Han, HasanKaradeniz, OğuzcanDalyan, TuğbaSönmez, Elena BattiniSarıoğlu, Baykal2023-09-142023-09-142023-05-252326-005X1079-8587https://hdl.handle.net/11411/5180https://doi.org/10.32604/iasc.2023.030674Robot companions will soon be part of our everyday life and students in the engineering faculty must be trained to design, build, and interact with them. The two affordable robots presented in this paper have been designed and constructed by two undergraduate students; one artifi-cial agent is based on the Nvidia Jetson Nano development board and the other one on a remote computer system. Moreover, the robots have been refined with an empathetic system, to make them more user-friendly. Since automatic facial expression recognition skills is a necessary pre-processing step for acknowledging emotions, this paper tested different variations of Convolutional Neural Networks (CNN) to detect the six facial expressions plus the neutral face. The state-of-the-art performance of 75.1% on the Facial Expression Recognition (FER) 2013 database has been reached by the ensemble voting method. The runner-up model is the Visual Geometry Group (VGG) 16 which has been adopted by the two robots to recognize the expressions of the human partner and behave accordingly. An empirical study run among 55 university students confirmed the hypothesis that contact with empathetic artificial agents contributes to increasing the acceptance rate of robotseninfo:eu-repo/semantics/openAccessCHALLENGESArtificial intelligencedeep learningconvolutional neural networksfacial expression recognitionroboticseducationprofessional learningArticle2-s2.0-8516328060810.32604/iasc.2023.030674Q3WOS:000992836700035