Hosted by Arduino & Qualcomm

World’s First VENTUNO Q Workshop by Arduino & Qualcomm

Qualcomm's IQ8 Running 40 TOPS. On-Device ROS2 Motor Control by STM32. One board. 

Get your hands on the new Arduino VENTUNO Q, the first Qualcomm-powered SBC to bridge the gap between heavy-duty Edge AI and precision robotics. Don't miss the world’s first live demo!

Experience the future of autonomy. Join us for the world’s first hands-on workshop with the Arduino VENTUNO Q, the ultimate all-in-one SBC for advanced robotics. With 40 TOPS via the Qualcomm IQ8 and native ROS2 support, it’s the only board that pairs elite edge AI with the precision of an STM32H5 for real-time motor control. Join our workshop to see it in action.

Date: Monday 06/08/2026

Time: 10:00 AM - 12:00 PM | 2:30 PM - 4:30 PM

Hosted By: Arduino & Qualcomm

Hosted by NXP

Discrete NPUs meet GenAI at the Edge by NXP, featuring i.MX and the Ara240, a 40 eTOPS DNPU now available for hands-on edge AI development

For the first time, the NPU team at NXP invites you to join us for a one-day, developer-focused hackathon, with real hardware (FRDM-IMX95 PRO and 2x Ara240 DNPUs, over 80 eTOPS of edge AI compute!!!) at your fingertips. 

The workshop has 2 themes, and we encourage participants to come in teams, work alone, or be prepared to make new friends and collaborate as we build together on "Edge AI for Nature" and "Physical AI Everywhere". 

Each team will get one day access to a board, all necessary software, and the latest open-source genAI models (LLMs, VLMs) from partners.

Date: Tuesday 06/09/2026

Time: 10:00 AM - 12:00 PM

Hosted By: NXP

Hosted by NXP

Discrete NPUs meet GenAI at the Edge by NXP, featuring i.MX and the Ara240, a 40 eTOPS DNPU now available for hands-on edge AI development

For the first time, the NPU team at NXP invites you to join us for a one-day, developer-focused hackathon, with real hardware (FRDM-IMX95 PRO and 2x Ara240 DNPUs, over 80 eTOPS of edge AI compute!!!) at your fingertips. 

The workshop has 2 themes, and we encourage participants to come in teams, work alone, or be prepared to make new friends and collaborate as we build together on "Edge AI for Nature" and "Physical AI Everywhere". 

Each team will get one day access to a board, all necessary software, and the latest open-source genAI models (LLMs, VLMs) from partners.

Date: Tuesday 06/09/2026

Time: 2:30 PM - 4:30 PM

Hosted By: NXP

Hosted by Avnet & Infineon

Build, Sense, and Visualize featuring the Infineon PSOC™ Edge

Join Avnet for a hands-on workshop exploring how to accelerate the development and deployment of edge AI and embedded systems. From hardware selection to system integration and scaling to production, this session will walk through practical approaches, tools, and real-world use cases. Attendees will gain actionable insights into building efficient, reliable solutions that bridge the gap between prototype and deployment in today’s rapidly evolving Physical AI landscape.

Date: Monday 06/08/2026

Time: 10:00 AM - 11:00 AM

Hosted By: Avnet & Infineon

Hosted by Alif Semiconductor

Deploy Intelligent Applications Efficiently at the Edge

Date: Monday 06/08/2026

Time: 11:00 AM - 12:00 PM

Hosted By: Alif Semiconductor

Hosted by Syntiant

Voice-First Smart Frames: Deploying Always-On Edge AI in Consumer Wearables

Smart glasses are emerging as a new category of edge AI devices where voice becomes the primary interface to cloud intelligence. However, building practical wearable systems requires solving several challenges simultaneously: ultra-low power budgets, continuous sensing, real-world noise environments, and seamless integration with cloud AI services.

This workshop explores the design and deployment of voice-first smart glasses powered by ultra-low-power edge AI processors. Participants will learn how always-on neural inference enables natural voice interaction while maintaining privacy, low latency, and multi-day battery life.

Using commercially available smart frames as a demonstration platform, the session will walk through the architecture of a production wearable system, including:

• Always-on wake word detection running continuously on-device

• Environmental noise suppression and voice enhancement

• Running AI models within sub-milliwatt power budgets

• Integrating edge inference with cloud AI services

• Scaling edge AI from prototype development to production hardware

The workshop will include a live demonstration of smart frames, illustrating how edge AI enables seamless interaction with AI assistants while keeping sensitive data local to the device.

The techniques discussed are broadly applicable across wearables, interactive headsets, AI home hubs, and robotics, highlighting how always-on edge AI is enabling the next generation of intelligent devices.

Date: Monday 06/08/2026

Time: 2:30 PM - 3:30 PM

Hosted By: Malik Moturi - Syntiant Corp.

Hosted by Mathworks

Verifying AI models before they reach the Edge

At the edge, mistakes are expensive. Once an AI model is optimized, compiled, and connected to real sensors, failures are harder to diagnose. Ensuring that AI systems behave as intended, and avoiding unintended or unsafe behavior, is therefore critical—particularly in safety‑ and mission‑critical applications. 

Meeting this challenge requires AI verification approaches that explicitly increase confidence in model behavior beyond what empirical testing alone can provide. In practice, AI verification combines complementary techniques that address uncertainty and risk at different stages: formal methods enable rigorous, design‑time reasoning about model behavior under bounded uncertainty; uncertainty quantification techniques such as conformal prediction help assess when model outputs should be trusted; and runtime monitoring supports detection of out‑of‑distribution or anomalous behavior once systems are deployed. Together, these approaches provide structured, evidence‑based confidence in AI systems before and during edge deployment. 

In this interactive, hands‑on workshop, you will learn how to apply AI verification techniques, with a focus on formal methods, to build confidence in neural network behavior before deployment. The workshop introduces formal verification methods that provide mathematically grounded guarantees about model behavior. Using real examples from aerospace and automotive applications, participants will see how formal verification complements simulation and testing to support more reliable edge AI deployment decisions

Date: Monday 06/08/2026

Time: 3:30 PM - 4:30 PM

Hosted By: Lucas Garcia, PhD - Mathworks

Hosted by Ikerlan

HYDRA: A Modular and Automated Platform for AI Model Optimization and Benchmarking on Edge Devices

Deploying AI models on Edge devices requires a careful balance between performance, resource consumption, and application-specific constraints. However, data scientists often lack visibility into the limitations of resource-constrained hardware, resulting in a time-consuming, iterative process with IoT/Edge engineers to adapt models for deployment. Furthermore, selecting the optimal Edge hardware is complex due to the diversity of devices and architectures, and existing benchmarking tools do not offer a unified or scalable approach for performance evaluation. To address these challenges, we present an Edge AI Model Validation and Benchmarking Platform, which streamlines model evaluation, optimization, and deployment decision-making for Edge AI applications. 

The platform enables users to upload AI models, define validation plans with resource constraints (CPU/RAM limits, GPU usage), and apply optimization techniques such as quantization and pruning using automated optimization pipelines. It provides real-time monitoring of key performance metrics—including inference latency, memory footprint, and computational efficiency—and supports both embedded and non-embedded processors for accurate cross-device comparisons. A core innovation is the automated model-device matching system, which ranks hardware configurations based on weighted performance metrics, ensuring that AI models are deployed on the most suitable devices. 

This solution has immediate applicability in IoT, autonomous systems, and industrial AI, where performance, latency, and efficiency are critical. We invite researchers, engineers, and industry stakeholders to engage with Ikerlan to explore how this platform can address their Edge AI deployment needs and contribute to broader adoption of intelligent systems at the Edge.

Date: Tuesday 06/09/2026

Time: 10:00 AM - 11:00 AM

Hosted By: Julen Arratibel - Ikerlan

Hosted by Siemens

Bridging IT and OT: Deploying Edge AI in Industrial Automation

Join Siemens for a practical workshop on building and deploying intelligent systems at the intersection of industrial automation and AI. This session will explore how to integrate edge computing, real-time data, and AI models into operational environments—bridging the gap between IT and OT. Through real-world use cases and tools, attendees will gain insights into creating scalable, reliable, and secure solutions that drive efficiency and innovation in modern industrial systems.

Date: Tuesday 06/09/2026

Time: 11:00 AM - 12:30 PM

Hosted By: Siemens

Hosted by Avnet, STMicroelectronics, Farnell, and EBV Elektronik

Accelerate your AIoT adoption with /IOTCONNECT™ and AIoT Craft

Date: Tuesday 06/09/2026

Time: 2:30 PM - 3:30 PM

Hosted By: Avnet, STMicroelectronics, Farnell, and EBV Elektronk

Hosted by Ultralytics

Computer Vision at the Edge: Training and Deploying Ultralytics YOLO Models Across Real Hardware

Through hands-on Python code, participants will train Ultralytics YOLO models, including the latest YOLO26, across a comprehensive set of computer vision tasks: object detection, instance segmentation, pose estimation, oriented object detection (OBB), image classification, multi-object tracking, and open vocabulary detection. 

Open vocabulary models extend traditional detection beyond fixed category lists, enabling flexible recognition driven by natural language, a powerful paradigm for real-world deployment scenarios. 

A significant portion of the workshop is dedicated to the full edge deployment pipeline, and we will not shy away from its complexity. Compiling a model for edge hardware is rarely a straightforward process. It involves understanding the specific constraints of each target platform, navigating toolchains that differ significantly across vendors, managing quantization precision and its impact on accuracy, handling operator compatibility issues, and validating that the compiled model behaves as expected on device. We will walk through this process step by step, demystifying quantization, compilation, and hardware-specific model export so that attendees come away with a realistic and practical understanding of what production edge deployment actually involves. 

The workshop goes beyond slides and code. Attendees will have access to physical edge hardware devices brought directly to the session, as well as live online connections to additional platforms, allowing participants to witness real inference performance across multiple chips firsthand. 

This includes platforms such as STMicroelectronics STM32N6, Intel OpenVINO, DeepX, Axelera, NVIDIA Jetson, and many more. Rather than simply showing benchmark numbers, we will demonstrate how these results are achieved and how attendees can replicate the same process on their own hardware targets using the Ultralytics ecosystem.

In addition, the workshop will feature contributions from hardware and software partners operating at the frontier of edge AI. These partners will share insights into the engineering work behind their platforms, covering topics such as NPU architecture, vendor-specific SDK toolchains, model optimization strategies tailored to their hardware, and the practical lessons learned from deploying vision models at scale on constrained devices. This gives attendees a rare opportunity to engage directly with the teams building the chips and tools that power modern edge AI systems. Participants will leave with working code, hands-on deployment experience across multiple real hardware platforms, and a solid and honest framework for navigating the full complexity of bringing Ultralytics YOLO models from training to the edge in their own projects.

Target Audience

Machine learning engineers, computer vision practitioners, embedded systems developers, and hardware engineers interested in production edge AI deployment across diverse platforms.

Prerequisites

Basic familiarity with Python and deep learning concepts. No prior experience with Ultralytics or edge deployment required.

Date: Tuesday 06/09/2026

Time: 3:30 PM - 4:30 PM

Hosted By: Franceso Mattioli - Ultralytics

Media Credentials Request Form

Questions or Support on EDGE AI London 2026? Email Us events@edgeaifoundation.org

EDGE AI Youtube 

EDGE AI Instagram

EDGE AI LinkedIn

EDGE AI Discord