Review
Artificial Vision Algorithms for Socially Assistive Robot
Applications: A Review of the Literature
Victor Manuel Montaño-Serrano
1,†
, Juan Manuel Jacinto-Villegas
1,2,†,
* , Adriana Herlinda Vilchis-González
1
and Otniel Portillo-Rodríguez
1
Citation: Montaño-Serrano, V.M.;
Jacinto-Villegas, J.M.; Vilchis-
González, A.H.; Portillo-Rodríguez,
O. Artificial Vision Algorithms for
Socially Assistive Robot Applications:
A Review of the Literature. Sensors
2021, 21, 5728. https://doi.org/
10.3390/s21175728
Academic Editors: Abolfazl Zaraki
and Hamed Rahimi Nohooji
Received: 27 July 2021
Accepted: 23 August 2021
Published: 25 August 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Facultad de Ingeniería, Universidad Autónoma del Estado de México, Toluca 50130, Mexico;
vmmontanos@uaemex.mx (V.M.M.-S.); avilchisg@uaemex.mx (A.H.V.-G.); oportillor@uaemex.mx (O.P.-R.)
2
Cátedras CONACYT, Ciudad de México 03940, Mexico
* Correspondence: jjacinto@conacyt.mx
† These authors contributed equally to this work.
Abstract:
Today, computer vision algorithms are very important for different fields and applications,
such as closed-circuit television security, health status monitoring, and recognizing a specific person
or object and robotics. Regarding this topic, the present paper deals with a recent review of the
literature on computer vision algorithms (recognition and tracking of faces, bodies, and objects)
oriented towards socially assistive robot applications. The performance, frames per second (FPS)
processing speed, and hardware implemented to run the algorithms are highlighted by comparing
the available solutions. Moreover, this paper provides general information for researchers interested
in knowing which vision algorithms are available, enabling them to select the one that is most suitable
to include in their robotic system applications.
Keywords: trustworthy HRI; robot artificial cognition; HRIs in real-world settings
1. Introduction
Socially assistive robots (SARs) are a type of robot that interacts closely with people [
1
].
Due to their characteristics, they can communicate with and understand the activities and
psychological state of a person, in order to respond in a positive way [
2
]. In addition,
these robots can express feelings and emotions [
1
,
3
]; they are commonly used in tasks
such as monitoring and caring for the elderly, supporting activities of daily living (ADL),
controlling the behavior and health of patients, performing company work, and offering
entertainment [
4
,
5
], besides helping with exercises and rehabilitation [
6
], among others.
To provide assistance to people employing SARs, it is typically necessary to implement
computer vision algorithms to identify the different objects in the environment, the user’s
location, or the user’s face when involved in a specific activity. Computer vision is a
growing area of study, in which constantly efficient algorithms, such as those for detection,
tracking, and recognition, are developed to perform a task with minimal error and emulate
human vision, which represents a challenge for different researchers.
Moreover, this paper deals with reviewing the literature on different computer vision
algorithms used in SAR applications, highlighting the number of FPS corresponding to
the velocity that each algorithm can process to determine if it can be used in real time,
its performance presented in percentages, and the hardware/software used to obtain the
results that the authors have reported.
Methods
The method used to carry out this review of the literature is described next. Google
Scholar, Elsevier, MDPI, and IEEE Explore databases were used to search for articles
published in peer-reviewed journals, books, and conferences, within the interval period
of 2010–2021. The keywords used for this review paper were: assistive robotics; face,
Sensors 2021, 21, 5728. https://doi.org/10.3390/s21175728 https://www.mdpi.com/journal/sensors
