Workshops

This tutorial aims to provide a structured introduction to the foundations and frontiers of Embodied AI (EAI), with a particular focus on the computational architectures behind robot motion generation. We begin by tracing the evolution of EAI models from early transformer-based agents to the latest vision-language-action frameworks employing diffusion and flow-matching techniques. The tutorial will dissect current action expert module architectures—token-based transformers and diffusion-based denoising models—and discuss their implications on dexterity, speed, and real-world deployment. In addition to covering state-of-the-art models such as RT-2, PaLM-E, and π-0, we explore unsolved challenges in scaling laws, OOD generalization, and real-world data bottlenecks. Finally, we invite participants into open discussions on the deeper theoretical gaps in EAI—what might be the “aerodynamics” of robotics—and how we might shape the next generation of general-purpose embodied agents. This tutorial is designed for researchers and practitioners seeking both foundational insights and forward-looking perspectives in Embodied AI.

Surgery is a broad and rapidly evolving field, increasingly embracing robotics technologies. Hundreds of innovation-driven companies are actively designing instruments and visual systems to support surgical procedures. However, while technological development continues at a fast pace, our understanding of the primary users, surgeons, and their capacity to effectively adopt and integrate these technologies remains relatively limited.

Given that the operating room is a high-risk, high-stakes environment, poorly designed robotic systems and interfaces can contribute to adverse events, compromise patient safety. To ensure safe and effective surgical performance, it is essential to consider the human factors involved in the interaction between surgeons and robotic technologies.

This tutorial will provide an overview of the physical and cognitive capacities and limitations of surgeons in the context of robotic-assisted surgery. We will explore the essential mental and physical demands required for optimal performance and highlight recent advancements in assessing surgical workload, stress, and fatigue. Real-world case studies illustrating how poor interface design has led to errors and adverse outcomes will be analyzed to emphasize the consequences of neglecting human factors.

In addition, we will present evidence-based suggestions for improving the design of human-machine interfaces to enhance usability, decision-making, and surgeon adaptability to novel technologies. Finally, we will discuss future directions in robotic and AI-assisted surgery, with an emphasis on systems that are responsive to the real-time cognitive and physical status of the surgical team.

Unmanned Aerial Vehicles (UAVs), as intelligent aerial robots that integrate perception and decision-making, play a vital role in a wide range of applications, including agricultural management, disaster relief, and urban surveillance. Leveraging UAVs for object localization, tracking, and segmentation enables effective monitoring of plant and animal growth, supports search and rescue operations, and facilitates the understanding and recognition of target behaviors. Despite significant progress, many existing models focus on a single modality, are tailored to specific tasks with limited generalization ability, and often suffer performance degradation under challenging conditions such as motion blur, extreme lighting, and target occlusion. This workshop will focus on how to build efficient and robust models for UAV-based object tracking and segmentation using visible and thermal data. During the workshop, we propose to host two winner talks from the RISEx 2025 competition and one tutorial talk on this topic.

This workshop will introduce participants to battery-free wireless sensing and intelligent RF systems with hands-on demonstrations at the University of Alberta’s Intelligent Wireless Technology (IWT) Lab. The tutorial will cover the principles of RFID-based sensing, energy harvesting, and ultra-low-power wireless communication, with applications in robotics, healthcare, smart infrastructure, and defense. Attendees will explore how AI-powered analysis and machine learning can be integrated with RF sensing to enable intelligent decision-making and adaptive robotic systems. The workshop emphasizes practical skills—participants will interact with prototype RFID sensors, observe real-time data collection, and analyze performance through modern RF measurement tools. The session is designed to encourage collaboration, inspire innovative applications in robotics, and provide graduate students and researchers with new methodologies to refine their work.

The integration of robotics and artificial intelligence (AI) is reshaping modern healthcare, bridging the gap between advanced automation and human-centered care. From robotic-assisted surgery and precision rehabilitation to AI-driven diagnostic systems and hospital logistics automation, these technologies are rapidly transitioning from research laboratories to real-world clinical environments. This workshop will explore how robotics and AI are being practically implemented across diverse domains of healthcare, enhancing surgical precision, streamlining clinical workflows, supporting remote and personalized care, and improving patient outcomes.

Participants will engage with current examples of robotic systems used in surgery, rehabilitation, and hospital support services, alongside emerging AI tools that augment clinical decision-making and patient monitoring. The workshop will also address the practical challenges in deploying these technologies, including interoperability, data governance, validation standards, and workforce integration. By highlighting both established and emerging use cases, this session aims to provide a comprehensive overview of how robotics and AI are transforming the practice and delivery of healthcare today and in the near future.