Find Academic Supervisors

Kevin LeahyView profile

Assistant Professor

• Autonomous Systems
• Formal Methods
• Multi-Agent Systems
• +3 more

Kevin Leahy is an Assistant Professor in the Robotics Engineering Department at Worcester Polytechnic Institute (WPI) and Director of the Automata Lab. He holds a PhD (2017) and MS (2016) in Mechanical Engineering from Boston University, along with a BA in Economics (2009). Prior to WPI, he served as a Technical Staff member at MIT Lincoln Laboratory (2017–2023), focusing on multi-agent systems, collision avoidance, and formal methods. He currently chairs the IEEE Technical Committee for Verification of Autonomous Systems. His research integrates formal methods, AI, and control theory to address challenges in autonomous systems. Key areas include decentralized control for multi-agent teams, safe reinforcement learning, and privacy-preserving control systems. His work emphasizes practical applications in robotics, such as vision-based localization and persistent surveillance for UAVs. Leahy has led projects on scalable coordination algorithms (ScRATCHeS) and developed tools for temporal logic-based motion planning. His lab, Automata, explores the intersection of formal verification, machine learning, and robotics. He has published extensively in top journals like International Journal of Robotics Research and conferences such as ICRA and CDC. Before academia, he worked in health economics consulting, analyzing treatment cost-effectiveness. He maintains active roles in the robotics community, including editorial work for Nonlinear Analysis: Hybrid Systems and service on the IEEE Verification committee.

Dimitra PanagouView profile

Associate Professor

• Motion planning
• Coordination and control
• Robotic networks
• +10 more

Dimitra Panagou is an Associate Professor with the Department of Robotics and the Department of Aerospace Engineering at the University of Michigan. She directs the Distributed Aerospace Systems and Control Laboratory (DASC Lab) located in the Ford Robotics Building, where she leads research in safe and resilient autonomy for robotic systems. Her research interests focus on motion planning, coordination and control of robotic networks, autonomous multi-vehicle systems, nonlinear systems and control, navigation and guidance, distributed/decentralized control, and dynamic coverage. Professor Panagou's work emphasizes the development of planning, learning and control methods to address real-world, safety- and time-critical problems through provably correct solutions. Her research spans nonlinear systems, decision making under constraints and uncertainty, estimation and learning, mission planning, and networked control systems with applications across aerial, ground, marine, and space domains. Professor Panagou's recent publications (2024-2025) demonstrate a strong focus on control barrier functions, safety-critical control, resilient multi-robot systems, and risk-aware navigation. Her work bridges theoretical foundations with practical applications in autonomous systems, with particular emphasis on providing mathematical guarantees for safety and performance. The research spans multiple domains including aerial vehicles, marine systems, and ground robotics, addressing challenges in uncertain environments and under various constraints. Professor Panagou has received several prestigious awards including: NASA Early Career Faculty Award AFOSR Young Investigator (YIP) Award NSF CAREER Award IEEE TCAC Best Student Paper Award (for work from her lab) She has been invited to deliver a plenary talk at CDC 2024 and a keynote talk at ICRA 2025, highlighting her prominence in the control and robotics communities. Her research is supported by multiple grants from agencies including NASA, NSF, and AFOSR. The Distributed Aerospace Systems and Control Laboratory (DASC Lab) is equipped with state-of-the-art facilities including a fleet of UAVs (Hummingbirds, Firefly, and Solos), a high-precision motion capture system with 14 VICON cameras, drone LiDAR, and various sensors. The lab conducts both indoor and outdoor flight experiments, with permission for outdoor flights over the Wave Field at the University of Michigan's North Campus.

Xiaobo Sharon HuView profile

Professor

• Circuit Design
• Architecture Design
• Energy-Aware Systems
• +7 more

Xiaobo Sharon Hu is the Leo E. and Patti Ruth Linbeck Professor of Engineering in the Department of Computer Science and Engineering with a concurrent appointment in the Department of Electrical Engineering at the University of Notre Dame. She currently serves as a Program Director at the National Science Foundation (since November 2022) while maintaining her faculty position at Notre Dame. Her research focuses on circuit and architecture design with emerging technologies, energy and reliability aware system design, and resource management for real-time embedded systems. Her work spans processing-in-memory architectures, secure hardware design, and real-time scheduling theory. Her research benefits from close collaborations with device experts and has resulted in over 450 referred publications. Professor Hu's recent publications demonstrate strong activity in compute-in-memory architectures, secure hardware design, and real-time wireless networking. Her work bridges the gap between circuit design and system-level considerations, particularly focusing on energy efficiency and security. She has made significant contributions to elastic scheduling theory and has been instrumental in connecting the real-time systems community with the design automation community. Her scientific achievements have been recognized with numerous awards: 2024 IEEE TCRTS Outstanding Technical Achievement and Leadership Award Fellow of the Association for Computing Machinery (ACM) 2023 IEEE/ACM William J. McCalla ICCAD Best Paper Award 2023 Marie R. Pistilli Women in Engineering Achievement Award Best Paper Awards from ISLPED (2018), NanoArch (2009), and DAC (2001) NSF CAREER Award (1997) Professor Hu has mentored numerous graduate and undergraduate students throughout her career, with many alumni now holding positions at leading technology companies including Apple, Amazon, Google, IBM, and Qualcomm. She has served in significant leadership roles including Editor-in-Chief of ACM Transactions on Design Automation of Electronic Systems (2020-2024), General Chair of DAC 2018, and Technical Program Chair of IEEE Real-Time Systems Symposium 2019.

• Industrial Automation
• Human-Robot Collaboration
• Industry 4.0
• +4 more

Dr. Åsa Fasth Berglund is an active researcher at Chalmers University of Technology within the Production Systems department. Her work focuses on industrial digitalization, human-automation collaboration, and Industry 4.0 implementation strategies. She leads multiple research initiatives funded by VINNOVA and the European Commission, with 30+ documented projects since 2006. Her core research explores: Cognitive automation frameworks for manufacturing operators Human-robot co-production systems Extended reality (XR) applications in industrial settings Digital work instruction methodologies Sustainable and flexible production system design Publication analysis reveals consistent focus on Industry 4.0 technologies since 2016, with recent emphasis on operational flexibility, human-robot collaboration, and digital twins. Her work frequently combines empirical case studies with technical implementation frameworks. Dr. Berglund has secured significant research funding including: DIH World (EU Commission, 2020-2023) FAKTA Automation (VINNOVA, 2019-2022) Stena Industry Innovation Lab (Stena Foundation, 2018-2020) 5G-Enabled Manufacturing (VINNOVA, 2018-2020) She co-leads the Production Systems research group and established the Stena Industry Innovation Lab at Chalmers, focusing on applied industry solutions. Current projects investigate digital twins for sustainable manufacturing and AI-driven cognitive automation.

Boyuan ChenView profile

Researcher

• Artificial Intelligence
• Machine Learning
• Robotics
• +6 more

Boyuan Chen is a research scientist at OpenAI and MIT's Department of Electrical Engineering and Computer Science (EECS), specializing in world models, reinforcement learning, and embodied AI. His work bridges AI systems with physical world understanding through innovative approaches to video generation, spatial reasoning, and robotic control. PhD in EECS from MIT with a minor in philosophy Bachelor's degree in computer science and mathematics from UC Berkeley His research focuses on: World Models: Developing architectures like Diffusion Forcing Transformer to enable stable long-horizon video generation and planning Embodied AI: Advancing spatial reasoning capabilities in Vision-Language Models (SpatialVLM) for robotics applications Reinforcement Learning: Creating self-supervised methods for cross-task transfer learning and soft robot control Key article trends: 2025: History-Guided Video Diffusion for flexible temporal conditioning 2024: Diffusion Forcing combining next-token and sequence-level modeling 2024: SpatialVLM introducing 3D spatial reasoning to vision-language models 2023: Self-supervised RL transfer using random features 2021: 3D keypoint learning for robotic control Advising & Collaborations: PhD advisors: Prof. Russ Tedrake and Prof. Vincent Sitzmann (MIT) Undergraduate mentor: Prof. Pieter Abbeel (UC Berkeley) Industry internship: Dr. Fei Xia (DeepMind) Robotics & Team Leadership: Co-founder of MIT's Robomaster ICRA challenge team Founder of high school's first FRC team Developer of personal robots like Autonomous Bogie Rover and Autonomous Drone

• Wireless Communications
• Machine Learning
• Network Optimization
• +4 more

Zelin Ji is a Visiting Professor at the School of Electronic Engineering and Computer Science, Queen Mary University of London. His work focuses on advanced wireless communication systems, machine learning applications in networking, and optimization of resource allocation in distributed and semantic-aware networks. Key areas of research include reconfigurable intelligent surfaces, federated learning, device-to-device communications, and energy-efficient solutions for next-generation networks. His research explores cutting-edge technologies such as deep reinforcement learning for power optimization, transfer learning for signal processing, and meta federated learning frameworks. He contributes to improving network efficiency through semantic-aware collaborative systems and computational offloading strategies. Zelin Ji holds no listed academic awards but demonstrates expertise in interdisciplinary fields merging electrical engineering, computer science, and artificial intelligence. His current role involves visiting academic engagements without part-time designation. While no specific grants or student advisees are documented, his publications reflect a strong focus on theoretical and applied research in wireless communication systems and network optimization.

• Robotics
• Artificial Intelligence
• Control Theory
• +7 more

Roya Firoozi is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Waterloo, Canada. She holds a Ph.D. in Control Theory from UC Berkeley (2021) and a Postdoctoral Research position at Stanford University's Multi-Robot Systems Lab (2024). Her research focuses on advancing safe robot autonomy in interactive environments through generative AI, distributed optimization, and game theory. Key areas include multi-agent systems, autonomous vehicles, and perception-driven control. Education: Ph.D. in Control Theory, UC Berkeley (2021) Bachelor's in Mechanical Engineering, UC Berkeley (2014) Postdoctoral Research, Stanford University (2024) Research Interests: Robotics-aided generative AI, multi-modal perception, interactive autonomy in multi-agent systems, game-theoretic optimization, and safe navigation in dynamic environments. Her work bridges theoretical foundations with real-world experiments in robotics and autonomous systems. Awards: NSF Postdoctoral Research Fellowship ASEE Fellowship (2021-2023) Rising Stars in Aerospace Engineering (2022) Outstanding Graduate Instructor Award (2021) Advising & Grants: Currently supervising graduate students (PhD/Master's) focused on robotics and control systems. Research is supported by grants from NSF and industry collaborations. She has pioneered algorithms for distributed multi-vehicle coordination and occlusion-aware navigation systems. Labs & Teams: Leads the Autonomous Systems Lab at Waterloo, focusing on robotics, AI, and control. Collaborates with Stanford's Multi-Robot Systems Lab and UC Berkeley's MPC Lab on projects involving autonomous vehicles and fault detection systems.

Jörn HeesView profile

Professor

• Data Science
• Deep Learning
• Anomaly Detection
• +3 more

Prof. Jörn Hees is a Professor for Data Science at the Department of Computer Science, Hochschule Bonn-Rhein-Sieg (H-BRS), and serves as Chairman of the Computer Science Faculty Council. He is affiliated with the Institute for Artificial Intelligence and Autonomous Systems (A2S) and the Institute of Technology, Resource and Energy-efficient Engineering (TREE). His research focuses on Data & Graph Mining, Deep Learning, Anomaly Detection, Explainable AI, and AI-assisted education (e.g., automated grading systems). He teaches courses such as Stochastics, Data Analysis and Visualization, Artificial Intelligence (Bachelor level), and Deep Learning Foundations, Natural Language Processing (Master level). His work bridges theoretical advancements with practical applications in finance, remote sensing, and education. Notable projects include federated outlier detection systems (Fin-Fed-OD), the TreeSatAI benchmark dataset for tree species classification, and AI-driven grading solutions using LLMs. His publications emphasize anomaly detection techniques, multimodal fusion, and interpretable machine learning. Despite no explicit awards listed, his contributions to AI education and computational methods are evident through his extensive publication record. He coordinates research teams and advises on infrastructure for AI education and infrastructure monitoring via Earth observation data.

• Massive MIMO
• Aeronautical Communications
• Optimization Algorithms
• +4 more

Jiankang Zhang is a Senior Lecturer in Computer Science at Bournemouth University, UK. He previously held positions at the University of Southampton (Senior Research Fellow) and Zhengzhou University (Lecturer/Associate Professor). His research focuses on massive MIMO , aeronautical communications , optimization algorithms , and edge computing , with applications to UAV networks, visible light communication (VLC), and physical layer security. Education: PhD in Communication and Information Systems (Zhengzhou University, 2012), BSc in Mathematics and Applied Mathematics (Beijing University of Posts and Telecommunications, 2006) His recent work explores reconfigurable intelligent surfaces (RIS) for secure transmissions, UAV-assisted networks , and multi-agent reinforcement learning for resource allocation in NOMA-V2X systems. He contributes to IEEE journals as an Associate Editor and Guest Editor. Scientific Awards: IEEE Senior Member (2018), Outstanding Associate Editor (IEEE Access, 2020), Workshop Chair (IRSCN), Guest Editor roles His article trends emphasize 5G/6G , secure wireless communication , machine learning-aided network optimization , and UAV mobility , with a focus on balancing security vs. efficiency in next-generation networks.

Vladimir MilovanovićView profile

Associate Professor

• Electrical Engineering
• Computer Science
• Signal Processing
• +7 more

Dr. Vladimir Milovanović is an Associate Professor at the Faculty of Engineering, University of Kragujevac, Serbia, holding a position as Chair of the Department of Electrical Engineering and Computer Sciences. His academic career is anchored in interdisciplinary research at the intersection of electrical engineering, computer science, and biomedical applications. His research focuses on hardware design, radar sensor systems, biomedical signal processing, and machine learning applications. Notable areas include CMOS circuit design, FPGA-based implementations, and parameterizable hardware generators for signal processing tasks. He also explores medical imaging analysis using deep learning techniques for conditions like disc hernia diagnosis. Recent work emphasizes radar technology (FMCW transceivers, signal processing architectures), embedded systems (FPGA development, IP core utilization), and high-performance streaming data algorithms. His publications span over two decades, demonstrating expertise in analog/digital circuit design, comparative classifier analysis in biomedical contexts, and hardware-software co-design methodologies. Dr. Milovanović collaborates with industry on energy-efficient MIMO arrays and semiconductor gas sensors. His contributions include open-source HDL models for digital signal processors and comparator circuits optimized for low-power and high-speed applications.

Chenchen LiuView profile

Assistant Professor

• High-Performance Computing
• Machine Learning
• Brain-Inspired Computing
• +3 more

Dr. Chenchen Liu is an Assistant Professor in the Department of Computer Science and Electrical Engineering at the University of Maryland, Baltimore County (UMBC). She leads the Computing Compass Laboratory and focuses on high-performance computing for machine learning, brain-inspired computing with hardware-software co-design, and novel non-volatile memory technologies. Education: Ph.D., Electrical and Computer Engineering, University of Pittsburgh, 2017 M.S., Electrical and Computer Engineering, Peking University, 2013 Research Interests: Her work emphasizes optimizing neural networks for efficiency, enhancing AI security against adversarial attacks, and advancing neuromorphic systems using memristor and ReRAM technologies. Recent publications address multi-tenant DNN inference, edge computing frameworks, and latency-aware GPU optimization. Her articles highlight innovations in neuromorphic hardware, federated learning, and defense against adversarial attacks. Ongoing efforts include designing robust AI systems for autonomous driving and edge environments.

Tony GengView profile

Assistant Professor

• Computer Architecture
• Machine Learning
• Generative AI
• +6 more

Tony Geng is an Assistant Professor at the University of Rochester, jointly appointed in the Departments of Electrical and Computer Engineering and Computer Science. He directs the IntelliArch Lab and holds secondary affiliations with the Goergen Institute for Data Science. His research spans computer architecture, generative AI, graph intelligence, and high-performance computing, focusing on sustainable and efficient artificial general intelligence. His work integrates hardware-software co-design for accelerating machine learning workloads, with applications in scientific discovery, fintech, and social media. Recent projects explore dynamical systems for graph learning and diffusion models for scientific simulations. Notable recognitions include multiple DOE and NSF research awards, the Excellence in Graduate Teaching Award, and substantial GPU allocations from NERSC for generative AI research. He actively mentors PhD students and postdocs in sustainable AI development.

Mingzhe ChenView profile

Assistant Professor

• Machine Learning
• Wireless Networks
• Federated Learning
• +7 more

Mingzhe Chen is an Assistant Professor and John S. and James L. Knight Foundation Chair in Data Science and AI at the University of Miami's Department of Electrical and Computer Engineering. He holds affiliations with the Frost Institute for Data Science and Computing. His research focuses on machine learning for wireless networks, federated learning, semantic communications, and UAV applications. He earned his Ph.D. from Beijing University of Posts and Telecommunications (2019), with postdoctoral work at Princeton University and Virginia Tech. Education: Ph.D., Beijing University of Posts and Telecommunications (2019) Postdoctoral Research, Princeton University (2019–2021) Visiting Researcher, Virginia Tech (2016–2019) Research Interests: Machine learning for wireless systems, federated learning fundamentals, semantic communication, UAV networks, and VR over wireless. Recent work emphasizes 6G advancements, digital twins, and secure AI-driven networks. Awards: IEEE Marconi Prize Paper Award (2023) IEEE Katherine Johnson Young Author Award (2023) NSF grants for projects on 6G, digital twins, and secure AI (2022–2024) Advising & Grants: Supervises PhD students including Dongyu Wei and Hanzhi Yu. Secured NSF funding for initiatives like "3D HARMONY" (CNS Core) and "Untethered Extended Reality" (NewSpectrum). Active in organizing IEEE conferences (e.g., WFIOT 2025, MILCOM 2025). Labs & Teams: Leads research groups focusing on AI-driven wireless networks and collaborates with Ericsson Research. His lab explores digital twin synchronization, federated learning, and semantic feature multiple access (SFMA) systems.

Will BranfordView profile

Professor

• Solid State Physics
• Nanotechnology
• Magnonics
• +4 more

Will Branford is a Professor of Solid State Physics at Imperial College London's Department of Physics within the Faculty of Natural Sciences. He holds roles as Head of Community for Matter and Co-director of the School of Human and Artificial Intelligence. His research focuses on the interplay between structure, geometry, and magnetic/electronic properties of materials, particularly in nanoscale magnetic textures, artificial spin ice, and neuromorphic computing. Key affiliations include the London Centre for Nanotechnology and the Experimental Solid State Physics Group. He explores applications in magnonics and neuromorphic systems, emphasizing energy-efficient computation. His work leverages nanofabrication to manipulate material properties, such as spin waves and magnetic metamaterials. Recent studies include optical control of magnetic states, spin-orbit coupling in hybrid nanowires, and neuromorphic training in network lasers. His contributions address challenges in reconfigurable magnonic crystals and magnetic memory integration. Branford's research also extends to interdisciplinary areas like retinomorphic vision systems and physical reservoir computing packages (e.g., PRCpy). His articles highlight advances in magnetic writing techniques, spin wave dynamics, and device-agnostic network optimization. Collaborative efforts span condensed matter physics, nanotechnology, and artificial intelligence.

Boris SedlakView profile

Researcher

• Distributed Systems
• Edge Computing
• Service-Oriented Computing
• +5 more

Boris Sedlak is a PostDoc Researcher and Ph.D. student in the Distributed Systems Group (DSG) at TU Wien, Austria. His research focuses on ensuring runtime requirements in large-scale computing systems through causal inference and active inference concepts, with applications in edge computing, vehicular networks, and distributed systems governance. Education: Ph.D. in Computer Science (Ongoing) at TU Wien, funded by the TEADAL EU Horizon project. M.Sc. in Software Engineering & Internet Computing (Distinction) at TU Wien (2018–2022). B.Sc. in Media Informatics at FH St. Pölten, Austria (2015–2018). Research Interests: Boris specializes in distributed computing continuum systems, active inference for system equilibrium, causal inference in distributed environments, edge computing elasticity, and privacy-preserving data stream processing. He explores applying neuroscience-inspired concepts to computing systems for adaptive and self-organizing solutions. Key Projects: TEADAL (2022–2025): Focuses on federated and trustworthy data lakes in distributed systems. INTEND (2024–2026): Investigates intelligent service adaptations through active inference. AloTwin (2023–2025) and FogProtect (2020–2022): Address edge computing security and data governance. Recent Contributions: Boris has published extensively on adaptive stream processing, SLO-aware task offloading in vehicular platoons, and equilibrium models using active inference. His work bridges causal reasoning and system design, emphasizing scalable solutions for heterogeneous edge infrastructures. Advisory & Collaboration: Supervises bachelor/master theses and actively collaborates on topics involving service-level objectives, causal models, and edge intelligence. He has presented at ICSOC, IEEE Edge Computing, and AIoTwin Summer School.