Technical development of the CeCi social robot

  Citation: Flores-Vázquez, C.; Angulo, C.; Vallejo-Ramírez, D.; Icaza D.; Pulla Galindo, S. Technical Details about CeCi Social Robot. Sensors 2022,22, 7619. https://doi.org/ 10.3390/s22197619 Academic Editor: Miguel Ángel Conde Received: 23 August 2022 Accepted: 30 September 2022 Published: 8 October 2022 Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Copyright: © 2022 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/). sensors Article Technical Development of the CeCi Social Robot Carlos Flores-Vázquez 1,2,3,* , Cecilio Angulo 2, David Vallejo-Ramírez 1,3 , Daniel Icaza 1 and Santiago Pulla Galindo 1 1Electrical Engineering Career, Research Group in Visible Radiation and Prototyping GIRVyP, The Center For Research, Innovation, and Technology Transfer CIITT, Universidad Católica de Cuenca, Cuenca 010107, Ecuador 2 Intelligent Data Science and Artificial Intelligence Research Center, Universitat Politècnica de Catalunya UPC BarcelonaTECH, Pau Gargallo 14, 08034 Barcelona, Spain 3Laboratory of Luminotechnics, The Center For Research, Innovation, and Technology Transfer CIITT, Universidad Católica de Cuenca, Cuenca 010107, Ecuador *Correspondence: cflor[email protected] Abstract: This research presents the technical considerations for implementing the CeCi (Computer Electronic Communication Interface) social robot. In this case, this robot responds to the need to achieve technological development in an emerging country with the aim of social impact and social interaction. There are two problems with the social robots currently on the market, which are the main focus of this research. First, their costs are not affordable for companies, universities, or individuals in emerging countries. The second is that their design is exclusively oriented to the functional part with a vision inherent to the engineers who create them without considering the vision, preferences, or requirements of the end users, especially for their social interaction. This last reason ends causing an aversion to the use of this type of robot. In response to the issues raised, a low-cost prototype is proposed, starting from a commercial platform for research development and using open source code. The robot design presented here is centered on the criteria and preferences of the end user, prioritizing acceptability for social interaction. This article details the selection process and hardware capabilities of the robot. Moreover, a programming section is provided to introduce the different software packages used and adapted for the social interaction, the main functions implemented, as well as the new and original part of the proposal. Finally, a list of applications currently developed with the robot and possible applications for future research are discussed. Keywords: social robotics; robot design; human robot interaction; mobile robotic platform; SLAM 1. Introduction The development of technology is one of the challenges for developing countries that regularly base their economy on the sale of commodities. This research aims to demonstrate the capacity of a country such as Ecuador to build its own technology and that this can be used for the development of new research in universities as well as for technology transfer for new products in the private sector. All those mentioned above could generate new qualified jobs in the country and an effect of economic welfare [1–3]. The development of this robot is mainly based on the article by Flores et al. [ 4 ]. However, the proposals of [5–9] were reviewed to complement and improve this prototype. Considering the current market regarding existing equipment such as the Savioke Relay robot Figure 1a with a height of 0.91 m and a weight of 45.36 kg; with the ability to navigate autonomously indoors employing a LIDAR, 3D sensors, and several sonar sensors [ 10 , 11 ], which also enabled a container with 0.75 cubic feet of storage to fulfill functions of transport and delivery of elements within a hotel. The price of the Savioke robot is EUR 25,971.00 [12]. Sensors 2022,22, 7619. https://doi.org/10.3390/s22197619 https://www.mdpi.com/journal/sensors Sensors 2022,22, 7619 2 of 19 (a) (b) (c) (d) (e) (f) (g) (h) (i) Figure 1. Robots: ( a ) Savioke [ 13 ] ( b ) Vecna QC Bot [ 14 ] ( c ) Aethon TUG [ 15 ] ( d ) Care-O-bot 4 [16] (e) Temi [17] (f) Thalon [18] (g) Dinerbot-T8 [19] (h) Pepper [20] (i) Nao [21]. Others along the same lines as Savioke could be Vecna QC Bot, and Aethon TUG see Figure 1b,c deployed for environments such as hospitals and hotels [ 22 ]. The three previously mentioned have been on the market for several years, but their designs show a functional,task-oriented approach, which is far from the proposed user centered design approach. The proposed robot CeCi is characterized by its utility as it is a service robot, but social design considerations have been emphasized to interact with users as described in [4,23,24]. Care-O-bot 4: this robot is a complete proposal considering the social aspects and functionality. It has a height of 158 cm and its full weight is 140 kg with 29 degrees of freedom (see Figure 1d) so it can be deduced that its cost is above one of the design conditions raised in this proposal, an accessible price for emerging countries [ 25 ]. A final consideration is that its arms can only hold 5 kg, so its constituent hardware generates an expectation that is higher than its useful functional capabilities. The price of Care-O-bot is EUR 65,927.00 to EUR 231,743.00 Euros depending on the configuration [26]. The Temi robot, which is manufactured by Robotemi, a company from Shenzhen, China, Figure 1e is a robot with various applications such as food delivery [ 27 ]. An application that stood out during the pandemic, its usefulness in medical assistance could be seen, as a thermometer and a thermal camera were added to its original design, mainly to deal with COVID problems and in telepresence activities in geriatric homes. Its basic configuration consists of four wheels, LIDAR, cameras, proximity sensors and an IMU. Among the considerations of this robot is its design, which does not generate empathy with people, is intended to be functional rather than social [ 28 , 29 ]. The TEMI price is EUR 7541.00 including travel and shipping case [ 30 ]. Import taxes of 12 to 25% should be added to this value. Thalon Robot (Figure 1f) is the Colombian version of Savioke. Twenty engineers were employed for its development and construction, and the price is EUR 242,500.00. It is Sensors 2022,22, 7619 3 of 19 programmed to fulfill the functions of a minibar in hotels. It has refrigerated storage spaces in its torso. Navigation and obstacle avoidance are based on a 3D LIDAR, ultrasound and infrared sensor [31]. The Dinerbot–T8 from Keenon Robotics is one of the most refined robots in terms of aesthetic and Smart delivery capabilities. Features include centimeter-accurate positioning for athe smooth traversing of ultra-narrow paths, Intelligent Obstacle Avoidance, binocular vision plan with a 204 ◦ real-time dynamic obstacle detection for safer and more flexible movement. Its height is 1096 mm [32]. See Figure 1g. Pepper Figure 1h and Nao Figure 1i are two robots from Soft Bank Robotics. Unlike the previously reviewed robots with a task and practicality orientation, these prioritize the human-robot interaction approach. As such, their functionality or practicality is not a priority, and their ability to move objects and weight are lower than the previous robots. NAO’s price is EUR 19,478.00 [ 21 ] and Pepper Robot’s price is EUR 31,964.00 [ 33 ] both including a travel and shipping case. Pepper and Nao have allowed the development of interesting application cases in social robotics such as [ 34 , 35 ] that we wish to implement with CeCi in the near future. This brief review of the main social-service robots allows to show the context described from the introduction concerning high prices and functionalities similar to the one of this research achieved by the CeCi social robot. Even these robot prices increase with the addition of shipping costs, which is precisely why CeCi has straight and flat shapes to pack the disassembled robot in the smallest possible space and reduce transportation costs. The patent number EC ECSDI22004944S process took place alongside the development of this paper [ 36 ]. The National Service of Intellectual Rights (SENADI) registers the patent in Ecuador. This organization defines four patent categories: Patent of Invention, Utility Model, Industrial Design, Layout-Designs of integrated circuits. CeCi is patented as an Industrial Design, specifically “the particular appearance of a product resulting from any meeting of lines or combination of colors, or from any two-dimensional or threedimensional external shape, line, contour, configuration, texture, or material, without changing the destination or purpose of this product” [ 37 ]. The Figure 2shows the nearest industrial robot designs registered in Ecuador by LG Electronics. However, the originality of the invention in the form of CeCi allowed its registration under the name of Social Robot. The registration of an industrial design will have a duration of 10 years. (a) (b) Figure 2. Domestic robot LG: (a) Patent 1 [38]. (b) Patent 2 [39]. Social Focus For the development of this research, the concept of acceptability was considered as a priority. “Acceptability as an evaluation before use or implementation of robots as opposed to acceptance, which is the evaluation after the implementation” [ 40 ]. The importance of human-robot interaction in social robotics lies in the matter of understanding ideas and preconceptions of the user, which is a vital element in the early stages of robot development [41]. Simple movements or gestures can give us relevant information about human activity [ 42 ] and this can be extrapolated to give intentionality of the activities that a robot might perform. In the case of CeCi, the eyes allow to achieve empathy for an Sensors 2022,22, 7619 4 of 19 adequate human-robot interaction and their verbal exchanges match the criteria of the articles [43,44]. The excellent article “What Makes a Social Robot Good at Interacting with Humans?” by Eva Blessing Onyeulo and Vaibhav Gandhi [ 45 ] they raise these two crucial questions: “Do social robots need to look like living creatures that already exist in the world for humans to interact well with them?”; “Do social robots need to have animated faces for humans to interact well with them?”. His answer to these questions is “that for humans to be able to interact well with a robot, the robot does not necessarily need to look like a human. However, the robot would benefit from some sort of “face”, a focal area that humans would have a direct conversation, especially if the facial features can move around to better express emotion in a life-like way”. This research ratifies CeCi’s proposed body shape that was achieved based on user feedback through focus groups. In this proposal, the selection and operation of hardware and software is presented in Section 2, in Section 3, the results achieved with the CeCi robot, and finally, in Section 4, the objectives achieved and future work that could be developed with the robot. 2. Materials and Methods This section will present the different constituent parts of the robot. In the the first subsection, a comparison of the sensors selected and implemented, an explanation of their operation and a comparison with other options will be made. The second subsection explains the implemented software and the capabilities that it allows the robot to develop. 2.1. Hardware Considerations This section presents all the hardware components that passed the four filters imposed for this research: The first filter is that the hardware element (sensor, actuator, processor, case among others) meets the technical requirements explained in the tables of the finalist details in the selection. The second filter, which is the most restrictive, is that the price of this component must be the minimum possible while maintaining the standards of filter 1. The third filter is the availability of this part in the local market or that the supplier allows easy shipment to South America-Ecuador. Finally, but probably most importantly, that it is in line with the end user’s preferences. If the hardware component did not meet these three requirements it was discarded even though they stood out in any of the three criteria above the others. Therefore, in this section, only the components that met the four filter criteria are presented, explaining their final selection. The mobile robot platform selected was iClebo Kobuki Figure 3, manufactured in Korea by Yujin Robot Co, Ltd. [ 46 ], because after a comparison with the iCreate 2 base of the manufacturer iRobot, it was found that Kobuki has more significant resources available in hardware and software in Robot Operating System (ROS) [ 47 ], so it has a greater possibility of action and versatility when testing for research and development purposes Table 1. To process all the information received by the different peripherals, an Intel NUC i5 with 8 GB of RAM was installed in the first instance. Still, due to the amount of information processed simultaneously, especially when performing simulations in the GAZEBO application and visualizations in RVIZ, the machine would not respond and would freeze. Similarly, when using the camera functions in conjunction with the mobile robot base, the camera image was lost or turned off, due to the above, the equipment was upgraded to an INTEL NUC i7 with 16 GB of RAM. By making this change, a significant improvement was obtained. However, there is still no total fluency when running several functions of the robots simultaneously, especially simulations. For operation only with the physical robot the computer is adequate. If it is possible to increase the ram to 64 GB and add an external graphics card would be recommendable improvement. Sensors 2022,22, 7619 5 of 19 Figure 3. Kobuki Sensors. Table 1. Mobile Robot Base Comparison. Kobuki iCreate 2 [48] Odometry Yes Yes Motor Overload Detection Yes No Bumpers Yes Yes Cliff Sensors Yes Yes Payload 5 kg 5 kg Battery 4400 mAh 4500 mAh Price 649.00 €200.00 € Wheel drop sensor Yes No Dimensions Diameter: 351.5 mm/Height: 124.8 mm/Weight: 2.35 kg Diameter: 340 mm/Height: 92 mm/Weight: 3.58 kg In the camera section, a physical comparison was made between two options: Orbbec Astra camera and Intel RealSense D435i Figure 4, both of which fit very well with the robot. Considering mainly the range of vision, price, support and compatibility with the operating system used, the Orbbec was chosen. The improvements presented by the D435i in terms of image quality, weight, dimensions and even the inclusion of the IMU (Inertial Measurement Unit) [ 49 ], which is a helpful element with the capacity to measure and report the specifications of the orientation, speed and gravitational forces that the equipment can suffer, were insufficient in the cost-benefit analysis in Table 2. One problem to consider with the Intel camera is that it still has compatibility issues with the Kinect version of ROS, but not with the Melodic and Noetic versions. When analyzing what type of laser scanner to use, three elements were taken into consideration. The first one was the Hokuyo UST-20LX which is an excellent piece of equipment with the best features and performance, but with a high cost for this application, it was discarded. So an option in line with a low-cost robot is the one offered by Slamtec. It was decided to install the RPLIDAR A3, its range, scanning frequency, and weight are sufficient for this robot and a considerable improvement over the previous version, the RPLIDAR A2, which was also considered as shown in Table 3. Sensors 2022,22, 7619 6 of 19 (a) (b) Figure 4. Cameras: (a) Intel RealSense D435i. (b) Orbbec Astra. Table 2. Camera comparison. Orbecc Astra Intel RealSense D435i Size 160 mm ×30 mm ×40 mm 90 mm ×25 mm ×25 mm RGB Image Size 1280 ×960 1920 ×1080 Range 0.3 a 8 mts 0.2 a 3 mts Field of View 60◦×49.5◦86◦×57◦(±3◦) Depth diagonal field of view over 73◦90◦ Microphones 2 Not Available Inertial Measurement Unit (IMU) Not Available Available Reference cost [50] EUR 149.00 EUR 349.00 Table 3. Laser Range Scanning Comparison . Hokuyo UST-20LX RPLIDAR A3 RPLIDAR A2 Dimensions 70 mm ×35 mm ×50 mm 72.50 mm ×41 mm ×76 mm 72.50 mm ×41 mm ×76 mm Weight 130 g 190 g 340 g Angular Resolution 0.25◦0.225◦or 0.36◦0.45◦–1.35◦ Range 0.06–20 m 8–25 m 0.2–18 m Precision ±40 mm Not Specified Not Specified Sample Rate 40 Hz 15 Hz (adjustable between 5–20 Hz) 8 Hz Reference cost [50] 2280.00 €EUR 539.00 EUR 465.00 For the screen, there are two GeChic portable touchscreen monitors with similar characteristics, the only difference being their size, 13.3 and 11.3 inches. The 13.3 00 monitor was installed as it is considered to be better visualized due to its large size, but when carrying out tests it was noted that it presents complications due to its volume and weight, as it must be on top of the robot to be able to interact with people and this generates instability in the structure, which can be seen when moving along paths that are not wholly smooth. For future versions, the 11.3-inch monitor will be considered. When testing in natural environments, the energy consumed by all constituent elements of CeCi, exceeded the capacity provided by the two batteries included in the Kobuki base. With this configuration, the robot’s autonomy in constant activity is 15 min and 25 min at rest. To solve this problem, an external 50,000 mAh Krisdonia battery Power Bank was included, which added autonomy of 4 h of continuous activity and 5 h and 30 min when idle. The external battery provides the power supply for the NUC computer, touch screen, lidar sensor, and camera. Therefore, the sensors and motors integrated in the mobile base are powered by the internal kobuki batteries, giving the mobile base an autonomy of 5 h of continuous Sensors 2022,22, 7619 7 of 19 activity on a flat surface and autonomy of 7 h at rest. Table 4compares the batteries used, and Table 5shows the consumption of the main peripherals of the robot. Figure 5illustrates the hardware parts mentioned with their respective locations on the robot. Figure 5. CeCi Parts. Table 4. Comparison of batteries used to power all components of the robot. Krisdonia 50,000 mah Power Pack External Battery Integrated Kobuki Battery Type Lithium polymer Lithium-Ion Capacity 50,000 mAh 4400 mAh Universal Compatibility Yes No Fast Charging Yes No Voltage/Amperage 5V/8.4V/9V/12V–3A; 16V/20V–4.7 A 3.3V/5V/12V/–1.5A; 12V–5A Active Autonomy 4 h 15 min Standby Autonomy 5 h 30 min 25 min Table 5. Power consumption of the main components of the robot. Voltage (V) Amperage (A) Watts (W) Orbbec Astra 5 0.38 1.85 RPLidar A3 5.5 0.6 3.6 Touchscreen 13.300 5 1.6 8 Speakers, Mouse, Keyboard 5 0.6 3 NUCi7BNH 4.5 12 54 TOTAL 70.2 Sensors 2022,22, 7619 8 of 19 2.2. Software Considerations Since the idea of making CeCi was generated, the open source platform Ubuntu 16.04 LTS was used, the version with long-term support [ 4 ]. During the course of the research several tests were carried out. One of them was to upgrade to 18.04 and even to version 20.04 but when installing and testing, it was found that it does not have compatibility with several packages necessary for the robot to fulfill the projected functions, so the development was continued in Ubuntu 16.04 LTS. Currently, CeCi software is supported on Ubuntu 20.04 LTS except for the navigation system, which is still in the process of being adapted. However, commercially available robots such as Temi, among others, are still using Ubuntu 16.04 for reliability. It is crucial to consider the right environment for working in ROS, which is not an operating system in the most common sense of programming and process management. Instead, it provides a structured communication layer at a higher level than the host operating systems. So there are several structured versions and each is compatible with a different version of Ubuntu, in this case, the version compatible with the 16.04 LTS operating system is ROS Kinetic [51]. For a clear understanding of the software that enables the operation of the social robot, some remarks about ROS are necessary [ 52 , 53 ]: This framework provides services such as hardware drivers, device control, implementation of resources commonly used in robotics, message passing between processes and packet maintenance. It is based on a graph architecture where the processing takes place in nodes that can receive, send and multiplex messages from sensors, control, states, planning, and actuators, among others. These messages are called topics or services. ROS is organized in terms of its software in (a) the operating system part, ROS, and (b) the ROS package that the user programmers contribute. Packages can be grouped into sets called stacks. Within the packages are the nodes to be executed. Figure 6illustrates the above. Figure 6. Graphical explanation of how ROS works in a brief overview [53]. The Robotic Operating System (ROS) is free software that is based on an architecture where processing takes place in nodes [ 54 ] that can receive, send and multiplex messages from: sensors, control, states, schedules, and actuators, among others. The ease of integrating various functions [ 55 ] and utilities through its topical system (internal communication) [ 56 ] exemplified in Figure 6, makes it very appropriate for the development of algorithms and the progress of research in robotics-related subjects [ 57 ]. Although it is not an operating system, ROS provides the standard services of an operating system, such as: hardware abstraction, low-level device control, implementation of commonly used functionality, inter-process message passing, and package maintenance. The CeCi software system is based on the structure provided by ROS in Packages, Nodes, Topics and Services. The following is an explanation by functional parts respecting the ROS architecture. The complete diagram of the Robot software was extracted from ROS using its graphical tool rqt_graph (node, topic and service diagram) and is included in Figure A1. The main packages used for CeCi are Kobuki and Turtlebot 2 from the Yujim Robot manufacturer. There was no major problem because the ROS version used has support. Sensors 2022,22, 7619 9 of 19 The Kobuki package allows to control and read the sensors of the mobile robotic base of the same name in detail, the utilities used are: • Automatic return to its charging base; • Publish bumpers and cliff sensors events as a pointcloud so navistack can use them; • URDF and Gazebo model description of Kobuki; • Keyboard teleoperation for Kobuki; • A ROS node wrapper for the kobuki driver; • Watches the bumper, cliff, and wheel drop sensor to allow safe operation; • Set of tools to thoroughly test Kobuki hardware [58]. Figure 7shows in a diagram the main functions contained in the package. Figure 7. Kobuki block diagram. The closest robot to CeCi in terms of peripherals is the Turtlebot 2 [ 59 ], so this robot package was used as a basis. The Turtlebot package integrates all the functionalities of the Kobuki package plus those of the packages linked to the drivers and functionalities of the 3D camera (openni2_camera package) and the lidar sensor (rplidar package). In addition, special function (navigation) is used, which can be found in the turtlebot package developed by Gaitech. The Figure 8illustrates the above. Figure 8. Turtlebot block diagram. Sensors 2022,22, 7619 16 of 19 Appendix A Figure A1. Total System Development Diagram. Sensors 2022,22, 7619 17 of 19 References 1. Wadho, W.; Chaudhry, A. Innovation and firm performance in developing countries: The case of Pakistani textile and apparel manufacturers. Res. Policy 2018,47, 1283–1294. [CrossRef] 2. Oppenheimer, A. ¡ Sálvese Quien Pueda!: El Futuro del Trabajo en la era de la Automatización; Penguin Random House Grupo Editorial: New York, NY, USA, 2018. 3. Villafuerte, J.; Intriago, E. Productive matrix change in Ecuador and the petroleum crisis. Case study: Entrepreneurs and productive associations. J. Bus. 2016,1, 1–11. [CrossRef] 4. Flores-Vázquez, C.; Bahon, C.A.; Icaza, D.; Cobos-Torres, J.C. Developing a socially-aware robot assistant for delivery tasks. In Proceedings of the International Conference on Applied Technologies, Quito, Ecuador, 3–5 December 2019; Springer: Cham, Switzerland, 2019; pp. 531–545. 5. Panceri, J.A.C.; Freitas, É.; de Souza, J.C.; da Luz Schreider, S.; Caldeira, E.; Bastos, T.F. A New Socially Assistive Robot with Integrated Serious Games for Therapies with Children with Autism Spectrum Disorder and Down Syndrome: A Pilot Study. Sensors 2021,21, 8414. [CrossRef] [PubMed] 6. Murphy, R.R.; Gandudi, V.B.M.; Adams, J. Applications of robots for COVID-19 response. arXiv 2020, arXiv:2008.06976. 7. Ramírez-Duque, A.A.; Aycardi, L.F.; Villa, A.; Munera, M.; Bastos, T.; Belpaeme, T.; Frizera-Neto, A.; Cifuentes, C.A. Collaborative and inclusive process with the autism community: A case study in Colombia about social robot design. Int. J. Soc. Robot. 2021 , 13, 153–167. [CrossRef] 8. Toscano, E.; Spitale, M.; Garzotto, F. Socially assistive robots in smart homes: Design factors that influence the user perception. In Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction, Sapporo Hokkaido, Japan, 7–10 March 2022; pp. 1075–1079. 9. Rácz, M.; Noboa, E.; Détár, B.; Nemes, Á.; Galambos, P.; Sz˝ucs, L.; Márton, G.; Eigner, G.; Haidegger, T. PlatypOUs—A Mobile Robot Platform and Demonstration Tool Supporting STEM Education. Sensors 2022,22, 2284. [CrossRef] 10. Huang, J.; Lau, T.; Cakmak, M. Design and evaluation of a rapid programming system for service robots. In Proceedings of the 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI), Christchurch, New Zealand, 7–10 March 2016; pp. 295–302. 11. Pransky, J. The pransky interview: Dr Steve cousins, CEO, savioke, entrepreneur and innovator. Ind. Robot. Int. J. 2016 ,43, 1–5. [CrossRef] 12. IEEE. Relay. 2022. Available online: https://robots.ieee.org/robots/relay/ (accessed on 14 September 2022). 13. Cousins, S. 5 Ways Relay Autonomous Delivery Robots Are So Cost-Effective. 2019. Available online: https://www.relayrobotics. com/ (accessed on 14 September 2022). 14. VirtualExpoGroup. MedicalExpo. 2020. Available online: https://www.medicalexpo.es/prod/vecna-technologies/product- 105903-697490.html (accessed on 14 September 2022). 15. ST Engineering Aethon, I. TUG Has Capabilities on Top of Capabilities. 2018. Available online: https://aethon.com/products/ (accessed on 14 September 2022). 16. Phoenix-Desing. Care-O-bot 4. 2015. Available online: https://www.care-o-bot.de/en/care-o-bot-4.html (accessed on 14 September 2022). 17. Temi USA Inc. Temi. 2022. Available online: https://www.robotemi.com/ (accessed on 14 September 2022). 18. RevistadeRobots.com. ROBOT THALON, EL NUEVO BOTONES DE TU HOTEL. 2021. Available online: https://revistaderobots. com/robots-y-robotica/robot-thalon-el-nuevo-botones-de-tu-hotel/ (accessed on 14 September 2022). 19. Keenon Robotics Co., Ltd. Dinerbot T8. 2020. Available online: https://www.keenonrobot.com/EN/index/Lists/index/catid/2. html (accessed on 14 September 2022). 20. Europe, S.R. Pepper. 2022. Available online: https://www.softbankrobotics.com/emea/es/pepper (accessed on 14 September 2022). 21. RobotLAB Inc. Robot NAO V6. 2022. Available online: https://www.robotlab.com/tienda-de-robots/robot-nao-para-la- educacion (accessed on 14 September 2022). 22. Chung, M.J.Y.; Huang, J.; Takayama, L.; Lau, T.; Cakmak, M. Iterative design of a system for programming socially interactive service robots. In Proceedings of the International Conference on Social Robotics, Kansas City, MO, USA, 1–3 November 2016; Springer: Cham, Switzerland, 2016; pp. 919–929. 23. Chung, M.J.Y.; Cakmak, M. “How was your stay?”: Exploring the use of robots for gathering customer feedback in the hospitality industry. In Proceedings of the 2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Nanjing, China, 27–31 August 2018; pp. 947–954. 24. Luo, J.M.; Vu, H.Q.; Li, G.; Law, R. Understanding service attributes of robot hotels: A sentiment analysis of customer online reviews. Int. J. Hosp. Manag. 2021,98, 103032. [CrossRef] 25. Kittmann, R.; Fröhlich, T.; Schäfer, J.; Reiser, U.; Weißhardt, F.; Haug, A. Let me Introduce Myself: I am Care-O-bot 4, a gentleman robot. In Mensch und Computer 2015—Proceedings; Diefenbach, S., Henze, N., Pielot, M., Eds.; De Gruyter Oldenbourg: Berlin, Germany, 2015; pp. 223–232. 26. IEEE. Care-O-Bot 4. 2022. Available online: https://robots.ieee.org/robots/careobot/ (accessed on 14 September 2022). 27. Hung, C.F.; Lin, Y.; Ciou, H.J.; Wang, W.Y.; Chiang, H.H. FoodTemi: The AI-oriented catering service robot. In Proceedings of the 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), IEEE, Penghu, Taiwan, 15–17 September 2021; pp. 1–2. Sensors 2022,22, 7619 18 of 19 28. Bogue, R. Robots in a contagious world. Ind. Robot. Int. J. Robot. Res. Appl. 2020,47, 642–673. [CrossRef] 29. Follmann, A.; Schollemann, F.; Arnolds, A.; Weismann, P.; Laurentius, T.; Rossaint, R.; Czaplik, M. Reducing loneliness in stationary geriatric care with robots and virtual encounters—A contribution to the COVID-19 pandemic. Int. J. Environ. Res. Public Health 2021,18, 4846. [CrossRef] 30. RobotLAB. TEMI. 2022. Available online: https://www.robotlab.com/store/temi (accessed on 14 September 2022). 31. Camila, P.M.L. Thalon, el Robot Colombiano que le Llevará la Comida a su Habitación. 2019. Available online: https://www. eltiempo.com/tecnosfera/dispositivos/thalon-el-robot-que-hace-el-servicio-de-habitacion-de-los-hoteles-360140 (accessed on 14 September 2022). 32. KEENON Robotics. DINERBOT-T8. 2020. Available online: https://www.keenonrobot.com/EN/index/Page/index/catid/32 .html (accessed on 14 September 2022). 33. ROBOTLAB Inc. Robot Pepper Para la Investigacion. 2022. Available online: https://www.robotlab.com/tienda-de-robots/ (accessed on 14 September 2022). 34. Cobo Hurtado, L.; Viñas, P.F.; Zalama, E.; Gómez-García-Bermejo, J.; Delgado, J.M.; Vielba García, B. Development and usability validation of a social robot platform for physical and cognitive stimulation in elder care facilities. Healthcare 2021 ,9, 1067. [CrossRef] [PubMed] 35. Ramis, S.; Buades, J.M.; Perales, F.J. Using a social robot to Evaluate facial expressions in the wild. Sensors 2020 ,20, 6716. [CrossRef] [PubMed] 36. Angulo, C.; Flores-Vázquez, C. Diseño ROBOT SOCIAL. Patent ECSDI22004944S, 31 January 2022. 37. ECUADOR, S. Patentes. 2022. Available online: https://patents.google.com/patent/ECSDI22004944S/es?oq=+ECSDI22004944S (accessed on 14 September 2022). 38. LE Inc. Robot Para Uso DoméStico. Patent DM/093 781, 1 December 2016. 39. LE Inc. Robot Para Uso doméstico. Patent DM/206 289, 20 June 2019. 40. Krägeloh, C.U.; Bharatharaj, J.; Sasthan Kutty, S.K.; Nirmala, P.R.; Huang, L. Questionnaires to measure acceptability of social robots: A critical review. Robotics 2019,8, 88. [CrossRef] 41. De Graaf, M.M.; Ben Allouch, S.; Van Dijk, J.A. Why would I use this in my home? A model of domestic social robot acceptance. Hum.-Comput. Interact. 2019,34, 115–173. [CrossRef] 42. Flores-Vázquez, C.; Aranda, J. Human activity recognition from object interaction in domestic scenarios. In Proceedings of the 2016 IEEE Ecuador Technical Chapters Meeting (ETCM), IEEE, Guayaquil, Ecuador, 12–14 October 2016; pp. 1–6. 43. Hellou, M.; Gasteiger, N.; Lim, J.Y.; Jang, M.; Ahn, H.S. Personalization and Localization in Human-Robot Interaction: A Review of Technical Methods. Robotics 2021,10, 120. [CrossRef] 44. Oliveira, R.; Arriaga, P.; Paiva, A. Human-robot interaction in groups: Methodological and research practices. Multimodal Technol. Interact. 2021,5, 59. [CrossRef] 45. Onyeulo, E.B.; Gandhi, V. What makes a social robot good at interacting with humans? Information 2020,11, 43. [CrossRef] 46. YUJINROBOT. YUJINROBOT. 2016. Available online: https://yujinrobot.com/ (accessed on 26 April 2022). 47. Hyun, E.J.; Kim, S.Y.; Jang, S.; Park, S. Comparative study of effects of language instruction program using intelligence robot and multimedia on linguistic ability of young children. In Proceedings of the RO-MAN 2008-The 17th IEEE International Symposium on Robot and Human Interactive Communication, IEEE, Munich, Germany, 1–3 August 2008; pp. 187–192. 48. Dekan, M.; Duchon, F.; Jurisica, L.; Vitko, A.; Babinec, A. iRobot create used in education. J. Mech. Eng. Autom. 2013 ,3, 197–202. 49. Zhao, H.; Wang, Z. Motion measurement using inertial sensors, ultrasonic sensors, and magnetometers with extended kalman filter for data fusion. IEEE Sens. J. 2011,12, 943–953. [CrossRef] 50. Robotnik Automation SLL. ROS Components. 2016. Available online: https://www.roscomponents.com/es/ (accessed on 30 March 2022). 51. Pietrzik, S.; Chandrasekaran, B. Setting up and Using ROS-Kinetic and Gazebo for Educational Robotic Projects and Learning. In Proceedings of the 2019 3rd International Conference on Control Engineering and Artificial Intelligence (CCEAI 2019), Los Angeles, CA, USA, 24–26 January 2019; Journal of Physics: Conference Series; IOP Publishing: Bristol, UK, 2019; Volume 1207, p. 012019. 52. Quigley, M.; Conley, K.; Gerkey, B.; Faust, J.; Foote, T.; Leibs, J.; Wheeler, R.; Ng, A.Y.; Berger, E. ROS: An open-source Robot Operating System. In Proceedings of the ICRA Workshop on Open Source Software, Kobe, Japan, 12–17 May 2009; Volume 3, p. 5. 53. Malavolta, I.; Lewis, G.A.; Schmerl, B.; Lago, P.; Garlan, D. Mining guidelines for architecting robotics software. J. Syst. Softw. 2021,178, 110969. [CrossRef] 54. Koubâa, A. Robot Operating System (ROS); Springer: Cham, Switzerland, 2017; Volume 1. 55. Priyandoko, G.; Wei, C.K.; Achmad, M.S.H. Human following on ros framework a mobile robot. Sinergi 2018 ,22, 77–82. [CrossRef] 56. Mishra, R.; Javed, A. ROS based service robot platform. In Proceedings of the 2018 4th International Conference on Control, Automation and Robotics (ICCAR), Auckland, New Zealand, 20–23 April 2018; pp. 55–59. [CrossRef] 57. Ponomarev, D.A.; Kuzmina, T.O.; Stotckaia, A.D. Real-time control system for a tracked robot. In Proceedings of the 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), St. Petersburg, Moscow, Russia, 27–30 January 2020; pp. 814–818. [CrossRef] 58. Stonier, D.; Ju, Y.; Simon, J.S.; Liebhardt, M. Kobuki. 2016. Available online: http://wiki.ros.org/kobuki (accessed on 10 May 2022). Sensors 2022,22, 7619 19 of 19 59. Melonee Wise, T.F. Specification for TurtleBot Compatible Platforms. 2011. Available online: https://www.ros.org/reps/rep-01 19.html (accessed on 26 April 2022). 60. Harik, E.H.C.; Korsaeth, A. Combining hector slam and artificial potential field for autonomous navigation inside a greenhouse. Robotics 2018,7, 22. [CrossRef] 61. Kohlbrecher, S.; Von Stryk, O.; Meyer, J.; Klingauf, U. A flexible and scalable SLAM system with full 3D motion estimation. In Proceedings of the 2011 IEEE International Symposium on Safety, Security, and Rescue Robotics, Kyoto, Japan, 1–5 November 2011; pp. 155–160. 62. Ahmad, N.; Ghazilla, R.A.R.; Khairi, N.M.; Kasi, V. Reviews on various inertial measurement unit (IMU) sensor applications. Int. J. Signal Process. Syst. (IJSPS) 2013,1, 256–262. [CrossRef] 63. Lucas, B.D.; Kanade, T. An iterative image registration technique with an application to stereo vision. In Proceedings of the 7th International Joint Conference on Artificial Inteligence (IJCAI), Vancouver, BC, Canada, 24–28 August 1981; Volume 81. 64. Särkkä, S.; Vehtari, A.; Lampinen, J. Rao-Blackwellized particle filter for multiple target tracking. Inf. Fusion 2007 ,8, 2–15. [CrossRef] 65. Grisetti, G.; Stachniss, C.; Burgard, W. Gmapping, A Highly Efficient Rao-Blackwellized Particle Filer to Learn Grid Maps From Laser Range Data. 2019. Available online: http://openslam.org/gmapping.html (accessed on 14 September 2022). 66. Grisetti, G.; Stachniss, C.; Burgard, W. Improved techniques for grid mapping with rao-blackwellized particle filters. IEEE Trans. Robot. 2007,23, 34–46. [CrossRef] 67. Krishna, P. Navigation 2. 2022. Available online: https://github.com/ros-planning/navigation2/tree/main/nav2_amcl (accessed on 13 May 2022). 68. Fox, D.; Burgard, W.; Dellaert, F.; Thrun, S. Monte carlo localization: Efficient position estimation for mobile robots. In Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), Orlando, FL, USA, 18–22 July 1999; pp. 5–7. 69. Fox, D. KLD-sampling: Adaptive particle filters. In Proceedings of the Advances in Neural Information Processing Systems 14 (NIPS 2001) 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, Vancouver, BC, Canada, 3–8 December 2001; Volume 14. 70. Mens, T.; Wermelinger, M. Separation of concerns for software evolution. J. Softw. Maint. Evol. Res. Pract. 2002 ,14, 311–315. [CrossRef] 71. Gaitech. Gaitech EDU. 2016. Available online: http://edu.gaitech.hk/turtlebot/turtlebot-tutorials.html (accessed on 26 April 2022). 72. Foote, T. tf: The transform library. In Proceedings of the Technologies for Practical Robot Applications (TePRA), 2013 IEEE International Conference, Woburn, MA, USA, 22–23 April 2013; Open-Source Software Workshop; pp. 1–6. 73. Abdelrasoul, Y.; Saman, A.B.S.H.; Sebastian, P. A quantitative study of tuning ROS gmapping parameters and their effect on performing indoor 2D SLAM. In Proceedings of the 2016 2nd IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), Ipoh, Malaysia, 25–27 September 2016; pp. 1–6. 74. Gerkey, B. Gmapping. 2019. Available online: http://wiki.ros.org/gmapping (accessed on 5 March 2022). 75. Ortega, C.A.D.L.; Romo, J.C.M.; González, M.M. Reconocimiento de voz con redes neuronales, DTW y modelos ocultos de Markov. Concienc. Tecnol. 2006, 5. 76. Lamere, P.; Kwok, P.; Gouvea, E.; Raj, B.; Singh, R.; Walker, W.; Warmuth, M.; Wolf, P. The CMU SPHINX-4 speech recognition system. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2003), Hong Kong, China, 6–10 April 2003; Volume 1, pp. 2–5. 77. Mena, C.D.H.; Camacho, A.H. Ciempiess: A new open-sourced mexican spanish radio corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), Reykjavik, Iceland, 26–31 May 2014; pp. 371–375. 78. Open Source Robotics Foundation, I. Kobuki’s Control System. 2016. Available online: http://wiki.ros.org/kobuki/Tutorials/ KobukiControlSystem (accessed on 26 April 2022). 79. Amazon.com, Inc. 1996. Available online: https://www.amazon.com/ (accessed on 24 May 2022). 80. Herrera-Franco, G.; Montalván-Burbano, N.; Mora-Frank, C.; Bravo-Montero, L. Scientific research in Ecuador: A bibliometric analysis. Publications 2021,9, 55. [CrossRef]