Find Academic Supervisors

Jean OhView profile

Researcher

• Robotics
• Artificial Intelligence
• Human-Robot Interaction
• +5 more

Jean Oh is a Researcher at the Robotics Institute of Carnegie Mellon University (CMU) , leading the interdisciplinary Bot Intelligence Group (BIG) . Her work focuses on developing persistent robots that co-exist and collaborate with humans in shared environments, emphasizing continuous improvement through training, exploration, and human interaction. Education: Ph.D. in Language and Information Technologies, CMU M.S. in Computer Science, Columbia University B.S. in Biotechnology, Yonsei University Oh's research integrates vision, language, and planning systems in robotics, with applications in human-robot teaming , self-driving cars , disaster response , eldercare , and creative robotics . She has pioneered projects like socially-compliant robot navigation in human crowds and AI-driven robotic painting systems. Recent publication trends highlight her work in vision-language planning , social navigation , computational creativity , and human-robot collaboration . Notable contributions include the StyleCLIPDraw algorithm for text-to-art generation and Social-PatteRNN for human-like trajectory prediction. Scientific Awards: Best Paper Award in Cognitive Robotics (ICRA'18, ICRA'15) Best Systems Paper Finalist (HRI'25) Best Oral Paper Finalist (Humanoids'24) Best Paper in Entertainment (IROS'24) Argoverse Challenge Winner (CVPR'24) Best Student Paper (AIAA'24) Best Demo Finalist (RoboSoft'24) Oh mentors a diverse team of PhD, MS, and undergraduate students from CMU departments including Robotics, Computer Science, and Mechanical Engineering. Her research is funded by US Army Research Lab , DiDi Chuxing , and DARPA , with collaborations across industry and academia .

Roberto ManduchiView profile

Professor

• Computer Vision
• Assistive Technology
• Human-Computer Interaction
• +2 more

Roberto Manduchi is a Professor of Computer Science and Engineering at the University of California, Santa Cruz, within the Baskin School of Engineering. His primary affiliation is with the Computer Science and Engineering department where he leads research in assistive technology for visual impairments. He holds a Dottorato di ricerca in Electrical Engineering from the University of Padova, Italy, and previously worked at Apple and NASA JPL before joining UCSC in 2001. His research focuses on mobile computer vision, inertial sensors, and location-aware systems to enhance spatial awareness and information access for blind and low-vision individuals. Key research areas include indoor navigation systems, screen magnification for low-vision readers, obstacle detection using augmented reality, and text accessibility assessment through specialized OCR pipelines. His work bridges computer vision, human-computer interaction, and accessibility design. Analysis of his recent publications (2022-2025) reveals strong emphasis on inertial-based indoor navigation (e.g., PALMS localization system, backtracking algorithms), screen magnification usability studies, and novel approaches to scene text access for blind users. His research consistently targets practical applications for visual impairment, with significant contributions to pedestrian dead reckoning, magnetic signature localization, and gaze-contingent interfaces. Manduchi serves on the scientific advisory board of Aira and is a board member of the Vista Center for the Blind and Visually Impaired. He leads the UCSC Computer Vision Lab where his team develops accessible computing solutions. His work includes both theoretical contributions to computer vision and tangible assistive applications, with recent projects focusing on smartphone-based inertial odometry, multi-scale tactile maps, and real-time obstacle cueing systems.

Emily CrossView profile

Professor

• Cognitive Neuroscience
• Social Neuroscience
• Embodied Cognition
• +5 more

Emily Cross is a Full Professor at the Department of Humanities, Social and Political Sciences at ETH Zurich, leading the Social Brain Sciences Professorship since spring 2023. She previously held professorships at Bangor University (Wales), University of Glasgow (Scotland), Macquarie University (Australia), and Western Sydney University's MARCS Institute (Australia). Her research centers on how embodied experience shapes social learning and perception across diverse contexts. Key contributions include identifying neural signatures of embodied expertise using dancers, developing embodied neuroaesthetics theory, uncovering neurocognitive foundations of visual learning across lifespans, and pioneering paradigms for human-robot social engagement. Her interdisciplinary approach bridges technology, performing/visual arts, and social sciences to explore experience-dependent plasticity at brain and behavioral levels. Recent publications (2024-2025) demonstrate intense focus on human-robot interaction dynamics, aesthetic movement perception, and context-dependent social cognition. Work increasingly examines self-disclosure mechanisms to robots, cultural influences on robot acceptance, and neural correlates of movement synchrony, reflecting her expanding influence at the neuroscience-robotics intersection. Scientific awards include: Philip Leverhulme Prize for Psychology Jacob Bronowski Award from British Science Foundation Young Talent Award from Dutch Neuroscience Society RoboHub and Insight Analytics top women in robotics listings Australia’s Superstars of STEM (2022) Cross passionately trains next-generation scientists with emphasis on research ethics. Her work attracts major funding from ERC, NIH, Fulbright Commission, ESRC, EPSRC, and UK Ministry of Defence. She serves on UNESCO’s International Bioethics Committee (co-rapporteur for neurotechnology ethics report) and as Associate Editor for International Journal of Social Robotics. She leads ETH Zurich's dynamic Social Brain Sciences group, which embraces interdisciplinarity through research paradigms bridging technology, performing/visual arts, and biological/social sciences, while maintaining active roles in editorial boards and conference committees including Intelligent Virtual Agents and Affective Computing meetings.

Anil Ufuk BatmazView profile

Assistant Professor

• Virtual Reality
• Augmented Reality
• Human-Computer Interaction
• +3 more

Dr. Anil Ufuk Batmaz is an Assistant Professor in the Department of Computer Science and Software Engineering at Concordia University. His research focuses on Virtual Reality (VR), Augmented Reality (AR), and Human-Computer Interaction, with emphasis on interaction techniques, immersive analytics, and motor skill training systems. He holds a BSc in Electrical and Electronics Engineering (2007-2011), an MSc in the same field (2011-2013), and a PhD in Biomedical Engineering (2015-2018). His work bridges engineering and cognitive science, investigating how visual and haptic feedback impact user performance in immersive environments. Research interests include: 3D interaction techniques for mid-air tasks Effects of display technologies on motor coordination Hybrid UI design for mixed reality systems Training systems for precision tasks using VR Recent publications emphasize evaluation of AR/VR interfaces in healthcare, sports training, and collaborative environments. His work has appeared in venues like IEEE TVCG, ACM CHI, and ISMAR, addressing challenges in spatial navigation, error feedback, and system reliability.

Jim TørresenView profile

Professor

• Artificial Intelligence
• Robotics
• Biology-Inspired Computing
• +6 more

Jim Tørresen is a Professor of Computer Science at the Department of Informatics, University of Oslo, where he has been employed since 1999 (Associate Professor 1999-2005, Professor since 2006). He serves as group leader for the Robotics and Intelligent Systems (ROBIN) research group and is also a Principal Investigator at the Centre for Interdisciplinary Studies in Rhythm, Time and Motion (RITMO). His academic career includes visiting positions at Cornell University's Creative Machines Lab (2010-2011) and Kyoto University in Japan (1993-1994). His educational background includes a Dr.ing. (Ph.D.) in Computer Architecture from the Norwegian University of Science and Technology (1996) and an M.Sc. in Computer Architecture from the same institution (1991). Before his academic career, he worked in industry at Navia Aviation (1998-1999) and NERA Telecommunications (1996-1998). Tørresen's research spans artificial intelligence, robotics, and bio-inspired computing. His work focuses on biology-inspired algorithms, programmable logic (FPGA), robotics (simulation, prototyping, control), and human-robot interaction. He has made significant contributions to areas including evolutionary computing, reconfigurable hardware, and adaptive systems. His research often bridges theoretical computer science with practical applications in healthcare, music, and industrial settings. His recent publications demonstrate a strong focus on human-robot interaction, particularly in healthcare contexts for elderly care, as well as applications in sports science, musical robotics, and geological engineering. His work shows a consistent pattern of interdisciplinary research that combines machine learning techniques with domain-specific challenges. Tørresen has also authored a popular science book on artificial intelligence in the "what is" series by Universitetsforlaget, which discusses fundamental concepts, methods, future perspectives, and ethical aspects of AI. He has been active in academic leadership, serving as General Chair for the 22nd International Conference on Field Programmable Logic and Applications (FPL) in 2012 and the 9th Joint IEEE International Conference of Developmental Learning and Epigenetic Robotics in 2019. As group leader of ROBIN, he oversees research on intelligent systems that operate in dynamic environments requiring runtime adaptation. The group works at both fundamental and applied levels, using evolutionary algorithms for robot learning and machine learning techniques for classification and recognition tasks in various application domains.

• Human-Robot Interaction
• Rehabilitation Robotics
• Socially Assistive Robotics
• +7 more

Carlos Cifuentes is an Associate Professor in Human-Robot Interaction at the Bristol Robotics Laboratory (BRL) , part of the University of the West of England (UWE Bristol) . He also serves as the Deputy Director of the VIVO Hub , a £13.4M UK-funded research initiative (2024-2030) focused on robotics for rehabilitation and healthcare. His research spans Human-Robot Interaction , Rehabilitation Robotics , Healthcare Robotics , and Socially Assistive Robotics , with applications for conditions such as cardiac diseases , post-stroke recovery , spinal cord injuries , cerebral palsy , Parkinson's disease , musculoskeletal disorders , and autism spectrum disorder (ASD) . Carlos has over 15 years of experience and 200+ publications in robotics for rehabilitation and assistive technologies. His recent work explores smart walkers with multimodal feedback, soft prosthetics using polymeric optical fiber sensors , and machine learning models for fatigue and stress estimation. He also investigates inclusive design for social robots in global contexts , including a CASTOR Robot for ASD therapy and collaborative design processes with Colombian communities. Carlos serves as an Associate Editor for IEEE Robotics and Automation Magazine (since 2021), ICRA , and IROS (since 2023). He leads projects integrating wearable sensors , deep learning , and haptic feedback to enhance mobility, autonomy, and quality of life for individuals with disabilities. As Deputy Director of the VIVO Hub, he focuses on long-term deployment of robotic systems in real-world healthcare settings, emphasizing collaboration with clinicians , caregivers , and neurodiverse communities . His work bridges robotics , biomedical engineering , and human-centered design .

• Non-Destructive Evaluation
• Ultrasonic Testing and Imaging
• Eddy Current Testing
• +9 more

Dr. Ehsan Mohseni is a Senior Lecturer in the Department of Electronics and Electrical Engineering at the University of Strathclyde, Faculty of Engineering. He is a key member of the Centre of Ultrasound Engineering (CUE) research group and supports the Royal Academy of Engineering and Spirit AeroSystems research chair led by Professor Gareth Pierce. His work focuses on advancing robotic and intelligent Non-Destructive Evaluation (NDE) systems for industrial applications. B.Sc. in Materials Science and Metallurgical Engineering, University of Tehran, 2006 M.Sc. in Metal Forming Processes, University of Tehran Ph.D. in Automated Defect Detection using Electromagnetic NDE, École de Technologie Supérieure (ETS), Montreal, Canada Dr. Mohseni’s research is centered on NDE 4.0, integrating advanced sensing, multi-physics modeling, and machine learning. His expertise spans ultrasonic and eddy current testing, multi-sensor data fusion, and probability of detection studies. He focuses on applications in additive manufacturing, welding, composites, and metal processing, aiming to overcome current technological barriers in industrial inspection. The recent publications highlight a strong trend toward intelligent, automated, and robotic NDE systems. Key themes include self-supervised learning for ultrasonic segmentation, human-machine collaboration in data analysis, and advanced signal processing for weld and composite inspection. The integration of AI, flexible sensor arrays, and embedded navigation systems reflects a shift toward smart, adaptive inspection platforms aligned with Industry 4.0. Scientific Awards: The BINDT Annual Conference Award (2019) Dr. Mohseni is actively involved in research funding and knowledge transfer. He serves as Principal Investigator on KTP projects with ETHER NDE LIMITED and NATIONAL OILWELL VARCO UK LIMITED, focusing on in-process inspection for additive manufacturing and field calibration for ultrasonic testing. He contributes to large-scale collaborative projects funded by Innovate UK and industry partners, emphasizing practical deployment of NDE solutions. He also supervises research staff and collaborates with global aerospace firms including Pratt & Whitney Canada, Safran, and Bell Helicopter. He is a core member of the Centre of Ultrasound Engineering (CUE), a dynamic research group developing next-generation ultrasound technologies. The team works on advanced robotic sensing hubs, flexible transducer arrays, and AI-driven data interpretation tools, often in collaboration with the Royal Academy of Engineering research chair and industrial partners.

Can LiuView profile

Assistant Professor

• Human-Computer Interaction
• Artificial Intelligence
• Spatial Computing
• +5 more

Dr. Can Liu is an Assistant Professor at the School of Creative Media, City University of Hong Kong, where she leads the ERFI Lab (Laboratory of Empirical Research for Future Interfaces). Her research focuses on designing future interfaces for ubiquitous technologies through empirical understanding of human cognition and behavior, with emphasis on multimodal interaction combining physical and digital elements. Education: PhD in Human-Computer Interaction, Université Paris-Sud (France), INRIA labs ex)situ and ILDA MSc in Media Informatics, RWTH Aachen University (Germany) Dr. Liu's research spans three primary domains: AI-assisted Input (using LLMs/NLP to enhance text manipulation and speech interfaces), Spatial Computing (multimodal interfaces for AR/VR and large displays), and Hybrid/Remote Collaboration (supporting intuitive remote interaction through understanding collocated collaboration). Her work integrates empirical user studies with real-world system deployments in public spaces. Recent publications demonstrate strong trends toward LLM-integrated interfaces, wearable computing applications, and novel interaction techniques for foldable devices. Her team consistently publishes at top venues including CHI, UIST, and CSCW, with increasing focus on practical AI integration for everyday tasks. Awards and Recognition: Best Paper Award at ACM CHI 2014 (top 1%) Honourable Mention at ACM CHI 2012 (top 5%) Dr. Liu actively mentors PhD students and researchers while securing substantial research funding including Google Faculty Research Awards, National Natural Science Foundation grants, and RGC Early Career Schemes. She serves on numerous program committees including ACM CHI (Associate Chair 2024, 2022, 2021, 2020, 2019, 2017) and co-organizes research initiatives like the HCIX Summer Research Program. Her laboratory ecosystem includes the ERFI Lab, affiliation with the Augmented Materiality Lab and Kowloon Interaction Center, and active participation in the Greater Bay HCI community, supporting both fundamental research and industry collaboration with partners including Google, Huawei, and Lenovo.

Avinash SinghView profile

Senior Lecturer

• Machine Learning
• Cognitive Neuroscience
• Brain-Computer Interfaces
• +6 more

Dr. Avinash Singh is a Senior Lecturer at the School of Computer Science at the University of Technology Sydney (UTS), Australia. He serves as co-chair of the IEEE Neuroethics Framework for the Workplace, sponsored by IEEE Brain, and is a member of the IEEE Standards Committee on Unifying Brain-Computer Interfaces (BCI). He also serves as an expert advisor for UNICEF and The Centre of Neurotechnology and Law, UK. Dr. Singh completed his PhD in Computer Science in 2019 at UTS, collaborating with the Technical University of Berlin, Germany, the University of California San Diego, USA, and the US Army Research Lab. Prior to his doctorate, he earned a Master's in Software Systems from Birla Institute of Technology and Science Pilani, India, and earlier degrees in Computer Science and Mathematics from Indian institutions. Working at the intersection of machine learning, cognitive neuroscience, and mixed-reality, Dr. Singh focuses on designing and developing real-world neuroadaptive BCI systems. His research integrates AI technologies with cognitive neuroscience to explore cognitive functions, discover relationships between brain dynamics, evaluate everyday interactions, and develop robust next-generation neuroadaptive BCIs. His work spans areas including neuroadaptive BCI applications for improving interpersonal communication, sensory augmentation for blind individuals, and dream reconstruction from brain signals. Analysis of Dr. Singh's recent publications reveals a consistent focus on developing novel EEG signal processing techniques, creating neuroadaptive interfaces, and applying BCI technology to real-world problems. His work shows increasing integration of deep learning with neuroscience, particularly in the context of cognitive conflict detection, spatial navigation, and assistive technologies for the visually impaired. The research demonstrates strong interdisciplinary connections across computer science, neuroscience, and human-computer interaction. Google TensorFlow Faculty Award (2021) Dr. Singh actively supervises PhD students and has received multiple research grants, including ARC Linkage Projects and NHMRC Ideas Grants. His funded research spans neuro-AI for personalized image generation, sensory augmentation for blind individuals, and ethical frameworks for BCI technology. He leads the UTSxDream Recording project (formerly DreamMachine) and collaborates with international institutions on BCI standardization efforts. Dr. Singh founded the India Future Society, a think tank focused on transhumanism, and actively advocates for the ethical development of neurotechnology. His work bridges academic research with practical applications in assistive technology, human-robot collaboration, and spatial navigation systems.

Daniele LeonardisView profile

Associate Professor

• Wearable Robotics
• Haptic Interfaces
• Neurorehabilitation
• +4 more

Daniele Leonardis serves as Associate Professor of Applied Mechanics at the Institute of Mechanical Intelligence (IIM) of the Sant'Anna School of Advanced Studies in Pisa since October 2025. His research centers on wearable haptic interfaces and hand exoskeletons for clinical neurorehabilitation, virtual reality, and teleoperation applications. His primary research domains include: Development of miniaturized actuators for high-fidelity haptic rendering in wearable devices Clinical neurorehabilitation using serious games for children with Cerebral Palsy Integration of tactile feedback in teleoperation systems for complex manipulation tasks Soft exoskeletal devices for movement assistance in spinal/neurological patients Industrial robotics for railway infrastructure inspection Leonardis leads significant research initiatives: Coordinator and scientific director of the completed TELOS project (2024) for VR-based cerebral palsy rehabilitation Scientific director for SSSA in the European SUN project on augmented reality and haptic feedback Director of the SmartNest third-party research project Collaborator in TATTO, LEARN, and AVATAR projects Supervisor for RFI's mobile railway inspection system design His recent publications (2024-2025) demonstrate concentrated advancements in teleoperation interfaces, soft exoskeleton validation, and novel actuation methods for tactile feedback, with strong clinical and industrial validation components. He actively disseminates research through editorial roles in leading robotics journals and public demonstrations at international conferences. As founding partner of Next-Generation-Robotics spin-off, Leonardis bridges academic research and commercial applications in railway inspection robotics, reflecting his commitment to translational impact.

Mathias BrothView profile

Professor

• Multimodal Interaction Analysis
• Human Communication
• Spoken Language Studies
• +4 more

Professor Mathias Broth at Linköping University's Department of Culture and Society (IKOS) specializes in multimodal interaction analysis, examining how humans coordinate communication through speech, gestures, and environmental cues. His research spans interaction in traffic environments, preschool mobility practices, and language-culture dynamics. Develops multimodal interaction analysis methodologies Studies traffic interaction between autonomous vehicles and human drivers Investigates preschool children's participation in traffic safety practices Explores communication in driver training contexts Research trends focus on embodied communication, showing how people coordinate gaze, gesture, and verbal cues in real-time interactions across different environments including: Traffic situations with autonomous vehicles Preschool group movements Driver training instruction Human-robot interaction Media production scenarios Second language classrooms Broth contributes to the Language and Culture research environment while supervising PhD students in interaction studies.

• Human Factors Engineering
• Ergonomics
• Virtual Reality in Training & Education
• +5 more

Shuchi Deb is an Associate Professor of Industrial, Manufacturing, and Systems Engineering at the University of Texas at Arlington, where she has served since 2019 and was promoted to Associate Professor in September 2024. She directs an active, grant-funded research program that blends human-factors engineering, virtual & augmented reality, and transportation safety to improve human-system interaction across manufacturing, education, and public-safety domains. Education: Ph.D. in Industrial & Systems Engineering, Mississippi State University, 2017 M.S. in Industrial and Management Engineering, Montana State University, 2014 B.Sc. in Industrial and Production Engineering, Shahjalal University of Science & Technology (Bangladesh), 2006 Research & Innovation: Deb’s scholarship focuses on human-centred design of complex socio-technical systems. She exploits immersive technologies—virtual, augmented and mixed reality—to study and enhance safety, training transfer, and user experience in contexts ranging from automated-vehicle interactions and cyclist–infrastructure compatibility to additive-manufacturing education and police reality-based training. Her work repeatedly integrates psychophysiological sensing (EEG, eye-tracking, facial-expression analysis) with usability engineering to create adaptive, trustworthy human-machine interfaces. Recent federally supported projects include an NSF grant to build a bilingual VR platform for additive-manufacturing education ($837 k), a USDOT project developing a driver-readiness monitor for prolonged automated driving, and a Department of Justice award with the Fort Worth Police Department to create VR-based reality training scenarios ($269 k). These grants exemplify her translational approach: coupling rigorous human-factors experimentation with deployable technological solutions. Scientific Recognition: Outstanding Contribution & Mentorship Award, UT Arlington (2024) Best Graduate Student Paper, Mississippi State University (2017) IIE/FlexSim Simulation Competition Winner (2016) SEMS Best Student Paper, IISE (2016) Annual Ergonomics Design Competition, Auburn University (2015) Advising & Grant Leadership: Deb has chaired or served on more than a dozen Ph.D. and M.S. thesis committees and mentored over twenty undergraduate researchers. Since 2019 she has attracted > US $2.3 million in external funding as PI or Co-PI, supporting a broad cohort of graduate researchers who disseminate their work annually at ASEE, IISE, HFES, TRB, and AHFE conferences. Labs & Teams: She founded and advises the Human Factors Lab at UT Arlington, a shared facility equipped with VR headsets, motion-capture systems, driving and cycling simulators, and psychophysiological recording suites. The lab collaborates with industry (Fort Worth Police, local manufacturers) and across campus (Computer Science, Mechanical & Aerospace Engineering) to provide interdisciplinary training to students.

• Human-Computer Interaction
• 3D User Interfaces
• Gesture Recognition
• +3 more

Dr. Ravin Balakrishnan is a leading figure in Human-Computer Interaction at the University of Toronto, Canada. With over 163 publications from 1994-2023, his work spans 3D interfaces , gesture recognition , mobile computing , and collaborative systems . He received the CHCCS 2020 Achievement Award for his contributions. Key research areas: Human-Computer Interaction, 3D User Interfaces, Tactile Displays, Mobile Computing Major awards: CHCCS 2020 Achievement Award Collaborators: Tovi Grossman, Daniel Wigdor, Karan Singh Publication Trends (2023-2006): 2023: Interactive camera robots for video capture 2022: Swarm robotics for physical demonstrations 2021: Drone tour interfaces and VR navigation 2020: Telepresence drones and volumetric displays 2019: Multimedia education tools 2016: Dual-screen interaction and tactile feedback 2011: Curve sketching and children's interfaces 2008: Spherical displays and tactile widgets 2006: Volumetric display techniques His work bridges academic research with real-world applications in education, accessibility, and collaborative environments. Publications in top venues like CHI, UIST, and ACM Transactions demonstrate sustained impact in interaction design.

Marina KollmitzView profile

Researcher

• Autonomous Robot Navigation
• Human-Robot Interaction
• Force Compliance
• +3 more

Marina Kollmitz is a researcher at the Autonomous Intelligent Systems group within the Department of Computer Science at the University of Freiburg, Germany. She works in the Faculty of Engineering and focuses on robotics research with applications in hospital environments, particularly through the NaRKo project on compliant service robots for logistics in hospitals. Dr. Kollmitz completed her PhD in 2020 at the Autonomous Intelligent Systems group under the supervision of Prof. Dr. Wolfram Burgard at the University of Freiburg. Prior to her doctoral studies, she earned her Dipl.-Ing. in Mechanical Engineering from Leibniz University Hannover between 2007 and 2015, establishing a strong foundation in engineering principles that informs her robotics research. Her research focuses on Autonomous Robot Navigation , Human-Robot Interaction , and Force Compliance in robotic systems. She has pioneered work in detecting people and recognizing their mobility aids (wheelchairs, crutches, walking frames, etc.) using deep learning techniques. Her research enables robots to navigate safely and appropriately in human environments by understanding contextual cues about the people they encounter. She has developed specialized computer vision systems that can operate effectively in complex hospital settings where understanding human mobility needs is critical for safe robot operation. Dr. Kollmitz's publication record demonstrates a clear research trajectory from foundational work on social navigation to sophisticated deep learning approaches for 3D perception. A consistent theme across her work is the practical application of robotics in healthcare settings, with a particular emphasis on developing systems that can safely interact with people who have varying mobility needs. Her MobilityAids project has resulted in a significant contribution to the field with a publicly available dataset containing over 17,000 annotated RGB-D images. During her time at the University of Freiburg, Dr. Kollmitz served as a Teaching Assistant for the Introduction to Mobile Robotics course from 2016 to 2019, contributing to the education of undergraduate and graduate students in robotics fundamentals. She has also contributed to open-source robotics software frameworks, particularly extending Facebook's Detectron system for robot perception tasks. Dr. Kollmitz is actively involved in the Autonomous Intelligent Systems research group, which develops advanced robotic systems with a focus on perception, navigation, and human-robot interaction. Her work bridges theoretical robotics research with practical healthcare applications, developing technologies that could significantly improve how service robots operate in hospitals and other care facilities while maintaining safety and appropriate social interaction.

Ben TalbotView profile

Research Fellow

• Cognitive Robotics
• Artificial Intelligence
• Robot Navigation
• +5 more

Dr. Ben Talbot is a Research Fellow at the Queensland University of Technology (QUT) , affiliated with both the Australian Centre for Robotic Vision (ACRV) and the QUT Centre for Robotics (QCR) . He earned a PhD in 2018 and a BEng (Honours I) in Electrical Engineering in 2012 from QUT. Ben specializes in cognitive robotics , artificial intelligence , and real-world robotic applications , with a focus on translating theoretical advances into practical systems. PhD , Robotics, Queensland University of Technology, 2018 BEng (Honours I) , Electrical Engineering, Queensland University of Technology, 2012 His research explores robot navigation using abstract maps , semantic SLAM , and human-inspired spatial reasoning , particularly in unseen environments . He pioneered the Abstract Map framework, which enables goal-directed exploration through symbolic spatial information. His work emphasizes open-source software like BenchBot and OpenSeqSLAM2.0 , enhancing robotics community accessibility. Ben's publications span 2013–2023, showcasing advancements in controller fusion , scene understanding , and sim-to-real transfer . Notable trends include integrating reinforcement learning with classical control and developing dynamic spatial models for navigation. Awarded Best Student Paper at ACRA 2015 and multiple Vice-Chancellor's Awards in 2015, Ben also received the Dean's Scholars Award in 2009. His work has been featured in The LABS and Brisbane Times media outlets. Beyond research, Ben contributed to robotics education as Head Tutor for Advanced Robotics and Microprocessors & Digital Systems during his PhD. He actively supports active scene understanding via high-fidelity simulated environments and robust API designs, aligning with QUT's commitment to bridging classical and modern robotics.