Forutseende og intuitiv robotmedhjelper (PIRC)

• van Otterdijk, Marieke; Laeng, Bruno; Saplacan, Diana & Tørresen, Jim (2024). The Effect of Expressive Robot Behavior on Users’ Mental Effort: A Pupillometry Study. IEEE Transactions on Cognitive and Developmental Systems. ISSN 2379-8920. 16(2), s. 474–484. doi: 10.1109/TCDS.2024.3352893. Vis sammendrag

  Robots are becoming part of our social landscape. Social interaction with humans must be efficient and intuitive to understand because nonverbal cues make social interactions between humans and robots more efficient. This study measures mental effort to investigate factors influencing the intuitive understanding of expressive nonverbal robot motions. Using an eye tracker to measure pupil response and gaze, fifty participants were asked to watch eighteen short video clips featuring three different types of robots performing expressive robot behaviors. Our findings indicate that the appearance of the robot, the viewing angle, and the expression shown by the robot all influence the cognitive load. Therefore, they may affect the intuitive understanding of expressive robot behavior. Furthermore, we found differences in the fixation time for different features of the various robots. With these insights, we identified possible improvement directions for making interactions between humans and robots more efficient and intuitive.

• van Otterdijk, Marieke; Saplacan, Diana; Laeng, Bruno & Tørresen, Jim (2024). An Exploratory Study on People's Intuitive Understanding of Expressive Robot Behavior. ACM/IEEE International Conference on Human-Robot Interaction (HRI). ISSN 2167-2121. s. 1072–1076. doi: 10.1145/3610978.3640568. Vis sammendrag

  Robots are anticipated to communicate with humans in our social context. Using nonverbal communication by robots increases communication comprehension because humans intuitively understand such behavior due to their experience of human-human interaction. Thus, this behavior is suitable for studying what makes robot motion intuitive to understand in human-robot interaction (HRI). We study how robot features help humans intuitively grasp expressive robot gestures, concentrating on what makes behavior easy to interpret. After watching eighteen nine-second videos of three robot kinds demonstrating expressive robot actions, 50 participants completed an open-ended survey. Our findings highlight the inputs, mediating factors, and outputs that users reported based on observing examples of expressive robot behavior. These insights are a starting point for analyzing robot behavior from the perspective of intuition and provide a foundation for a theoretical framework for intuition in HRI.

• Kwak, Dongho; Baselizadeh, Adel; van Otterdijk, Marieke; Saplacan, Diana & Tørresen, Jim (2024). "Noisy" Matching of Motion Velocity of an Assistive Robot to the Users' Walking Velocity. ACM/IEEE International Conference on Human-Robot Interaction (HRI). ISSN 2167-2121. doi: 10.1145/3610978.3640546. Vis sammendrag

  This study investigates the impact of dynamic matching of robot motion velocity to users' walking velocity in a human-robot approach scenario on three categories: perceived comfort, interactivity, and naturalness. Considering age diversity, participants were divided into two age groups. Young participants tended to rate higher for all three categories when the robot's approaching velocity was dynamically matched. In contrast, elderly participants preferred a steady and slow robot approach for comfort and predictability. These findings contribute to the ongoing effort to design assistive robots that effectively cater to diverse user groups, ultimately enhancing user satisfaction and acceptance. Taken together, this study highlights the importance of dynamically tailoring robot behaviors based on user demographics for positive Human-Robot Interactions.

• Saplacan, Diana; van Otterdijk, Marieke & Tørresen, Jim (2024). Qualitative Observational Video-Based Study on Perceived Privacy in Social Robots’ Based on Robots Appearances. Advanced Robotics and its Social Impacts (ARSO). ISSN 2162-7568. doi: 10.1109/ARSO60199.2024.10557941. Fulltekst i vitenarkiv Vis sammendrag

  Privacy has recently got attention, especially since the introduction of the General Data Protection Regulation (GDPR) in Europe, the new Artificial Intelligence Act (AIA) and the new Machinery Regulation. Privacy can be defined as someone’s right to keep personal matters, including personal life, personal information, or relationships, to themselves. A social robot’s appearance (=the combination of embodiment and motion) may contribute to how human users perceive them, including how these robots are perceived in relation to privacy. If these robots are part of certain services such as home- or healthcare, these may also have consequences on how these services are perceived. This study aims at showcasing the users’ perception of privacy based on the perceived robot’s appearance. Three social robots were chosen for this purpose: PLEO (with a zoomorphic appearance), Pepper (with a childlike anthropomorphic appearance), and TIAGo (with a mechanical and asymmetrical appearance). The data was collected through an in-lab observational video-based study from 50 participants with very limited- or no experience with robots. Our findings show that PLEO was perceived as preserving most of the users' privacy, while Pepper was perceived as more privacy-invasive than PLEO but less than TIAGo. TIAGo was perceived as hard to interpret in terms of privacy. Our findings also point out that designing robots with a cute appearance, such as PLEO, may contribute to participants trusting the robot more and thus being willing to share their data. The paper provides a list of characteristics that participants associated with a social robot as preserving or not their privacy. Further, the paper discusses the appearance of these social robots in terms of “cuteness” as a dark pattern in the design of social robots that may lead to data myopia, but also the possible consequences this may have, for vulnerable users, while trying to design more inclusive robots.

• Hemaz, Said; Thorsen, Ola; Esema, Emmanuel; Ellefsen, Kai Olav; Herrebrøden, Henrik & von Arnim, Hugh Alexander [Vis alle 7 forfattere av denne artikkelen] (2024). Can machine learning help reveal the competitive advantage of elite beach volleyball players? . I Westphal, Florian; Peretz-Andersson, Einav; Riveiro, Maria; Bach, Kerstin & Heintz, Fredrik (Red.), 14th Scandinavian Conference on Artificial Intelligence - SCAI 2024. Swedish Artificial Intelligence Society. ISSN 978-91-8075-709-6. s. 57–66. doi: https:/doi.org/10.3384/ecp208007. Vis sammendrag

  As the world of competitive sports increasingly embraces data-driven techniques, our research explores the potential of machine learning in distinguishing elite from semi-elite beach volleyball players. This study is motivated by the need to understand the subtle yet crucial differences in player movements that contribute to high-level performance in beach volleyball. Utilizing advanced machine learning techniques, we analyzed specific movement patterns of the motion of the torso during spikes, captured through vest-mounted accelerometers. Our approach offers novel insights into the nuanced dynamics of elite play, revealing that certain movement patterns are distinctly characteristic of higher skill levels. One of our key contributions is the ability to classify spiking movements at different skill levels with an accuracy rate as high as 87%. This current research provides a foundation of what separates elite players from their semi-elite counterparts.

• Baselizadeh, Adel; Khaksar, Weria; Uddin, Md Zia; Saplacan, Diana & Tørresen, Jim (2023). Privacy-Preserving User Pose Prediction for Safe and Efficient Human-Robot Interaction, Proceedings of the 2023 19th IEEE International Conference on Automation Science and Engineering (CASE) . IEEE conference proceedings. ISSN 979-8-3503-2070-1. doi: 10.1109/CASE56687.2023.10260298. Fulltekst i vitenarkiv
• Tørresen, Jim; Saplacan, Diana; Baselizadeh, Adel & Mahler, Tobias (2023). Machine Excellence Tradeoffs to Ethical and Legal Perspectives, Proceedings of the 2023 IEEE Conference on Artificial Intelligence (IEEE CAI). IEEE conference proceedings. ISSN 979-8-3503-3984-0. s. 237–240. doi: 10.1109/CAI54212.2023.00109. Fulltekst i vitenarkiv Vis sammendrag

  Abstract—We appreciate well-functioning technology being able to also personalize its services. However, to protect privacy and avoid a potential misuse of personal data, we are encouraged to limit the amount of personal data we share through apps and Internet services. While some services do not really need all the data they ask us to provide, others depend on it to provide the best possible performance of its service. That regards systems that apply data in machine learning for tasks like medical diagnostics. Especially deep learning algorithms perform better by using a large amount of data and are now able to benefit from the large amount as well with limited training time given access to high-performance computing resources. This paper address and discuss the tradeoffs like the one we have between data sharing minimalization for increased privacy and data maximization for machine learning systems. Perspectives related to ethics, legal, and social issues are considered in the paper. There is no single conclusion on the challenge, but attention to it can increase the awareness that the best balance differs depending on the application addressed.

• van Otterdijk, Marieke; Saplacan, Diana; Baselizadeh, Adel; Laeng, Bruno & Tørresen, Jim (2023). To Shake or Not to Shake: Intuitive Reactions of Senior Adults to a Robot Handshake in a Western Culture, Proceedings of the 32nd IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) 2023. IEEE conference proceedings. ISSN 979-8-3503-3671-9. s. 890–896. doi: 10.1109/RO-MAN57019.2023.10309608. Fulltekst i vitenarkiv
• Strømmen, Knut Joar; Tørresen, Jim & Côté-Allard, Ulysse Teller Masao (2023). Latent space unsupervised semantic segmentation. Frontiers in Physiology. ISSN 1664-042X. 14. doi: 10.3389/fphys.2023.1151312.
• Saplacan, Diana; Schulz, Trenton; Tørresen, Jim & Pajalic, Zada (2023). Health Professionals’ Views on the Use of Social Robots with Vulnerable Users: A Scenario-Based Qualitative Study Using Story Dialogue Method , Proceedings of the 32nd IEEE International Conference on Robot & Human Interactive Communication (RO-MAN) 2023. IEEE conference proceedings. ISSN 979-8-3503-3671-9. s. 421–428. doi: 10.1109/RO-MAN57019.2023.10309644. Fulltekst i vitenarkiv Vis sammendrag

  We used the story dialog method (SDM) to gather the viewpoints of health professionals about the use of social ro-bots in the home and healthcare services with vulnerable users. SDM consists of participants bringing stories that are discussed together. The aim of the study was to address universal design and accessibility issues with robots in specific use situations. Three social robots were used for this purpose in four stories: TIAGo, Romibo and robot companions. SDM method was used in two workshops with eight participants (33 invited, 12 re-cruited, and 8 participated in the end). The participants uncov-ered issues regarding ethics, responsibility, use of data, infra-structure, design, and user concerns based on provided stories and own experiences. These issues provide important aspects that should be considered when using robots with vulnerable us-ers and ensuring that a robot is usable by as many people as pos-sible. The main contribution of the paper is introducing the SDM method to Human-Robot Interaction community, as well as find-ings around universal design and accessibility of robots, in order to create more inclusive social robots.

• Tariverdi, Abbas; Côté-Allard, Ulysse Teller Masao; Mathiassen, Kim; Elle, Ole Jakob; Kalvøy, Håvard & Martinsen, Ørjan Grøttem (2023). Reinforcement Learning-Based Switching Controller for a Milliscale Robot in a Constrained Environment. IEEE Transactions on Automation Science and Engineering. ISSN 1545-5955. 21(2), s. 2000–2016. doi: 10.1109/TASE.2023.3259905.
• Strand, Ørjan; Reilstad, Didrik Spanne; Wu, Zhenying; Castro da Silva, Bruno; Tørresen, Jim & Ellefsen, Kai Olav (2023). RADAR: Reactive and Deliberative Adaptive Reasoning - Learning When to Think Fast and When to Think Slow, 2022 IEEE International Conference on Development and Learning (ICDL). IEEE conference proceedings. ISSN 9781665413121. s. 184–189. doi: 10.1109/ICDL53763.2022.9962202. Vis sammendrag

  When designing and deploying Reinforcement Learning (RL) algorithms, one typically selects a single value for the discount rate, which results in an agent that will always be equally reactive or deliberative. However, similarly to humans, RL agents can benefit from adapting their planning horizon to the current context. To enable this, we propose a novel algorithm: RADAR: Reactive and Deliberate Adaptive Reasoning. RADAR enables an agent to learn to adaptively choose a level of deliberation and reactivity according to the state it is in, given that there are cases where one mode of operation is better than the other. Through experiments in a grid world, we verify that the RADAR agent has the capability to adapt its reasoning modality to the current context. In addition, we observe that the RADAR agent exhibits different preferences regarding its thinking modes when a penalty for mental effort is included in its mathematical formulation.

• Noori, Farzan Majeed; Hafeez, Azeem; Malik, Hafiz; Uddin, Md Zia & Tørresen, Jim (2023). Source Linking Framework in Vehicular Networks for Security of Electric Vehicles using Machine Learning. I Coleri, Sinem; Altintas, Onur & Kargl, Frank (Red.), 2023 IEEE Vehicular Networking Conference (VNC) proceedings. IEEE conference proceedings. ISSN 979-8-3503-3549-1. s. 207–214. doi: 10.1109/VNC57357.2023.10136272.
• Saplacan, Diana & Tørresen, Jim (2022). Robots as Welfare Technologies to Reduce Falls Amongst Older Adults: An Explorative Study from Norway, Human Aspects of IT for the Aged Population. Technology in Everyday Living. Lecture Notes in Computer Science. LNCS 13331. Springer Nature Switzerland AG. ISSN 978-3-031-05654-3. s. 88–106. doi: doi.org/10.1007/978-3-031-05654-3_6.
• Mantelli, Mathias; Noori, Farzan Majeed; Pittol, Diego; Maffei, Renan; Tørresen, Jim & Kolberg, Mariana (2022). Semantic Temporal Object Search System Based on Heat Maps. Journal of Intelligent and Robotic Systems. ISSN 0921-0296. 106(69). doi: 10.1007/s10846-022-01760-8.
• van Otterdijk, Marieke; Song, Heqiu; Tsiakas, Konstantinos; van Zeijl, Ilka & Barakova, Emilia (2022). Nonverbal Cues Expressing Robot Personality - A Movement Analysts Perspective. I Orlandini, Andrea; Recchiuto, Carmine & Rossi, Silvia (Red.), Proceedings of the 31st IEEE International Conference on Robot & Human Interactive Communication - RO-MAN. IEEE conference proceedings. ISSN 978-1-6654-0680-2. doi: 10.1109/RO-MAN53752.2022.9900647.
• Bordvik, David Andreas; Hou, Jie; Noori, Farzan Majeed; Uddin, Md Zia & Tørresen, Jim (2022). Monitoring In-Home Emergency Situation and Preserve Privacy using Multi-modal Sensing and Deep Learning, 2022 International Conference on Electronics, Information, and Communication (ICEIC 2022) . IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665409353. doi: 10.1109/ICEIC54506.2022.9748829. Fulltekst i vitenarkiv Vis sammendrag

  Videos and images are commonly used in home monitoring systems. However, detecting emergencies in-home while preserving privacy is a challenging task concerning Human Activity Recognition (HAR). In recent years, HAR combined with deep learning has drawn much attention from the general public. Besides that, relying entirely on a single sensor modal-ity is not promising. In this paper, depth images and radar presence data were used to investigate if such sensor data can tackle the challenge of a system's ability to detect abnormal and normal situations while preserving privacy. The recurrence plots and wavelet transformations were used to make a two-dimensional representation of the presence radar data. Moreover, we fused data from both sensors using data-level, feature-level, and decision-level fusions. The decision-level fusion showed its superiority over the other two techniques. For the decision-level fusion, a combination of the depth images and presence data recurrence plots trained first on convolutional neural networks (CNN). The output was fed into support vector machines, which yielded the best accuracy of 99.98%.

• Baselizadeh, Adel; Khaksar, Weria & Tørresen, Jim (2022). Motion Planning and Obstacle Avoidance for Robot Manipulators Using Model Predictive Control-based Reinforcement Learning. I Filev, Dimitar; Zhou, MengChu & Tunsel, Edward (Red.), 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-1-6654-5257-1. s. 1584–1591. doi: 10.1109/SMC53654.2022.9945504. Vis sammendrag

  This paper presents a Nonlinear Model Predictive Control-based Reinforcement Learning (NMPC-based RL) framework for robot manipulators. The controller is developed to address the motion planning problem for robot manipulators in the presence of obstacles. The proposed control scheme includes a parametrized NMPC structure used as an approximator for the RL framework’s value function and action-value function. In the NMPC structure, the cost function, system constraints, and the manipulator’s model are parameterized. The Q-Learning algorithm based on the Temporal Difference method adjusts the parameters of the NMPC to increase the closed-loop performance of the whole control scheme. The controller has been applied to a 6-degrees-of-freedom (DoF) model of a robot manipulator, aimed at moving its end-effector to reach the desired pose when static obstacles are in the robot’s workspace. Numerical simulations demonstrate that the proposed controller can effectively control the end-effector’s pose in such a way as to avoid any collisions between the manipulator and the obstacles. It is shown that the learning capability of the proposed NMPC-based RL framework can enhance the efficiency of the control loop up to 21%.

• Tørresen, Jim & Nakazawa, Atsushi (2022). Ethical Considerations in User Modeling and Personalization (ECUMAP). I Bellogin, Alejandro; Boratto, Ludovico; Santos, Olga C.; Ardissono, Liliana & Knijnenburg, Bart (Red.), UMAP'22: Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery (ACM). ISSN 978-1-4503-9207-5. s. 351–353.
• Nergård, Katrine Linnea; Endestad, Tor & Tørresen, Jim (2022). Effect of Hand Dominance When Decoding Motor Imagery Grasping Tasks. I Ribei, Paulo Rogério de Almeida; Cota, Vinícius Rosa; Barone, Dante Augusto Couto & de Oliveira, Alexandre César Muniz (Red.), Computational Neuroscience: Conference Proceedings Third Latin American Workshop, LAWCN 2021, São Luís, Brazil, December 8–10, 2021, Revised Selected Papers. Springer Nature. ISSN 978-3-031-08443-0. s. 233–249. doi: https:/doi.org/10.1007/978-3-031-08443-0_15.

Se alle arbeider i Cristin

• Saplacan, Diana (2024). User Studies in HRI: A Qualitative Research Perspective.
• Saplacan, Diana (2024). Social Robots and Socially Assistive Robots (SARs) within Elderly Care: Lessons Learned So Far.
• Bogen, Annika Celin & Ellefsen, Kai Olav (2023). Hvorfor mener noen at kunstig intelligens er farlig? [Internett]. ung.forskning.no.
• Saplacan, Diana (2023). Webpage for The Ethical, Legal and User Perspectives on Social and Assistive Robots (ELUPSAR) Workshop, at at 11th European Conference on Mobile Robots .
• Saplacan, Diana (2023). Introduction on my background and on the University of Oslo, Robotics and Intelligent Systems Research Group, Norway for Human-Robot Interaction Lab, Department of Social Informatics, Kyoto University, Japan.
• Saplacan, Diana; Pajalic, Zada & Tørresen, Jim (2023). Should Social and Assistive Robots Integrated within Home- and Healthcare Services Be Universally Designed? Cambridge Handbook on Law, Policy, and Regulations for Human-Robot Interaction. Cambridge University Press. ISSN 000-0-000-00000-0. doi: ISBN%209781009386661.
• Ellefsen, Kai Olav (2023). More human robot brains with inspiration from biology, psychology and neuroscience.
• Strand, Ørjan; Reilstad, Didrik Spanne; Wu, Zhenying; Castro da Silva, Bruno; Torresen, Jim & Ellefsen, Kai Olav (2023). Learning When to Think Fast and When to Think Slow.
• Saplacan, Diana (2023). Comment on "Vulnerability in Social and Health Robotics" - presentation by Rachele Carli (Univ. of Bologna and Univ. of Luxembourg), as part of the Vulnerability in Robot Society (VIROS) Annual Symposium, Session I on "Vulnerability and Cognitive Sovereignty".
• Saplacan, Diana (2023). Presentation of the paper "Health Professionals’ Views on the Use of Social Robots with Vulnerable Users: A Scenario-Based Qualitative Study Using Story Dialogue Method".
• Karlsen, Einar; Tørresen, Jim; Ellefsen, Kai Olav; Badescu, Claudia Andreea; van Otterdijk, Marieke & Watanabe, Shin [Vis alle 9 forfattere av denne artikkelen] (2023). Møte den nye helsearbeideren. [Fagblad]. Elektronikk.
• Tørresen, Jim (2023). From Adapting Robot Body and Control to Human–Robot Interaction.
• Tørresen, Jim (2023). What is AI?
• Tørresen, Jim & Yao, Xin (2023). Tutorial: Ethical Risks and Challenges of Computational Intelligence.
• Keeley, Crocket & Tørresen, Jim (2023). Workshop on Ethical Challenges within Artificial Intelligence - From Principles to Practice.
• Tørresen, Jim (2023). What is Robotics?
• Tørresen, Jim (2023). Future Intelligent and Adaptive Robots in Real-World Environments.
• Tørresen, Jim (2023). From Adapting Robot Body and Control Using Rapid-Prototyping to Human–Robot Interaction with TIAGo.
• Tørresen, Jim (2023). Artificial Intelligence – diverse in methods and applications.
• Tørresen, Jim (2023). Robots-assistants that Care about Privacy, Security and Safety.
• Tørresen, Jim; Saplacan, Diana & Mahler, Tobias (2023). Ethical, Legal and User Perspectives on Social and Assistive Robots (ELUPSAR) workshop.
• Tørresen, Jim (2023). Human Intuition and its Impact on Human–Robot Interaction Regarding Safety and Accountability.
• Ellefsen, Kai Olav (2023). Kunstig intelligens: Verden sett gjennom en maskins øyne.
• Ellefsen, Kai Olav (2023). Hva er Kunstig Intelligens?
• Ellefsen, Kai Olav (2023). Evolutionary Robotics.
• Saplacan, Diana (2023). AI and Ethical Considerations. Examples from HRI studies.
• van Otterdijk, Marieke; Saplacan, Diana; Laeng, Bruno & Torresen, Jim (2022). Explorative Study on Human Intuitive Responses to Observing Expressive Robot Behavior.
• van Otterdijk, Marieke; Song, Heqiu; Tsiakas, Konstantinos; van Zeijl, Ilka & Barakova, Emilia (2022). Nonverbal Cues Expressing Robot Personality - a Movement Analysts Perspective.
• Bergflødt, Anderson, Adrian; Søyseth, Vegard & Saplacan, Diana (2022). OPEN ZONE FOR EXPERIMENTAL INFORMATICS (ÅPEN SONE FOR EKSPERIMENTELL INFORMATIKK) as part of "Signals and noise in artificial intelligence" - SENT Festival at the Technical Museum, Oslo, Norway.
• Ellefsen, Kai Olav; Dautenhahn, Kerstin & Tørresen, Jim (2022). Guest Editorial Special Issue on Development and Learning and on Epigenetic Robotics. IEEE Transactions on Cognitive and Developmental Systems. ISSN 2379-8920. 14(4), s. 1302–1305. doi: 10.1109/TCDS.2022.3210665.
• Saplacan, Diana (2022). Presentation at The 2nd Workshop on Design-Centered HRI and Governance. Title: Making Care Robots Understandable: An Introduction to Universal Design Principles as Design and Ethical Guidelines of Social Assistive Robots.
• Saplacan, Diana (2022). Robots as Welfare Technologies to Reduce Falls Amongst Older Adults: An Explorative Study from Norway.
• Saplacan, Diana (2022). Tutorial presentation. Title: "Robots and Society: Challenges and Opportunities within social Human-Robot Interaction" at 31st IEEE International Conference on Robot & Human Interactive Communication.
• Cheung, Anne; Saplacan, Diana; Pietropaoli, Stefano & Weng, Yueh-Hsuan (2022). SORO – INTERDISCIPLINARY WORKSHOP ON THE GOVERNANCE FOR SOCIAL ROBOTS (HALF DAY).
• Saplacan, Diana (2022). Ethics and Social Robots: A Universal Design Perspective - Presentation during Interdisciplinary Workshop on the Governance for Social Robots (SORO) at JURIX 2022 (The 35th International Conference on Legal Knowledge and Information Systems).
• Saplacan, Diana (2022). Ongoing research with Social and Assistive Robots - Presentation for the National Commitee in Research Ethics in Science and Technology (NENT).
• van Otterdijk, Marieke (2022). Roboter bør vise glede når de skal gi hyggelige beskjeder.
• van Otterdijk, Marieke (2022). Forsker: Roboter bør vise glede når de skal gi hyggelige beskjeder.
• Saplacan, Diana (2022). Guest Lecture: Ongoing research with Social and Assistive Robots: Research projects, empirical examples, and theory.
• Saplacan, Diana (2022). TIAGo wishes you welcome to a debate on the theme: Should a robot be involved in care tasks? (Norwegian title: TIAGo ønsker velkommen til en debatt med tema: Bør en robot involveres i omsorgsoppgaver?).
• Saplacan, Diana; Baselizadeh, Adel & Tørresen, Jim (2022). Robot Demonstration: Meet TIAGo the robot! The robot showcases several tasks: brushing hair, putting the lipstick on, using a (plastic) knife, moving an object, carrying a bag.
• Saplacan, Diana (2022). What do we talk about when we talk about social robots vs. robot sociomorphism ? Empirical examples from previous and ongoing research.
• Ellefsen, Kai Olav (2022). Towards more Human Robot Brains. Vis sammendrag

  Despite many large breakthroughs in Artificial Intelligence in the last decade, robots are still struggling to solve tasks that we as humans take for granted, like emptying a dishwasher or learning multiple skills in a sequence. In this talk, Kai Olav Ellefsen will talk about work he and colleagues at the group of Robotics and Intelligent Systems (ROBIN), University of Oslo, have done with the goal of making robots more robust and better learners, by taking inspiration from how humans and animals learn.

• Saplacan, Diana (2022). Ethical challenges and opportunities with (care) robots - Universal Design as an ethical charter for inclusive robot design and interaction.
• Brinck, Ingar; Paiva, Ana; Saplacan, Diana & Bensch, Suna (2022). Debate during the symposium: "The Future of Human-Robot Interaction Science" at the Trandisciplinary AI for Good of All (TAIGA) Inauguration Conference, leaded by Prof. Thomas Hellström and Ass. Prof. Niclas Kaiser leading TAIGAS focus area on Embodied interactive AI, at Umeå University, Sweden .
• Tørresen, Jim; Atsushi, Nazawa; Saplacan, Diana; Prestes, Edson; Mahler, Tobias & Weng, Yueh-Hsuan (2022). Tutorial at IROS 2022 - Ethical, Legal and User Perspectives on Robots and Systems (ELAUPORAS) – Assessments and Potential Measures.
• Saplacan, Diana (2022). Ethics: Autonomous Technologies for All (ATA)?
• Saplacan, Diana (2022). Ethics: Research Ethics and Autonomous Technologies for User Diversity.
• Saplacan, Diana (2022). Comment on "Understanding Gaps in Standards, Regulations and Training Needs for Healthcare Professionals working alongside Physically Assistive Robots" - presentation by Prof. Praminda Calleb Solly from University of Nottingam, U.K.
• Reilstad, Didrik Spanne; Strand, Ørjan; Wu, Zhenying; Castro da Silva, Bruno; Torresen, Jim & Ellefsen, Kai Olav (2022). RADAR: Reactive and Deliberative Adaptive Reasoning – Learning When to Think Fast and When to Think Slow.
• Tørresen, Jim (2022). Sensing, acting and adapting in the real world.
• Tørresen, Jim (2022). Ethical Perspectives of Robotics and AI – How to develop preferable system? .
• Tørresen, Jim (2022). Research on health-related treatment and care technology – A technical and ethical view.
• Tørresen, Jim (2022). Tutorial: Ethical challenges for Autonomous and Multiagent Systems.
• Saplacan, Diana; Tørresen, Jim; Weng, Yueh-Hsuan & Li, Phoebe (2022). Tutorial: Robots and Society (RO-SO 2022) / Ethical perspectives and technical challenges and opportunities with care robots.
• Tørresen, Jim & Nakasawa, Atsushi (2022). Tutorial: Ethical Considerations in User Modeling and Personalization (ECUMAP).
• Tørresen, Jim (2022). Introduction to Research Visit to University of Oslo in Norway.
• Tørresen, Jim (2022). Keynote: Multi-Modal Sensing for Care Robots for Older People.
• Tørresen, Jim (2022). Tutorial: Ethical Challenges in Computational Intelligence Research.
• Tørresen, Jim (2022). Introduction to Research Visit to University of Oslo in Norway.
• Saplacan, Diana (2022). Ethical Issues in Mobile Robots - Guest Lecture for Norwegian University of Life Sciences (NMBU), at the Faculty of Science and Technology, part of Human-Robot Interaction Course, Advanced Topics in Mobile robots.
• Sumioka, Hidenobu; Tørresen, Jim; Shiomi, Masahiro; Chen, Liang-Kung & Nakazawa, Atsushi (2022). Editorial: Interaction in robot-assistive elderly care. Frontiers in Robotics and AI. ISSN 2296-9144. 9. doi: 10.3389/frobt.2022.1020103.
• Saplacan, Diana (2022). Participatory Design and Human-Robot Interaction - An ethical and inclusive perspective on contemporary technologies.
• Saplacan, Diana (2022). A talk on robots as connected devices or smart "things" in the home, part of the AI & Ethics workshop.
• Dahl, Heidi Elisabeth Iuell; Mehmandarov, Rustam Karim; Harkestad, Inge & Saplacan, Diana (2022). AI and Ethics workshop.
• Saplacan, Diana (2022). Healthcare Professionals’ Attitudes towards the Organization of Care Services and the Adoption of Welfare Robots in Norway.
• Saplacan, Diana (2022). The importance of standarization within new technological areas.
• Saplacan, Diana (2022). Webpage for the tutorial at RO-MAn 2022 Conference: Robots and Society: Ethical, social, legal, and technical perspectives on integrating social robots in the home and healthcare systems and services (RO-SO - Second Edition).
• Saplacan, Diana (2022). Some experiences about analysis and writing.
• Saplacan, Diana (2022). AI & Ethics Workshop. Vis sammendrag

  Workshop on AI & Ethics organized in cooperation with Tekna Big Data professional network and The Norwegian Council for Digital Ethics. The theme of the workshop: Must AI be professionalized to ensure ethical development? Role: Organizer/Contact person.

• Tørresen, Jim (2022). Robotikk: Digitalisering av fysiske oppgaver.
• Lindblom, Diana Saplacan; Tørresen, Jim & Hakimi, Nina (2024). Dynamic Dimensions of Safety - How robot height and velocity affect human-robot interaction: An explorative study on the concept of perceived safety. University of Oslo.
• Noori, Farzan Majeed; Tørresen, Jim; Uddin, Md Zia & Riegler, Michael A. (2023). Multimodal Deep Learning Approaches for Human Activity recognition. Universitetet i Oslo. ISSN 1501-7710. Fulltekst i vitenarkiv Vis sammendrag

  Smart homes may be beneficial for people of all ages, but this is especially true for those with care needs, such as the elderly. To assist, monitor for emergencies, and provide companionship for the elderly, a substantial amount of research on human activity recognition systems has been conducted. Several algorithms for activity recognition and prediction of future events have been reported in the scientific literature. However, the majority of published research does not address privacy concerns or employ a variety of ambient sensors. The objective of this thesis is to contribute to the progress in research relevant to activity recognition systems that use sensors that collect less privacy-related information. The following tasks are included in the work: assessment of sensors while keeping privacy concerns in mind, selection of cutting-edge classification methods, and how to fuse the data from multiple sensors. This thesis contributes to making progress on systems for analyzing human activity and state—or vital signs—for application in a mobile robot. This dissertation examines two topics. First, it examines the privacy concerns associated with having a robot in the home. On a robot, an ultra-wideband (UWB) radar-based sensor and an RGB camera (for ground truth) were installed. An actigraphy device was also worn by the users for heart rate monitoring. The UWB sensor was selected to maintain privacy while monitoring human activities. Considering different ways to represent data from a single sensor is the second topic under investigation. That is, how data from multiple representations can be combined. For this purpose, we investigate various data representations from a single sensor’s data and analysis using cutting-edge deep learning algorithms. The contributions provide considerations for equipping a mobile home robot with activity recognition abilities while reducing the amount of privacy-sensitive sensor data. The work also concerns examining the potential privacy restrictions that must be established for the analyzing systems. The thesis contains new methods for combining data from multiple information sources. To achieve our objective, convolutional neural networks and recurrent neural networks were applied and validated using conventional methods. The conclusion of the thesis is that we can achieve good accuracy with limited sensors while maintaining privacy. It is, however, likely adequate for assisting healthcare personnel and caregivers in their work by indicating current activity status and measuring activity levels, providing alerts about abnormal activities. The results can hopefully contribute to older people being able to live alone in their homes with a larger chance of any unwanted events being quickly detected and notified to the caregivers and providers.

• Taye, Eyosiyas Bisrat & Ellefsen, Kai Olav (2023). Accountability Module: Increasing Trust in Reinforcement Learning Agents. Universitetet i Oslo. Vis sammendrag

  Artificial Intelligence requires trust to be fully utilised by users and for them to feel safe while using them. Trust, and indirectly, a sense of safety, has been overlooked in the pursuit of more accurate or better-performing black box models. The field of Explainable Artificial Intelligence and the current recommendations and regulations around Artificial Intelligence require more transparency and accountability from governmental and private institutes. Creating a self-explainable AI that can be used to solve a problem while explaining its reasoning is challenging to develop. Still, it would be unable to explain all the other AIs without self-explainable abilities. It would likely not function for different problem domains and tasks without extensive knowledge about the model. The solution proposed in this thesis is the Accountability Module. It is meant to function as an external explanatory module, which would be able to function with different AI models in different problem domains. The prototype was inspired by accident investigations regarding autonomous vehicles but was created and implemented for a simplified simulation of vehicles driving on a highway. The prototype's goal was to attempt to assist an investigator in understanding why the vehicle crashed. The Accountability Module found the main factors in the decision that resulted in an accident. It was also able to facilitate the answering of whether the outcome was avoidable and if there were inconsistencies with the agent's logic by examining different cases against each other. The prototype managed to provide useful explanations and assist investigators in understanding and troubleshooting agents. The thesis and the Accountability Module indicate that a similar explanatory module is a robust direction to explore further. The chosen explainability methods and techniques were highly connected to the problem domain and limited by the scope of the thesis. Therefore, a more extensive test of the prototype with different problems needs to be performed to check the system's rigidity and versatility as well as the significance of the results. Nevertheless, in a collaboration between an Accountability Module expert and a domain expert, I expect a modular explainability solution to create more insight into an AI model and its significant incidents.

• Kocan, Danielius & Ellefsen, Kai Olav (2023). Attention-Guided Explainable Reinforcement Learning: Key State Memorization and Experience-Based Prediction. Universitetet i Oslo.
• Lindblom, Diana Saplacan; Tørresen, Jim & Meijer, Frida (2023). In Safe Hands: Contribution of gripper material on HRI and perceived safety: An explorative study. University of Oslo.
• Bordvik, David Andreas; Ellefsen, Kai Olav & Riemer-Sørensen, Signe (2022). Forecasting regulation market balancing volumes from market data and weather data using Deep Learning and Transfer Learning. Universitetet i Oslo. Vis sammendrag

  The energy and power sector is a major value contributor to our society and our high living standards. In recent times the power sector has gained increased complexity while undergoing significant changes, with the increased share of renewable production being one of the contributors. An increased portion of renewable contributors in the power mix from, e.g., wind power, results in more volatile power production, increasing the need for grid balancing, making the regulating power market more challenging for power producers to participate in. The purpose of the regulating power market is to compensate the gap between the planned production that has been settled in the day-ahead market and the actual production and demand. The ability to forecast the regulating power volumes and prices some hours in advance of the hour when it is actually traded would enable power producers to balance their positions in the market more optimally. This project exploits historical regulation data together with different market data and weather data to train deep learning models to forecast future regulation volumes. A thorough time-series analysis of regulating power volumes revealed some predictive potential. Furthermore, Bidirectional LSTM showed satisfying results when forecasting up to four hours into the future using data from 2016-to 2021. No previous research was found that uses more than two years of data, no previous research uses recent data, and no previous work has utilized deep learning to forecast the Norwegian regulation market volumes. Additionally, this project did a deep analysis of topographical weather images and transfer learning to evaluate the potential of predicting regulating power volumes using weather images. Different weather forecasts, actual weather, and weather uncertainties were all utilized. The weather data was generally not found to have a considerable direct influence on regulation volumes. However, the weather is considered to have an increasing influence in the future as more volatile renewable power production is expected in the power markets. No previous research has been found to investigate weather images in the context of the regulation market.

• Roa Gran, Kristian & Ellefsen, Kai Olav (2022). Learning to drive by predicting the future: Direct Future Prediction. Universitetet i Oslo. Vis sammendrag

  The use of artificial intelligence in systems for autonomous vehicles is growing in popularity [1, 2]. Following the rapid development of deep learning techniques over the past years, reinforcement learning has enabled automating the learning of prediction abilities. Controlling an autonomous vehicle with reinforcement learning is typically done by either learning a direct mapping from observations to actions, or by learning a model of the environment and using the model to make decisions. Model-free approaches have previously seen the most success as errors can easily propagate in an inaccurate model. The predictive reinforcement learning algorithm «Direct Future Prediction» (DFP) won the Visual Doom AI competition in 2016 with results 50% better than the second best submission [3]. By learning a simpler model of the environment that only focuses on a few measurable quantities this approach can efficiently solve challenging control tasks. Prior to this thesis, the utility of the method had not yet been tested for relevant real world tasks, such as sensorimotor control of an autonomous vehicle. DFP is tested on a variety of traffic scenarios with the aim of investigating the potential for predictive deep learning algorithms to learn to control an autonomous vehicle. The more classical reinforcement learning algorithm «Deep Q-Networks» (DQN) is also trained and tested on the same scenarios, and is used as a reference for determining the performance of DFP. Experiments are conducted in a more difficult version of the CarRacing simulator from OpenAI gym, where DQN has previously performed well [4, 5]. DFP is able to solve all of the traffic scenarios from the conducted experiments, and is able to drive around a challenging track while avoiding cleverly placed obstacles. The performance of DFP is equal to, or better, in every experiment when compared to DQN. The driving style of the DFP agents are calm and controlled, which is further highlighted by the sporadic driving of the DQN agents. Performance is strong also in previously unseen environments, indicating that the method has good generalization abilities, which is further explained when visualizing the future DFP predictions.

• Soma, Rebekka; Saplacan, Diana & Sikora, Magdalena Claudia (2022). Exploring personality and behavior with a robot table - a qualitative case study. Universitetet i Oslo.
• Olsen, Vincent Coward & Tørresen, Jim (2022). Robotic Rehabilitation Aiding with Upper-limb Impairments: Using the Robot TIAGo. Universitetet i Oslo.

Se alle arbeider i Cristin