Find Academic Supervisors

Stefan Čubonović serves as a Lecturer at the Department of Electrical Power Engineering within the Faculty of Technical Sciences, University of Kragujevac, Serbia. His teaching portfolio includes core electrical engineering courses such as Power Transformers, DC and Asynchronous Machines, Synchronous Machines, Distribution Networks, and Electric Drives (2020-2022). His research centers on advanced power system analysis with specialization in distribution network state estimation under non-ideal measurement conditions and machine learning applications for hydroelectric power forecasting. Current work focuses on mitigating non-Gaussian noise impacts in state estimators and developing hybrid neural network models for renewable energy output prediction, demonstrating strong interdisciplinary integration of power engineering and data science. Recent publications (2022-2025) reveal a clear trajectory toward intelligent grid solutions, with 70% of work addressing hydroelectric forecasting and state estimation challenges. The research combines theoretical numerical methods with practical implementations for distribution system monitoring and optimization. Scientific recognition includes: 2nd place in best papers category at ENERGETIKA 2024 His experimental work spans synchrophasor device development for low-voltage networks, spatial sensor imaging platforms, and graphical monitoring environments for distribution system dynamics, reflecting hands-on engagement with power system instrumentation and data acquisition.

• Electrical Power Engineering
• Power Systems
• Smart Grids
• +3 more

Ruohan Zhang is a postdoctoral researcher at Stanford Vision and Learning Lab , Stanford Institute for Human-Centered Artificial Intelligence , and Wu Tsai Human Performance Alliance . They will join Northwestern University , Department of Computer Science in Fall 2026. Research Focus: Human-centered artificial intelligence Robotic manipulation and learning Human-robot interaction Brain-machine interfaces Neuroscience-inspired AI Key Contributions: Developed BEHAVIOR Robot Suite for whole-body manipulation tasks Created UAD framework for unsupervised affordance distillation Advanced Chain-of-Modality approach for multimodal robotic learning Recent Scientific Awards: Wu Tsai Human Performance Alliance Fellowship (2022-24) AAAI/SIGAI Doctoral Consortium Scholarship (2019) Google AR/VR Research Award (2017-18) College Continuing Fellowship (2014-17) Teaching & Service: Organizer of ICCV, ECCV, NeurIPS workshops Instructor for CS231n: Deep Learning for Computer Vision at Stanford (2023) Teaching Assistant experience in Computational Brain , Machine Learning , and Discrete Mathematics at Stanford and UT Austin

• Robotics
• Human-Robot Interaction
• Brain-Machine Interface
• +5 more

Danfei Xu is an Assistant Professor at the School of Interactive Computing, College of Computing, Georgia Institute of Technology, and a part-time Research Scientist at NVIDIA AI. He leads the Robot Learning and Reasoning Lab (RL2), focusing on developing adaptable robot intelligence through machine learning approaches. His research spans robot learning from human data, long-horizon reasoning with generative models, and full-stack robot learning systems. Education: Ph.D. in Computer Science, Stanford University (2015-2021) B.S. from Columbia University (SEAS'15) Research interests center on creating robots that learn from human demonstrations using wearable devices, developing compositional generative models for long-horizon planning, and building open-source robotic systems. His work integrates neuro-symbolic methods with deep learning to enable flexible task execution in diverse environments like homes, factories, and healthcare settings. Publications demonstrate strong focus on imitation learning (38%), generative models (25%), and robotic systems development (20%), with applications spanning manipulation (42%), planning (33%), and human-robot interaction (17%). Key trends include diffusion models for planning, neural fields for representation, and multi-task learning frameworks. Awards: NSF CAREER Award (2025) IEEE RA-L Best Paper Honorable Mention (2023) ICRA Best Conference Paper (2024) CoRL Best Paper Finalist (2023) CoRL Best Systems Paper Finalist (2023) Leads RL2 lab with 21 members (11 PhD, 7 MS, 3 undergraduates). Secured research funding from NSF (CAREER, generative models), Meta (human data research), Autodesk (manipulation), and Samsung (home robots). Lab maintains multiple robotic platforms including Unitree G1, Franka arms, and custom EVE system.

• Robotics
• Machine Learning
• Robot Learning
• +3 more

Prof. Majid Khadiv is a Professor for AI Planning in Dynamic Environments at the Technical University of Munich (TUM), appointed in September 2023. He is affiliated with the TUM School of Computation, Information and Technology and the Munich Institute of Robotics and Machine Intelligence (MIRMI), where he leads research at the intersection of artificial intelligence and robotics. His educational background includes: PhD from K. N. Toosi University of Technology (2017) Prof. Khadiv's research focuses on planning, control and learning for robotic systems, with an emphasis on locomotion and manipulation. His work aims to develop theoretical frameworks that enable loco-manipulation systems to autonomously interact with environments and continuously learn from these interactions. His research spans both theoretical development and experimental validation on real robotic systems, particularly in the domains of humanoid robotics and legged locomotion. His recent publications demonstrate a consistent focus on advancing robotic control through the integration of model-based optimization, machine learning, and physical understanding of robot dynamics. Key themes include locomotion planning, contact dynamics, uncertainty handling, and the development of robust control frameworks that can operate in real-world environments with physical constraints. His notable scientific achievements include: Outstanding Reviewer Award, IEEE Robotics and Automation Letters (2023) Best Paper Award, IEEE-RAS Technical Committee on Model-based optimization for robotics (2022) 4x Internal Max Planck institute grants (Grassroots) (2019-2022) Prof. Khadiv has extensive experience in both academic research and practical robotics development. During his PhD, he led the dynamics and control team for the Iranian national humanoid robotics project, Surena III. From 2018-2023, he worked as a research scientist at the Max Planck Institute for Intelligent Systems. His research has received significant grant support, including multiple internal Max Planck Institute grants. While specific student advising information isn't detailed in the provided materials, his position as a professor at TUM suggests he supervises graduate students in robotics and AI. Prof. Khadiv is affiliated with the Munich Institute of Robotics and Machine Intelligence (MIRMI), which serves as The AI Mission Institute (AIM) at TUM. His laboratory work focuses on developing and testing algorithms on real robotic systems, with particular emphasis on validation of theoretical frameworks in practical settings. His team likely includes researchers working on various aspects of robot control, planning, and learning, contributing to TUM's broader mission in robotics and artificial intelligence.

• Robotics
• Artificial Intelligence
• Robot Control Systems
• +3 more

Shreyas Kousik is an Assistant Professor in the Woodruff School of Mechanical Engineering at the Georgia Institute of Technology, affiliated with the College of Engineering. He leads the Safe Robotics Lab, focusing on translating mathematical safety guarantees to real-world robotic systems through uncertainty modeling and collision avoidance methods. Education: Ph.D. in Mechanical Engineering, University of Michigan (Advisor: Prof. Ram Vasudevan) B.S. in Mechanical Engineering, Georgia Institute of Technology (Advisor: Prof. Antonia Antoniou) Research Focus: His work bridges autonomy theory and practical implementation, specializing in: (1) Real-time safety verification for robotic systems, (2) Reachability-based trajectory design under uncertainty, (3) Neural network applications for safe control, and (4) Human-centered robotic interactions. Primary methodologies include zonotope-based reachability analysis, model predictive control, and imitation learning frameworks. Publications: Recent works demonstrate strong emphasis on safety-critical applications including manipulator control (2025), bipedal social navigation (2024), and autonomous vehicle planning (2023). Predominant themes include real-time verification, uncertainty quantification, and integration of learning-based methods with formal guarantees. Technical Contributions: Developed open-source tools including the Reachability-based Trajectory Design (RTD) framework and robot simulator. Contributes to robotics infrastructure through GitHub repositories focused on trajectory optimization and control implementations.

• Robotics
• Autonomy
• Collision Avoidance
• +6 more

Dr. Ning Ma is a Lecturer in Medical Computing at the Department of Computer Science , University of Sheffield, with a dual appointment as an Academic Directorate of Medical Imaging and Medical Physics at the Sheffield Teaching Hospitals NHS Foundation Trust. He holds a PhD in hearing-inspired automatic speech processing from the University of Sheffield and earned his first degree in Computer Science from South China University of Technology. Member of Pervasive Computing and Speech and Hearing research groups Research Theme Co-Director for Healthcare Data/AI at the Insigneo Institute His research focuses on speech and hearing technologies applied to healthcare , particularly in developing AI systems for acoustic monitoring of sleep-disordered breathing and respiratory diseases . He pioneers methods for interpreting sounds and low-cost sensor data to screen conditions like obstructive sleep apnea and tuberculosis through multimodal machine learning . His recent work explores music AI and its intersection with mental health. Dr. Ma has led grants totaling over £500,000 from UKRI, MRC, EPSRC, and Innovate UK, including projects like AI-Enabled Cough Sound Analysis for TB Screening and SOMNUS: Sleep Monitoring by Unobtrusive Sensors . He serves on the Technical Programme Committee for INTERSPEECH and reviews for journals and funders. He is a member of the British Sleep Society , British Thoracic Society , and IEEE . His publications (over 60 peer-reviewed papers) explore topics such as deep learning for sleep apnea screening , binaural sound localization , and noise-robust speech recognition . Notable collaborations include work with Guy Brown on home-based OSA detection and with Tu Zhen on hearing aid optimization using differentiable hearing loss models.

• Speech and Hearing Technologies
• Machine Learning
• Healthcare
• +4 more

Dr. Midhun Parakkal Unni serves as an Academic Fellow in AI for Health at the Centre for Machine Intelligence within the School of Computer Science, University of Sheffield. His research integrates machine learning, dynamical systems theory, and signal processing to develop clinically deployable AI solutions for physiological understanding and prediction, with specific applications in neuromuscular control and wearable medical technologies. His academic foundation includes a PhD in Applied Mathematics from the University of Exeter, where he developed AI models for Parkinson's gait analysis and motor abnormality prediction. Professional experience spans research roles at the University of Manchester and TCS Innovation Labs, focusing on distribution shift mitigation in machine learning, human-in-the-loop methodologies, and dynamical systems modeling for cardiovascular pathologies. Dr. Unni's research program centers on creating uncertainty-aware and interpretable machine learning systems grounded in mechanistic physiological understanding. Key focus areas include: Healthcare AI Development : Building robust clinical AI systems that address real-world challenges like data distribution shifts between training and deployment environments Wearable Technology Integration : Analyzing physiological time-series data from sensor networks for continuous health monitoring Mathematical Modeling : Developing dynamical systems frameworks to mechanistically explain physiological processes Interpretable AI : Ensuring clinical meaningfulness through uncertainty quantification and human-AI collaboration He actively seeks collaborations with clinicians and researchers in AI for health, physiological modeling, and digital health tool development. While his profile indicates no current advisees or specific grants, he operates within the Centre for Machine Intelligence's collaborative ecosystem focused on translating AI innovations into practical healthcare solutions.

• Artificial Intelligence for Healthcare
• Physiological Modelling
• Dynamical Systems
• +5 more

Dr. Rui Paulo Pinto da Rocha is an Associate Professor in the Department of Electrical and Computer Engineering at the University of Coimbra, with dual affiliation at the Institute of Systems and Robotics (ISR) since 2000. His career spans 15 years of academic leadership and 19 years of active research in cooperative robotics. Key affiliations include: Senior Member of IEEE (since 2021) Chair of the IEEE RAS Technical Committee on Multi-Robot Systems (since 2018) Coordinator of multiple EU-funded projects including REMOORA , EuroAGE+ , and SEMFIRE Research focuses on cooperative multi-robot systems with decentralized coordination, covering: Swarm robotics for aquatic resource monitoring Marsupial robot teams with communication constraints 3D volumetric mapping using entropy gradients Human-robot collaboration in urban fires Multi-sensor fusion for disaster response Edge computing for low-power inference Recent publications (2023-2025) demonstrate technical breadth across ROS cloud integration , semantic mapping , and human detection systems . Notable scientific contributions include: Development of Darwinian Swarm PSO algorithm Benchmarking framework for swarm exploration Communication-constrained coordination models Multi-robot patrolling optimization techniques As an educator, he supervises 2 PhD candidates and numerous MSc students, while teaching courses on autonomous systems, industrial automation, and software engineering. His laboratory leadership includes: Technical management of ISR research infrastructure (2014) Development of RACbot-RT real-time control system Advancements in multi-robot SLAM frameworks

• cooperative multi-robot systems
• decentralized coordination
• resilient autonomy
• +6 more

Dr. Vu Phi Tran is a Researcher at the University of New South Wales (UNSW) Canberra, affiliated with the School of Engineering and Technology. He serves as a Research Assistant, Teaching Staff member, and Casual Professional staff within the Trusted Autonomy research group since 2020, contributing to high-impact publications in IEEE Transactions and Elsevier journals. His educational background includes a B.E. in Automation and Control Engineering from HCMC University of Technology and Education (2010), an M.S. in Mechatronics Engineering from Asian Institute of Technology (2015), and a Ph.D. in Aerospace Engineering from UNSW Canberra (2019). He previously served as a Lecturer at HCMC University from 2010-2012. Tran’s research spans adaptive and robust control , non-linear systems , UAV swarm coordination , and neural-fuzzy control architectures . His work focuses on real-world applications including gas source localization, resilient flight control for nano-drones, and formation control under disturbances, leveraging negative-imaginary systems theory and machine learning. Recent publications demonstrate a strong trend toward multi-robot environmental monitoring and adaptive learning-based controllers for uncertain environments. His scientific achievements include: Rockwell Automation Scholarship for Engineering Excellence THE HISAMATSU PRIZE for outstanding Mechatronics performance UNSW Tuition Fee Scholarship Dean’s Award for Outstanding PhD Theses T.F.C Lawrence Prize for Aeronautical Science Tran actively serves as a reviewer for IEEE Transactions on Robotics and Vehicular Technology, while leading projects funded by DST and AFOSR grants. His current work focuses on machine learning for obstacle avoidance in robot swarms and robust flight control systems. He operates from the Autonomous System Laboratory (Building 17, Room 131) at UNSW Canberra, collaborating with international researchers on UAV-UGV interaction systems.

• Adaptive and robust control
• Non-linear control systems
• Consensus and formation control
• +3 more

Dr. Farid Breidi serves as an Assistant Professor in Mechanical Engineering Technology at Purdue University's Polytechnic Institute, specializing in Extended Reality applications, Fluid Power Modeling, and Engineering Education innovation. His interdisciplinary work bridges digital technologies with traditional engineering practices to enhance both educational experiences and industrial applications. Education: Ph.D. in Agricultural and Biological Engineering, Purdue University (2016) M.S. in Mechanical Engineering, University of Wisconsin-Madison (2012) B.E. in Mechanical Engineering, American University of Beirut (2010) Dr. Breidi's research focuses on Extended Reality applications in engineering education, technology integration for workforce development, and digital fluid power systems. His work develops immersive learning modules that transform how students understand complex engineering concepts, particularly in fluid power systems where virtual and augmented reality create safe, interactive learning environments that would be impractical in physical labs. His publication portfolio demonstrates consistent advancement in mixed reality educational tools and digital hydraulic systems, with recent work emphasizing safety training, personalized learning pathways, and electrification challenges in heavy equipment. This research trajectory shows increasing integration of sustainability considerations and industrial applicability. As Principal Investigator, Dr. Breidi has secured significant funding from the National Science Foundation (NSF) and National Fluid Power Association (NFPA) for projects advancing educational technology and fluid power innovation. His work includes developing transparent hydraulic demonstrators, miniature racing car design projects for freshmen, and digital monitoring systems for hydraulic technologies.

• Extended Reality Applications in Engineering Education
• Fluid Power Modeling and Simulation
• Technology Integration for Workforce Development
• +3 more

Karl Dietrich von Ellenrieder is a Professor of Automation at the University of Bolzano's Faculty of Engineering. His career spans institutions like Florida Atlantic University (Ocean Engineering Professor, 2003-2016) and Monash University (Research Fellow, 1998-2002). A Senior Member of IEEE Control Systems and Oceanic Engineering Societies, he serves as Editor-in-Chief Elect of the IEEE Journal of Oceanic Engineering. Education: Bachelor of Science in Aeronautics & Astronautics, MIT (1990) Master of Science in Aeronautics & Astronautics, Stanford University (1992) Doctor of Philosophy in Aeronautics & Astronautics, Stanford University (1998) Dr. von Ellenrieder specializes in nonlinear control systems for marine and aerospace vehicles, focusing on actuator constraints, disturbance observers, and trajectory tracking. His work bridges theoretical control algorithms with practical implementations in autonomous underwater vehicles (AUVs), unmanned surface vessels (USVs), and quadrotor UAVs. His 15 most recent publications (2018-2024) demonstrate expertise in: Backstepping and sliding mode control Dynamic surface control techniques Shared human-robot control systems Control barrier function safety mechanisms Actuator saturation modeling Disturbance-robust control Scientific Honors: Senior Member, IEEE Control Systems Society Senior Member, IEEE Oceanic Engineering Society Editor-in-Chief Elect, IEEE Journal of Oceanic Engineering His research has secured funding from the US National Science Foundation (Award #1526016) and involves collaborations with institutions across the USA, Australia, and Europe.

• Field Robotics
• Automatic Control
• Marine Vehicle Control
• +4 more

Dimitris Sotiropoulos is an Assistant Professor at the Department of Electrical and Computer Engineering, University of Peloponnese, specializing in Engineering Mathematics . He holds a B.Sc. in Mathematics (1995) and a Ph.D. (2005) in Mathematical Programming and Numerical Analysis. Over 20 years of higher education teaching Author/co-author of 36+ scientific articles Supervised 20+ postgraduate theses Research Interests focus on computational mathematics, global optimization algorithms, and machine learning. Specific areas include interval analysis for automatic result verification, large-scale optimization, nonlinear equation solving, and artificial neural network training. His scientific work spans sustainability assessments for aerospace components, uncertainty quantification in composite materials, and stress modeling in human-computer interaction. Articles highlight applications of interval analysis to optimization problems and neural network training improvements via BFGS methods. Teaching roles include lectures at Ionian University's Department of Informatics and University of Peloponnese's Department of Computer Science and Technology. He also serves on Hellenic Open University's Supervisory Board since 2009, mentoring postgraduate students in computational mathematics.

• Computational Mathematics
• Numerical Analysis
• Interval Analysis
• +6 more

Elmar Rueckert is a Professor at the Cyber-Physical-Systems Institute of Montanuniversität Leoben in Austria. He previously held research roles at Graz University of Technology and Technical University of Darmstadt, focusing on robotics and machine learning. PhD in Computer Science (2014), Graz University of Technology Senior Researcher and Research Group Leader, TU Darmstadt (4 years) Assistant position (3 years) at TU Darmstadt Research interests span robotics , deep reinforcement learning , SLAM algorithms , and cyber-physical systems . His work addresses challenges in autonomous navigation, tactile response prediction, and open-source robotics platforms. Recent publications highlight applications of reinforcement learning in mobile robot navigation, SLAM failure analysis in indoor environments, and ROS-based mobile robot development. Key themes include autonomous systems , machine learning robustness , and real-time decision-making .

• Robotics
• Artificial Intelligence
• Machine Learning
• +3 more

Professor Christos Politis is a Chair in Digital Technologies at the School of Computer Science and Mathematics , Kingston University London, where he serves as Director of the Digital Information Research Centre (DIRC). His research focuses span Wireless Multimedia & Networking , Cognitive Radio , 5G/4G Networks , and Emergency Communication Systems , with significant contributions to Energy Efficiency , Security Protocols , and IoT Applications . He has led 23 academics 15 postdoctoral researchers Over 40 PhD students at DIRC. With over 200 publications and two patents , his work is funded by EU and UK programs (FP5/6/7, H2020, EPSRC, Innovate UK). He consults for governmental and commercial organizations in EU, UK, Canada, Greece, Qatar, China, and Malaysia , and holds a PhD and MSc in Electrical and Electronic Engineering from the University of Surrey, along with a BEng from the University of Athens. His academic journey includes roles at Ofcom, the University of Surrey, and placements in Greece. Recent publications highlight advancements in AI-driven ECG analysis , UAV-assisted post-disaster networks , V2X security , and smart energy systems . He is a senior member of the IEEE and a UK chartered engineer.

• Wireless Multimedia & Networking
• Cognitive Radio
• 5G/4G Networks
• +7 more

Vishal M. Patel is an Assistant Professor in the Department of Electrical and Computer Engineering at Johns Hopkins University, with research focusing on signal processing, computer vision, and biomedical applications. His work bridges machine learning with medical imaging and biometrics. Ph.D. in Electrical Engineering, University of Maryland, College Park (2010) Dr. Patel's research centers on medical image analysis, surgical video processing, and bias mitigation in generative models. He develops diffusion-based frameworks for ophthalmic applications like cataract surgery analysis and nystagmus video generation, while advancing face recognition systems and image restoration techniques under unconstrained conditions. His recent work integrates vision-language models for zero-shot classification in satellite imagery and maritime surveillance. His 2025 publications reveal a strong emphasis on medical AI, particularly in surgical video understanding and neurological disease phenotyping using eye movement data. Key trends include physics-aware video generation guided by large language models, identity-preserving face restoration, and robust bias mitigation in diffusion-based synthesis. The work consistently addresses real-world challenges in medical imaging, remote sensing, and biometric security. Major recognitions include: 2016 ONR Young Investigator Award 2016 Jimmy Lin Award for Invention A. Walter Tyson Assistant Professorship Award Best Paper Awards at IEEE AVSS 2017 and IEEE BTAS 2015 Two Best Student Paper Awards at IAPR ICPR 2018 Best Poster Awards at BTAS 2015 and 2016 As an Associate Editor for IEEE Signal Processing Magazine and IEEE Biometrics Compendium, Dr. Patel shapes scholarly discourse in his field. His ONR Young Investigator Award supports high-impact research in active learning for surgical videos, while editorial roles and technical committee memberships demonstrate leadership. Though student names aren't specified, his lab trains graduate researchers in medical computer vision. Dr. Patel leads a research laboratory focused on computer vision for biomedical applications, developing frameworks like GenVOG for nystagmus video generation and StepAL for surgical step detection. The lab pioneers diffusion models for medical image synthesis, surgical skill assessment, and robust biometric systems, with strong ties to ophthalmology and neurology applications.

• Signal and image processing
• Computer vision
• Machine learning
• +2 more