Go to DBLP homepageEditorial: Women in neurorobotics
Abstract: Understanding the neural mechanisms of empathy toward robots to shape future applications: This article, authored by Jenna H. Chin, Kerstin S. Haring and Pilyoung Kim, provides an overview of modern neuroscience evaluations linking to robot empathy. It evaluates the brain correlates of empathy and caregiving, with a specific emphasis on women. The understanding of these brain correlates can inform the development of social robots with enhanced empathy and caregiving abilities, benefiting various aspects of society, including the transition to parenthood and parenting, where women play a crucial role. The article also discusses some of the barriers women face in the field and underscores the importance of broad representation among researchers.Enactive artificial intelligence: subverting gender norms in human-robot interaction: This paper, authored by Inês Hipólito, Katie Winkle and Merete Lie, introduces Enactive Artificial Intelligence (eAI) as a gender-inclusive approach to AI, focusing on the subversion of gender norms within Robot-Human Interaction in AI. The study employs a multidisciplinary framework to explore the intersectionality of gender and technoscience. It reveals the development of four ethical vectors (explainability, fairness, transparency, and auditability) as essential components for promoting gender-inclusive AI. By considering these vectors, AI can align with societal values, promote equity and justice, and create a more just and equitable society for all.Continuous joint velocity estimation using CNN-based deep learning for multi-DoF prosthetic wrist for activities of daily living: by Zixia Meng and Jiyeon Kang, states that myoelectric control of prostheses is a well-established technique, but it often involves isolated movements that do not mirror natural movements during daily activities. This article addresses the need for a control system for multidegree-of-freedom (DoF) prosthetic arms trained using surface electromyography (sEMG) data collected from activities of daily living (ADL) tasks. It focuses on two major wrist movements, pronation-supination, and dart-throwing movement (DTM), introducing a new wrist control system. The proposed training strategy, "Quick training," is designed to handle real-world variations such as sensor displacement, muscle fatigue, and sensor contamination. The results, based on data from 24 participants, indicate the effectiveness of this approach, with significant improvements in root mean square error and Pearson correlation values across various ADL tasks.this article, authored by Mariacarla Staffa, Lorenzo D'Errico, Simone Sansalone and Maryam Alimardan highlights that significant efforts have been made in the past decade to humanize both the form and function of social robots to increase their acceptance among humans. This study addresses the challenges of emotion recognition using brain-computer interfaces during human-robot interaction. EEG signals were collected from participants interacting with a robot, and machine learning models were trained to classify human emotional responses to the robot's behavior. The results demonstrate the potential to classify emotional responses from EEG signals, opening the door for social robots to comprehend users' emotional states and attribute mental states to them, advancing the field of human-robot interaction.Social Robots as Effective Language Tutors for Children: Empirical Evidence from Neuroscience: This study, authored by Maryam Alimardani, Jesse Duret, Anne-Lise Jouen and Kazuo Hiraki, explores children's brain responses to robot-assisted language learning. EEG signals were collected from children learning French vocabularies in two groups, one learning from a social robot with narrated French stories and animations, and the other from a display without the robot. The results indicate increased brain synchronization in the theta frequency band in the Robot group, a factor previously associated with success in second language learning. This neuroscientific evidence highlights the effectiveness of social robots as language tutors for children, offering new possibilities for educational technologies.The guest editors have been proud to contribute to FRONTIERS platform championing diversity, innovation, and equality. We invite you to explore the impressive research presented in this collection and join us in celebrating the remarkable women who are shaping the future of Neurorobotics. Silvia Tolu is an Associate Professor at the Technical University of Denmark, Electrical and Photonics Engineering Department. Her main interests are in bio-inspired control and neurorobotics. She was awarded a PhD by the University of Granada, Spain. During her PhD she combined machine learning techniques and modelling of biological systems to develop control architectures capable of learning from sensorimotor relationships, and of generalising this knowledge to novel contexts. From 2015 she joined the Automation and Control group at the Technical University of Denmark as PostDoc where she focused her research on an understanding of the brain-body interplay. She became Assistant Professor in 2019. Most of her research has been performed in the context of European projects: Sensopac (2006-2008), Drivsco (2008-2009), Human Brain Project (HBP -FET Flagship initiative, 2016-ongoing), EU Marie Skłodowska-Curie Individual Fellowship (Marie Curie project BIOMODULAR, Project ID: 705100, 2017-2019). In BioModular, Silvia pursued discovering important insights into the modular structure of the cerebellum and its involvement in motor control and learning. In HBP, Silvia was the DTU team leader in the Sub-Project 10-Neurorobotics (2017)(2018)(2019)(2020). Her group focused on building and validating biomimetic learning architectures into the Neurorobotics platform with different robots (e.g., humanoids and animal-like robots). Silvia is currently leading the Neurorobotics Technology Laboratory (NRT-LAB) at DTU where her team aims to design bio-mimetic control architectures for artificial systems that integrate biologically plausible brain models and bodies for investigating motor control and learning principles and validate them in realistic, dynamic, and rich sensory tasks and environments. She collaborates with many research groups, mainly The Biorobotics Institute, Bolonia Univ., Eindhoven Univ. of Tech. (TUe), Univ. of Munich, Univ. of Copenhagen, Royal Institute of Tech.Jiyeon Kang is an Associate Professor in Gwangju Institute of Science and Technology (GIST) since 2023. Before joining GIST, she worked as an assistant professor in Mechanical and Aerospace Engineering in University at Buffalo (SUNY-Buffalo). She completed her postdoctoral training in rehabilitation biomechanics laboratory at University of Michigan. She obtained her Ph.D. degree in Mechanical Engineering from Columbia University. During her PhD program, she found new robotic intervention that leverages internal motor learning of the patients by walking in an environment with augmented gravity to strengthen the weak muscles of the leg. She received her B.S. and M.S. degrees in Mechanical Engineering from Seoul National University in 2008 and 2010, respectively. She worked as a researcher in Korea Institute of Science and Technology (KIST) developing a power-assist robot for supporting active daily living of individuals with special needs. Her research was funded by NSF and SUNY grant programs. She served as an organizer and workshop chair for IEEE RAS/EMBS BioRob2020 (USA) 2022(Korea). Her major interest is in rehabilitation/assistive robots and prosthetic devices to enhance the motor function of various patient groups. She is currently leading AI-based Wearable Robotics (AWEAR) lab with projects funded by National Research Foundation of Korea.
External IDs:dblp:journals/finr/StaffaTK23
Loading