14 end
15 end
16 return max(α, h)
Q function depicted in line 12, follows the qualifier idea presented in previous
approaches [10,11], returning a numerical value (0 ≤ α ≤ 4).
The importance of Algorithm 1 lies on the mechanism for associating a human
activity quantification with the internal action decision of an agent. Proposition
1 and Proposition 2 present two special cases of agent’s behavior when Algorithm
1 is used5 . One is the possibility to have a conclusion with no action, and the
second expresses an inconclusive behavior given that stable semantics may return
∅ as output.
Proposition 1. An agent calculating a goal-based action reflection Algorithm 1
using a skeptic semantics, grounded or ideal, may result in a conclusive empty
decision.6
Proposition 2. An agent calculating a goal-based action reflection Algorithm 1
using the credulous semantics: stable, may result in a inconclusive decision.7
5
We refrain of describing fully the proofs of these propositions due the lack of paper
space
6
Proof sketch: output of grounded and ideal may include {∅}. See [5]
7
Proof sketch: output of stable semantics may include ∅. See [5]
8 Guerrero et al.
3.2 Zone of proximal development using formal argumentation
In this section, based on the common-sense reasoning of activities using argu-
mentation theory, we propose a theory to calculate the following four scenarios
in assistive agent-based technology:
I. Independent activity execution This scenario describes an observer
agent which takes a decision which is purposefully do nothing to support a per-
son, or the decision is empty. More formally, the type of fragments (Definition
0
3) generated by the agents are with the form HF = hS, O , h∗ , gi such that
∗
h ∈ HA = {∅, do N othing}. In this setting, all the extensions generated by
SEM (AFP ) = E during a period of time will create an activity structure. In
other words, the cumulative effect of generating fragments, re-construct an ac-
tivity in a bottom-up manner. Moreover, Algorithm 1 returns only values of α,
i.e. the current value of a qualifier when the agent does not take any support
action. This context defines the baseline of activity execution independence of a
person.
II. ZP DH : activities supported by another person Similarly to previous
scenario, the role of the software agent is being an observer. However, built frag-
ments have the form HF = hS, O∗ , h∗ , gi such that h∗ ∈ HA = {∅, do N othing}
0 00
and O∗ = O ∪ O , where O∗ is the set of joint observations from the agent’s
0 00
perspective about the individual supported (O ) and the supporter O . We have
0 00 0 00 00
that O ⊆ O , and O , O 6= ∅. In this scenario, O is considered a reference
set of observations (Ref lines 3 and 12 in Algorithm 1). Algorithm 1 will re-
turn a value of α which measures in what extent an individual follows the guide
provided by another person.
When multiple extensions are collected during the period of time that the
individual is supported, then a different set of activities than individual activity
execution may be re-generated in a bottom-up manner.
III. ZP DS : activities supported by an agent In this scenario, an assistive
agent takes a decision oriented to uphold human interests. This is a straightfor-
ward scenario where h ∈ HA 6= {∅, do N othing}.
IV. ZP DH+S : human-agent supporting In this scenario, the main challenge
for the agent perspective is detect: 1) actions that an assistant person executes,
and 2) observations of both, the person assisted and the person who attends. This
is similar to ZP DH but with fragments built from HA 6= {∅, do N othing}. In
this case, the level of ZP DH+S is given by Algorithm 1, and the set of extensions
E with aligned goals between agent and human assistant.
Proposition 3. Let OGo be a set of observations about human goals (Go) and
actions (Ax) framed on an activity, captured by an agent using an activity model
AT. Let G and HA be agent’s goals and its hypothetical actions. In order to
provide non-conflicting assistance two properties have to be fulfilled:
– PROP1: OGo ∩ G 6= ∅
– PROP2: OAx ∩ HA 6= ∅
Assistive agents and human activities 9
PROP1 and PROP2 provides coherence among human-agents actions and
goals. This two properties may define a first attempt to establish consistency
principles of agent-based assistance. This is a future work in our research.
4 Empirical results
In this section, we present results of an empirical evaluation of different values
of ZPD. The pilot test was illustrative, aimed at exploring ZPD values in a real
setting, then make a qualitatively comparison with our formal approach.
4.1 Prototype and pilot evaluation
The scenario selected to test our approach was framed on supporting an older
adult in the activity: medication management using a smart medicines cabinet.
In a smart environment8 developed at the user, interaction and knowledge man-
agement research group9 , we setup the smart cabinet 10 (see Figure 2).
projector
smart medicines
cabinet
Kinect sensor 2 Text Recognition
II
Google API
Kinect sensor 1
Gesture Argument-based Goal-based action Augmented
Recognition Reasoning Reflection
reality
III IV
Kinect sensor 3 I Medicine database projection
(doses) V
Local machine
Fig. 2. Smart medicines cabinet using argument-based reasoning and an augmented
reality projection. I) Gesture recognition using three Kinect cameras, one for client
body capture, another for assistant personal gesture recognition, last one (Kinect sensor
2) on the top of the cabinet to recognize text from medicines boxes; II) Google API
for text recognition; III) common-sense reasoning; IV) goal-based action reflection to
consider human side; V) database containing doses and timing of pill intake.
8
360 degrees view of the lab: https://goo.gl/maps/rq3YiF1c5An
9
Computing Science department Umeå University- Sweden
10
Due the lack of space, we briefly describe the smart cabinet prototype which is
connected to our agent-based platform
10 Guerrero et al.
Architecture summary: Our prototype consists of five main parts: 1) ges-
tures recognition: obtaining observations from individuals using Kinect cameras;
2) text recognition using another Kinect camera with Google API text recogni-
tion (https://cloud.google.com/vision); 3) argument-based reasoning: the
main agent-based mechanism of common sense reasoning; 4) goal-based action
reflection generating an augmented reality feedback: a module to generate sup-
port indications as projections in the smart environment; and 5) a database of
medicine doses to obtain appropriate messages11 . We use three 3D cameras to
capture: 1) observations of an individual that needs help in a physical activ-
ity; 2) observations of the smart environment, including a supporting person;
and 3) information of the handle gestures of medicine manipulation. A central
computer was connected to the cameras, processing the information in real-time
analyzing gestures of individuals as observations for the agent. The agent plat-
form (JaCaMo) was used to build the agent. An argumentation process was used
using an argumentation library previously developed (see [9]). An agent try to
update/trigger its plan every frame time that a pre-defined gesture of the 3D
camera. Those pre-defined gestures were defined in Stage 1 and Stage 2 with
users and experts.
Pilot evaluation setting summary: This pilot study recruited five par-
ticipants, see Table X. All of the participants had technology experience using
computers . The procedure comprised three stages: 1) baseline interview (sub-
Type of user Age Sex Participation
TA-1 67 M Stage 1 - Stage 3
TA-2 71 F Stage 1 - Stage 3
TA-3 57 F Stage 1 - -
S-1 50 F - Stage 2 -
S-2 25 F - - Stage 3
Table 1. Pilot setting
jects: TA-1, TA-2, TA-3 + S-1, S-2); 2) interview with a nurse (S-2); and 3)
prototype evaluation (subjects: TA-1, TA-2 + S-2). For a lack of space we only
describe the third stage in which participants interact the smart platform. In
the third stage, TA-1 participated the evaluation in his home and the other
two participates evaluated the system. They were asked to read the instruc-
tion message from the augmented reality projection and then, distribute three
medications with different prescriptions by using the system. The Assessment
of Autonomy in Internet-Mediated Activity protocol (AAIMA) [16] was used to
evaluate ZPD. A comparison between our agent ZPD and AAIMA results were
obtained. In Table 2 results of ZPD-S and ZPD-H were obtained.
5 Discussion and conclusions
Formal argumentation can be seen as a process consisting of the following
11
Sources and documentation of the prototype can be found in https://github.com/
esteban-g
Assistive agents and human activities 11
Table 2. AAIMA Protocol for assessing medication management
Our main contribution in this paper is in general, a formal understanding of
the interplay among an assistive agent-based software, a person to be assisted and
a caregiver. Moreover, as far as we know, this is a first attempt to formalize the
behavior of rational agents using formal argumentation theory, in four scenarios:
I) independent activity execution, which resembles the so-called zone of current
development ZCD [12]; II) ZP DH which is a set of potential activities that a
person can execute with the support of another person (e.g. a therapist); III)
the ZP DS representing a potential activities when a person is supported by a
software agent; and IV) the ZP DH+S which is the set of activities that a person
may be able to perform when is supported by another person and a software
agent.
). We propose two properties (Proposition 3) that software agents should follow
if their goals are linked to human goals. The relevance and impact of these
properties not only covers agents based on formal argumentation theory, but
other approaches, such as those based on the Belief Desire Intention model [2].
We propose an algorithm to integrate individual’s information (the AT model
Definition 1) into the final decision-making process of an agent. This mechanism
captured in Algorithm 1, resembles a process of “reflection” which in humans is
a re-consideration of actions and goals given some other parameters. In fact, our
reflection mechanism maybe seen as an action-filtering process with the human-
in-the-loop12 . We also analyze different outputs of Algorithm 1 considering two
groups of argumentation semantics (Propositions 1 and 2).
12
A concept to integrate human information in cyber-physical systems [22]
12 Guerrero et al.
We evaluate our approach in a three stages pilot study using a scenario of
medication management as a complex activity. In this regard, we conducted
an experiment with older adults and practitioners to evaluate such activity.
We developed a prototype platform using augmented reality projecting assistive
messages about medication when a person required some support. For lack of
space, we did not fully report in this paper, the full functioning of the platform
neither the process of co-design and expert feedback.
References
1. Aljaafreh, A.L., Lantolf, J.P.: Negative feedback as regulation and second lan-
guage learning in the zone of proximal development. The Modern Language Journal
78(4), 465–483 (1994)
2. Bratman, M.: Intention, plans, and practical reason. Harvard University Press
(1987)
3. Carrera, Á., Iglesias, C.A.: A systematic review of argumentation techniques for
multi-agent systems research. Artificial Intelligence Review 44(4), 509–535 (2015)
4. Chaiklin, S.: The zone of proximal development in vygotskys analysis of learning
and instruction. Vygotskys educational theory in cultural context 1, 39–64 (2003)
5. Dix, J.: A classification theory of semantics of normal logic programs: II. weak
properties. Fundam. Inform. 22(3), 257–288 (1995)
6. Dung, P.M.: On the acceptability of arguments and its fundamental role in non-
monotonic reasoning, logic programming and n-person games. Artificial Intelligence
77(2), 321–357 (1995)
7. Gelfond, M., Lifschitz, V.: Classical negation in logic programs and disjunctive
databases. New generation computing 9(3-4), 365–385 (1991)
8. Guerrero, E., Nieves, J.C., Lindgren, H.: Ali: An assisted living system for persons
with mild cognitive impairment. In: Computer-Based Medical Systems (CBMS),
2013 IEEE 26th International Symposium on. pp. 526–527. IEEE (2013)
9. Guerrero, E., Nieves, J.C., Lindgren, H.: Semantic-based construction of argu-
ments: An answer set programming approach. International Journal of Approxi-
mate Reasoning 64, 54 – 74 (2015)
10. Guerrero, E., Nieves, J.C., Sandlund, M., Lindgren, H.: Activity qualifiers in an
argumentation framework as instruments for agents when evaluating human activ-
ity. In: Advances in Practical Applications of Scalable Multi-agent Systems. The
PAAMS Collection, pp. 133–144. Springer (2016)
11. Guerrero, E., Nieves, J.C., Sandlund, M., Lindgren, H.: Activity qualifiers using an
argument-based construction. Knowledge and Information Systems 54(3), 633–658
(2018)
12. Harland, T.: Vygotsky’s zone of proximal development and problem-based learning:
Linking a theoretical concept with practice through action research. Teaching in
higher education 8(2), 263–272 (2003)
13. Hedegaard, M.: The zone of proximal development as basis for instruction. In: An
introduction to Vygotsky, pp. 183–207. Routledge (2002)
14. Kaptelinin, V., Nardi, B.A.: Acting with Technology: Activity Theory and Inter-
action Design. Acting with Technology, MIT Press (2006)
15. Leontyev, A.N.: Activity and consciousness. Moscow: Personality (1974)
Assistive agents and human activities 13
16. Lindgren, H.: Personalisation of internet-mediated activity support systems in the
rehabilitation of older adults–a pilot study. proc Personalisation for e-Health pp.
20–27 (2009)
17. Mezirow, J., et al.: How critical reflection triggers transformative learning. Foster-
ing critical reflection in adulthood 1, 20 (1990)
18. Nieves, J.C., Guerrero, E., Lindgren, H.: Reasoning about human activities: an ar-
gumentative approach. In: 12th Scandinavian Conference on Artificial Intelligence
(SCAI 2013) (2013)
19. Organisation mondiale de la santé and World Health Organization: International
Classification of Functioning, Disability and Health: ICF. Nonserial Publication,
World Health Organization (2001), http://www.who.int/classifications/icf
20. Organization, W.H.: How to use the ICF: A practical manual for using the Inter-
national Classification of Functioning, Disability and Health (ICF). Geneva:WHO
(2013), http://www.who.int/classifications/drafticfpracticalmanual2.pdf
21. Salomon, G., Globerson, T., Guterman, E.: The computer as a zone of proximal
development: Internalizing reading-related metacognitions from a reading partner.
Journal of educational psychology 81(4), 620 (1989)
22. Schirner, G., Erdogmus, D., Chowdhury, K., Padir, T.: The future of human-in-
the-loop cyber-physical systems. Computer 46(1), 36–45 (2013)
23. Vygotsky, L.S.: Mind in society: The development of higher psychological processes.
Harvard university press (1980)