Keynotes

Keynote 1

Nirmalya Roy, Professor of Information Systems, University of Maryland, Baltimore County (UMBC)

Building Resilient Edge Intelligence for Autonomous Search and Rescue Robotics

Abstract

In this talk, I will present research from my group over the past several years on the design, implementation, and validation of robust machine learning models for autonomous robotic systems supporting search and rescue operations in disaster-prone environments. I will begin by introducing a collaborative federated learning framework for resource-constrained IoT devices and robotic platforms that enables distributed training and intelligent decision-making in infrastructure-limited scenarios. Next, I will discuss a camera-based physiological sensing system that leverages multi-task learning, self-supervised learning, generative adversarial learning and vision-language models to monitor the vital signs of victims. I will also present a view-invariant machine learning framework based on Novel Class Discovery for human action recognition in post-disaster environments to improve situational awareness and accelerate rescue operations. In addition, I will highlight our research on on-device semantic segmentation for scene understanding using active and incremental learning, autonomous navigation in unstructured environments through novel reinforcement learning approaches, and human–machine teaming methods designed to reduce operator cognitive load in cluttered and complex environments. Finally, I will showcase demonstrations, deployments, and field experiments conducted using the DoD MAGNUS and NSF TRACE Test Beds at UMBC. Overall, this talk will provide an overview of our efforts in resilient sensing, edge intelligence, and scalable machine learning for operation in challenged environments supported by multiple federal sponsors. The goal of this talk is to highlight emerging research directions and stimulate use-inspired research and translational activities within the SmartComp community.

Speaker Profile

Nirmalya Roy is a Professor in the Information Systems Department at the University of Maryland, Baltimore County (UMBC), where he leads the Mobile, Pervasive, and Sensor Computing (MPSC) Lab. He also serves as Director of the Center for Research in Use-Inspired Cyber-Physical Systems (CYPRESS) and Associate Director of the Center for Real-time Distributed Sensing and Autonomy (CARDS) at UMBC. Dr. Roy leads several major research initiatives, including the DoD-funded MAGNUS: Advancing AI, Robotics, and Networking Research through a Multi-Domain Testbed for Defense Innovation and the NSF-funded AI-Ready TRACE: Testbed for Disaster Resilience Auditing and Crisis Evaluation at UMBC. His research focuses on applied artificial intelligence and machine learning with applications in smart health, cyber-physical systems, the Internet of Things (IoT), robotics, and autonomous systems. His research contributions have been recognized through numerous best paper awards, including IEEE/ACM DCOSS-IoT (2023), SmartComp (2023, 2022), SPIE (2022), CHASE (2021), IGSC (2020), Elsevier PMC (2020), QShine (2009), and PerCom (2006). He also serves as a co-PI on the ArtIAMAS (AI and Autonomy for Multi-Agent Systems) Cooperative Research Agreement with the Army Research Laboratory (ARL), in collaboration with the University of Maryland, College Park (2021–2026). Dr. Roy has secured approximately $7 million in external research funding from organizations including the U.S. Department of Defense (DoD), Army Research Laboratory (ARL), Office of Naval Research (ONR), National Science Foundation (NSF), Alzheimer’s Association, Constellation E2: Energy to Educate, and the UMB–UMBC Research and Innovation Partnership. His NSF-funded portfolio includes EAGER, CPS, CAREER, US–India Collaborative Research, REU Site, and GCTC programs. He received his B.E. degree in Computer Science and Engineering from Jadavpur University in 2001 and his M.S. and Ph.D. degrees in Computer Science and Engineering from the University of Texas at Arlington in 2004 and 2008, respectively. He is also the co-founder of AI Sense LLC, an early-stage startup supported through NSF SBIR/STTR Phase I funding. Additional information on his students, research projects, testbeds, and startup activities can be found through the MPSC Lab || REU SCC || CYPRESS || CARDS || TRACE || MAGNUS || AI Sense LLC.

Keynote 2

Suman Banerjee, Professor of Computer Science, UW–Madison USA

Lightweight Edge AI for Sustainability, Spectrum Sensing, Public Safety, and More

Abstract

Edge computing provides a new way to implement services with many unique advantages. While many edge computing solutions have been implemented within different network infrastructures, in this talk, we will explore ways to design a lightweight edge computing platform which is robust and portable, leading to interesting applications and services in sustainability, public safety, and many more application domains.

Speaker Profile

Suman Banerjee is the David J. DeWitt Professor in Computer Sciences at UW-Madison where he is the founding director of the WiNGS laboratory which broadly focuses on research in wireless and mobile networking systems. He is the inaugural recipient of the ACM SIGMOBILE Rockstar award and a recipient of the NSF Career Award. He is a recipient of multiple award papers at various conferences, such as ACM MobiCom, ACM CoNEXT, and IEEE Dyspan. Further, technology developed by Prof. Banerjee have won various accolades including the first prize at the Wisconsin Governor's Business Plan Competition in 2011 and in the Interdigital Innovation Challenge in 2012. He was a co-founder of multiple startups, including StratusWorx (acquired by Ericsson in 2020), and OnTracMD (merged with MiCarePath in 2022). He served as the chair of ACM SIGMOBILE between 2013 and 2017. He is a fellow of the ACM and of the IEEE.