Alle Publikationen
- <<
- <
- 1
2019
-
(2019): On Proactive, Transparent, and Verifiable Ethical Reasoning for Robots. In: Proceedings of the IEEE 107 (3), S. 541-561. DOI: 10.1109/JPROC.2019.2898267
DOI: https://doi.org/10.1109/JPROC.2019.2898267 Abstract: Previous work on ethical machine reasoning has largely been theoretical, and where such systems have been implemented, it has, in general, been only initial proofs of principle. Here, we address the question of desirable attributes for such systems to improve their real world utility, and how controllers with these attributes might be implemented. We propose that ethically critical machine reasoning should be proactive, transparent, and verifiable. We describe an architecture where the ethical reasoning is handled by a separate layer, augmenting a typical layered control architecture, ethically moderating the robot actions. It makes use of a simulation-based internal model and supports proactive, transparent, and verifiable ethical reasoning. To do so, the reasoning component of the ethical layer uses our Python-based belief-desire-intention (BDI) implementation. The declarative logic structure of BDI facilitates both transparency, through logging of the reasoning cycle, and formal verification methods. To prove the principles of our approach, we use a case study implementation to experimentally demonstrate its operation. Importantly, it is the first such robot controller where the ethical machine reasoning has been formally verified.
Keywords: BDI implementation, belief desire intention implementation, control engineering computing, Design methodology, ethical machine reasoning, ethical reasoning, Ethics, formal verification, ieee xplore, intelligent robots, layered control architecture, learning (artificial intelligence), machine learning, Moral & Ethik, Predictive models, Python, robot controller, robot programming, Robots, safety, simulation-based internal model, Social implications of technology, software architecture, transparency -
(2019) : Beyond Programming: Can Robots’ Norm-Violating Actions Elicit Mental State Attributions?: 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI): Daegu, Korea: IEEE, S. 530-531
DOI: https://doi.org/10.1109/HRI.2019.8673293 Abstract: Social perceivers often view a human agent’s norm-violating behavior as diagnostic of that person’s mental states, while behaviors that conform to norms are viewed as less informative. We developed a series of stimulus videos depicting a DRC-HUBO robot engaging in norm-violating and norm-conforming behaviors. We explored the hypothesis that robots’ norm-violating actions may invite social perceivers to increase their mental state attributions in a similar manner as they do in humans. Surprisingly, we found that norm-conforming behaviors appear to be at least as conducive as norm-violating behaviors, and perhaps even moreso, to mental state attribution to robotic agents.
Keywords: action explanation, actions elicit mental state attributions, agency, Artificial intelligence, behavioural sciences computing, Cognition, control engineering computing, DRC-HUBO, DRC-HUBO robot, human agent norm-violating behavior, Humanoid Robots, human-robot interaction, ieee xplore, Künstliche Intelligenz, Mobile robots, multi-agent systems, norms, PSYCHOLOGY, robot programming, robotic agents, social perceivers, theory of mind, Videos 2018
-
(2018) : Artificial Empathy in Social Robots: An analysis of Emotions in Speech: 2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN): Nanjing, China: IEEE Robotics & Automation Society, S. 632-637
DOI: https://doi.org/10.1109/ROMAN.2018.8525652 Abstract: Artificial speech developed using speech synthesizers has been used as the voice for robots in Human Robot Interaction (HRI). As humans anthropomorphize robots, an empathetically interacting robot is expected to increase the level of acceptance of social robots. Here, a human perception experiment evaluates whether human subjects perceive empathy in robot speech. For this experiment, empathy is expressed only by adding appropriate emotions to the words in speech. Also, humans’ preferences for a robot interacting with empathetic speech versus a standard robotic voice are also assessed. The results show that humans are able to perceive empathy and emotions in robot speech, and prefer it over the standard robotic voice. It is important for the emotions in empathetic speech to be consistent with the language content of what is being said, and with the human users’ emotional state. Analyzing emotions in empathetic speech using valence-arousal model has revealed the importance of secondary emotions in developing empathetically speaking social robots.
Keywords: Angemessen(heit) (von Technik), Anthropomorphism, appropriate emotions, artificial empathy, artificial speech, control engineering computing, emotion recognition, empathetic speech, empathetically interacting robot, human perception experiment, Human robot interaction, human subjects, human users, human-robot interaction, Humans, ieee xplore, Medical services, robot interacting, Robot sensing systems, robot speech, Robots, service robot, social robots, speech synthesis, speech synthesizers, standard robotic voice, standards, Task Analysis -
(2018) : Ethical and Social Considerations for the Introduction of Human-Centered Technologies at Work: 2018 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO): Genoa, Italy: IEEE Robotics & Automation Society, S. 131-138
DOI: https://doi.org/10.1109/ARSO.2018.8625830 Abstract: Human-centered technologies such as collaborative robots, exoskeletons, and wearable sensors are rapidly spreading in industry and manufacturing because of their intrinsic potential at assisting workers and improving their working conditions. The deployment of these technologies, albeit inevitable, poses several ethical and societal issues. Guidelines for ethically aligned design of autonomous and intelligent systems do exist, however we argue that ethical recommendations must necessarily be complemented by an analysis of the social impact of these technologies. In this paper, we report on our preliminary studies on the opinion of factory workers and of people outside this environment on human-centered technologies at work. In light of these studies, we discuss ethical and social considerations for deploying these technologies in a way that improves acceptance.
Keywords: Collaboration, collaborative robots, control engineering computing, ethical aspects, ethical considerations, ethical issues, ethical recommendations, ethically aligned design, exoskeletons, Human Computer Interaction, Human Factors, human-centered technologies, human-robot interaction, ieee xplore, Interviews, knowledge based systems, Moral & Ethik, Production facilities, Robot sensing systems, social aspects of automation, social considerations, societal issues, user centred design, wearable sensors, working conditions -
(2018) : From social interaction to ethical AI: a developmental roadmap: 2018 Joint IEEE 8th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob): Tokyo, Japan: IEEE, S. 204-211
DOI: https://doi.org/10.1109/DEVLRN.2018.8761023 Abstract: AI and robot ethics have recently gained a lot of attention because adaptive machines are increasingly involved in ethically sensitive scenarios and cause incidents of public outcry. Much of the debate has been focused on achieving highest moral standards in handling ethical dilemmas on which not even humans can agree, which indicates that the wrong questions are being asked. We suggest to address this ethics debate strictly through the lens of what behavior seems socially acceptable, rather than idealistically ethical. Learning such behavior puts the debate into the very heart of developmental robotics. This paper poses a roadmap of computational and experimental questions to address the development of socially acceptable machines. We emphasize the need for social reward mechanisms and learning architectures that integrate these while reaching beyond limitations of plain reinforcement-learning agents. We suggest to use the metaphor of “needs” to bridge rewards and higher level abstractions such as goals for both communication and action generation in a social context. We then suggest a series of experimental questions and possible platforms and paradigms to guide future research in the area.
Keywords: adaptive machines, Artificial intelligence, control engineering computing, Decision Making, developmental roadmap, developmental robotics, ethical AI, ethical aspects, ethically sensitive scenarios, Ethics, Face, ieee xplore, Künstliche Intelligenz, learning (artificial intelligence), plain reinforcement-learning agents, Robot Ethics, robot programming, Robot sensing systems, social interaction, social reward mechanisms, socially acceptable machines, standards 2017
-
(2017) : Cross-cultural differences for adaptive strategies of robots in public spaces: 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN): Lisbon, Portugal: IEEE Robotics & Automation Society, S. 573-578
DOI: https://doi.org/10.1109/ROMAN.2017.8172360 Abstract: Robots deployed in public spaces must necessarily deal with situations that demand them to engage humans in a socially and culturally appropriate manner. However, social environments are often complex and ambiguous: many queries to the robot are collaborative (e.g. a family), and in case of conflicting queries, social robots need to participate in value decisions and negotiating multi-party interactions. Given the strong influence of the people’s demographic information and social schema among people, such as relationships and hierarchies, the focus of this research is to examine whether and how people exhibit socio-psychological effects with a shared robot deployed at international events or spaces (e.g. airports). With the aim to investigate who robots should adapt to (children or adults) in multi-party situations within human-robot interactions in public spaces and whether this adaptation can be influenced by culture, this paper presents a cross-cultural study conducted online. The results include a number of interesting findings based on people’s relationship with a child and their parental status. In addition, a number of cross-cultural differences were identified in respondents’ attitude towards robot’s multi-party adaptation in various public settings.
Keywords: Airports, Angemessen(heit) (von Technik), control engineering computing, cross-cultural differences, cultural aspects, Cultural differences, Face recognition, Foot, human-robot interaction, human-robot interactions, ieee xplore, multiparty adaptation, PSYCHOLOGY, public spaces, Robots, social robots, socio-psychological effects, speech, Videos -
(2017) : Acquiring social interaction behaviours for telepresence robots via deep learning from demonstration: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Vancouver, British Columbia, Canada: IEEE, S. 37-42
DOI: https://doi.org/10.1109/IROS.2017.8202135 Abstract: As robots begin to inhabit public and social spaces, it is increasingly important to ensure that they behave in a socially appropriate way. However, manually coding social behaviours is prohibitively difficult since social norms are hard to quantify. Therefore, learning from demonstration (LfD), wherein control policies are inferred from demonstrations of correct behaviour, is a powerful tool for helping robots acquire social intelligence. In this paper, we propose a deep learning approach to learning social behaviours from demonstration. We apply this method to two challenging social tasks for a semi-autonomous telepresence robot. Our results show that our approach outperforms gradient boosting regression and performs well against a hard-coded controller. Furthermore, ablation experiments confirm that each element of our method is essential to its success.
Keywords: ablation experiments, challenging social tasks, Cloning, control engineering computing, correct behaviour, deep learning approach, deep learning from demonstration, gradient boosting regression, gradient methods, hard-coded controller, human-robot interaction, ieee xplore, Künstliche Intelligenz, learning (artificial intelligence), LfD, machine learning, public spaces, Regression Analysis, Robot sensing systems, semiautonomous telepresence robot, social behaviour, Social intelligence, social interaction behaviours, Social Norms, social spaces, telepresence robots 2016
-
(2016): Bridging the Ethical Gap: From Human Principles to Robot Instructions. In: IEEE Intelligent Systems 31 (5), S. 76-82. DOI: 10.1109/MIS.2016.87
DOI: https://doi.org/10.1109/MIS.2016.87 Abstract: Asimov’s three laws of robotics and the Murphy-Woods alternative laws assume that a robot has the cognitive ability to make moral decisions, and fail to escape the myth of self-sufficiency. But ethical decision making on the part of robots in human-robot interaction is grounded on the interdependence of human and machine. Furthermore, the proposed laws are high-level principles that cannot easily be translated into machine instructions because there is an immense gap between the architecture, implementation, and activity of humans and robots in addressing ethical situations. The characterization of the ethical gap, particularly with reference to the Murphy-Woods laws, leads to a proposal for a shift in focus away from the autonomous behavior of the robot to human-robot communication at the interface, and the development of interdependence rules to underpin the process of ethical decision-making.
Keywords: autonomous behavior, cognitive ability, Context modeling, control engineering computing, ethical decision making, ethical gap, ethical interdependence, Ethics, human principle, human-robot interaction, human-robot interface, ieee xplore, Intelligent Systems, Law, laws of robotics, Moral & Ethik, Murphy-Woods alternative laws, Robot Ethics, robot instruction, Robot kinematics, Robot sensing systems, Robotics, standards 2014
-
(2014) : Sympathy expression model for the bystander robot in group communication: 2014 International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM): Puerto Princesa, Philippines: IEEE, S. 1-6
DOI: https://doi.org/10.1109/HNICEM.2014.7016192 Abstract: In this paper, we propose a sympathy expression model for a bystander robot that honors the concept of moral emotion. Therefore, we pay attention to the robot that is in a bystander position, which is unrelated to the communication between participants. We propose a sympathy expression model that lets a bystander robot learn the emotional display of others and enables cooperative expressiveness. This model allows the appropriate expressiveness affecting communication of a robot in the position of a bystander. To test it, we assume the interaction of three robots with the emotion generation model using the neural network. Further, we inspect the movement of this model by using a psychology model. As a result, we confirmed the appropriate actions of this model.
Keywords: bystander robot, control engineering computing, emotion generation model, Ethics, group communication, Humanoid Robots, ieee xplore, Moral & Ethik, moral emotion, neural nets, neural network, Observers, PSYCHOLOGY, psychology model, Robot kinematics, Robot sensing systems, Sympathy, sympathy expression model, Vectors 2008
-
(2008) : Typification-based ethics for artificial agents: 2008 2nd IEEE International Conference on Digital Ecosystems and Technologies: Phitsanulok, Thailand: IEEE, S. 482-491
DOI: https://doi.org/10.1109/DEST.2008.4635149 Abstract: A digital ecosystem has to deal with the notion of responsibility with respect to some of its entities, including artefacts. Autonomous artificial agents have given rise to the study of the possibility that these agents have ethical aspects. This paper introduces a conceptual framework for ethical situations that involve artificial agents such as robots. Specifically, we focus on how ethical rules should be applied in reference to artificial agents in order for them to act correctly when facing ethical situations. We typify these situations in order to facilitate ethical evaluations. This typification involves classifications of ethical agents and patients according to whether they are human beings, human-based organizations, or non-human beings, and in reference to ethical evaluations of each of these entities. The resultant methodology is applied to Asimovpsilas ldquoLaws of Robotics.
Keywords: Artificial agent, artificial agents, Asimov’s Laws, Biological system modeling, control engineering computing, digital ecosystem, Ecosystems, ethical agent, ethical aspect, ethical aspects, ethical evaluation, ethical rule, Ethics, Humans, ieee xplore, Moral & Ethik, ORGANIZATIONS, Robot, Robot sensing systems, Robots, Software agents, typification-based ethics
- <<
- <
- 1