Towards Empathetic Human-Robot Interactions

📝 Abstract

Since the late 1990s when speech companies began providing their customer-service software in the market, people have gotten used to speaking to machines. As people interact more often with voice and gesture controlled machines, they expect the machines to recognize different emotions, and understand other high level communication features such as humor, sarcasm and intention. In order to make such communication possible, the machines need an empathy module in them which can extract emotions from human speech and behavior and can decide the correct response of the robot. Although research on empathetic robots is still in the early stage, we described our approach using signal processing techniques, sentiment analysis and machine learning algorithms to make robots that can “understand” human emotion. We propose Zara the Supergirl as a prototype system of empathetic robots. It is a software based virtual android, with an animated cartoon character to present itself on the screen. She will get “smarter” and more empathetic through its deep learning algorithms, and by gathering more data and learning from it. In this paper, we present our work so far in the areas of deep learning of emotion and sentiment recognition, as well as humor recognition. We hope to explore the future direction of android development and how it can help improve people’s lives.

💡 Analysis

Since the late 1990s when speech companies began providing their customer-service software in the market, people have gotten used to speaking to machines. As people interact more often with voice and gesture controlled machines, they expect the machines to recognize different emotions, and understand other high level communication features such as humor, sarcasm and intention. In order to make such communication possible, the machines need an empathy module in them which can extract emotions from human speech and behavior and can decide the correct response of the robot. Although research on empathetic robots is still in the early stage, we described our approach using signal processing techniques, sentiment analysis and machine learning algorithms to make robots that can “understand” human emotion. We propose Zara the Supergirl as a prototype system of empathetic robots. It is a software based virtual android, with an animated cartoon character to present itself on the screen. She will get “smarter” and more empathetic through its deep learning algorithms, and by gathering more data and learning from it. In this paper, we present our work so far in the areas of deep learning of emotion and sentiment recognition, as well as humor recognition. We hope to explore the future direction of android development and how it can help improve people’s lives.

📄 Content

Towards Empathetic Human-Robot Interactions Pascale Fung, Dario Bertero, Yan Wan, Anik Dey, Ricky Ho Yin Chan, Farhad Bin Siddique, Yang Yang, Chien-Sheng Wu, Ruixi Lin Human Language Technology Center Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay, Hong Kong
pascale@ece.ust.hk Abstract. Since the late 1990s when speech companies began providing their cus- tomer-service software in the market, people have gotten used to speaking to ma- chines. As people interact more often with voice and gesture controlled machines, they expect the machines to recognize different emotions, and understand other high level communication features such as humor, sarcasm and intention. In order to make such communication possible, the machines need an empathy module in them, which is a software system that can extract emotions from human speech and behavior and can decide the correct response of the robot. Although research on empathetic robots is still in the primary stage, current methods involve using signal processing tech- niques, sentiment analysis and machine learning algorithms to make robots that can ’understand’ human emotion. Other aspects of human-robot interaction include facial expression and gesture recognition, as well as robot movement to convey emotion and intent. We propose Zara the Supergirl as a prototype system of empathetic robots. It is a software-based virtual android, with an animated cartoon character to present itself on the screen. She will get ’smarter’ and more empathetic, by having machine learn- ing algorithms, and gathering more data and learning from it. In this paper, we present our work so far in the areas of deep learning of emotion and sentiment recognition, as well as humor recognition. We hope to explore the future direction of android devel- opment and how it can help improve people’s lives. 1 Introduction From science fiction films to novels, humans have always fantasized – or needed – to have an emotional relationship with intelligent machines.
Many people in the society seem to think that the objective of creating intelligent machines is to “imitate humans” or create a new species of “humans”. This misunder- standing has led to the irrational fear of “machines taking over humans” by some people. Their reasoning is obvious – if intelligent machines are supposed to imitate humans then as they become more and more human-like they are bound to have hu- manly desire for power and dominance. It is obvious if one believes in the premises that we are creating machines to “imitate humans”. However, this is far from the re- ality of artificial intelligence research. Rather than trying to build some Frankenstein surrogate of the human race, the ob- jective of intelligent machine research and development has always been to help hu- mans. As such, even when we build robot “companions” we are working to create health benefits for the elderly or educational benefits for the young.
In the past couple of decades, interactive dialog systems have been designed as software programs either for the desktop, embedded in an enterprise solution, as cloud services, or as mobile applications. They would have a synthesized voice. Since the 1990s, voice interactive designers have tried to make the dialog prompts more natural, and speech synthesis has made great progress to enable computer voice to sound hu- man like. However, such systems remain invisible and virtual. Even after giving these applications names like Siri or Cortana, users remain emotionally indifferent to such systems as if they are merely using an ATM machine for transactions.
One reason behind this might be something that has been studied by human-robot interaction researchers [39]. It is known that physical embodiment of an intelligent system, whether in virtual simulation or in a robotic form, is important for users to feel related and empathize with the system [34].
More importantly though, physical robots, even extremely humanlike androids, seem cold and distant to humans because while they can sometimes be built to look and even sound emotional, they do not recognize or respond to human emotions and intent. Roboticists make great efforts to build robots in anthropomorphic form so that humans can empathize with them [22], and to have embodied cognition [10]. only to find human users disappointed by the lack of reciprocal empathy from these robots.
It follows that we shall embody interactive dialog systems in simulated or robotic forms. It is also important that we give such systems the ability to both recognize human emotions and intent, as well as expressing its own. Before we share our lives with robots, they need to be able to recognize human emotion and intent, through natural language communications, through facial expression and gesture communica- tions.
In this paper, we describe a proposed framework for

This content is AI-processed based on ArXiv data.