Learn more about Artificial Intelligence of Things, (AIoT) on Arm with the below resources. From keynotes covering the future of tinyML, to building autonomous robots during workshops, these resources provide deep-dive technical sessions about AIoT technologies. Jump to section:
Visit our YouTube playlist and watch all the AIoT Dev Summit tech talks and event highlight video.
Endpoint AI for IoT
Explore the latest additions to the Arm AI platform: the Cortex-M55, Arm’s most AI-capable Cortex-M processor and the Ethos-U55, the industry’s first microNPU for Cortex-M.
Scalable ML acceleration with ONNX runtime
Manash Goswami, Microsoft
Running AI/Neural networks on microcontrollers made simple with the STM32Cube.AI
Markus Mayr, STMicroelectronics
Maximize the performance of your ML platform with Arm software and tools
Ravi Mahatme, Arm
Building noise-immune speech interfaces for IoT
Chris Rowen, BabbleLabs
Pelion unified ID: the key to IoT at scale
Jerry Jun, Arm
Scaling the market with mobile IoT and security by design
Ian Smith, GSMA
A full Arm IoT stack from sensors to the cloud
Carl Perry, PacketWatch now
Getting started with a self-driving RC car
Rahul Ravikumar, GoogleWatch now
Extending ML to industrial IoT applications at the edge with AWS
Ian Perez Ponce, AWSWatch now
Listen to your data: swim builds AI models and predicts in real-time
Dr Simon Crosby, Swim.aiWatch now
From concept to production: design and optimize enterprise computer vision applications on embedded Arm devices
Dr. Nitin Gupta, Dori AIWatch now
Ci in IoT/embedded: creating a simple scalable and automated workflow
Charles McCann, ArmWatch now
Next generation ML for mobile and embedded platforms
Dr. Rajen Bhatt, QeexoWatch now
AI workflow for large scale deployment of far-edge ML devices
Mark Stubbs and Kabir Manghnani, Shoreline IoTWatch now
How we got rid of passwords in IoT
Carel Grove, ArmWatch now
Bootstrapping edge infrastructure for AIoT applications with open source software
Galem Koya, CanonicalWatch now
Robot Operating System (ROS): current and future capabilities on embedded systems
Katherine Scott, Open RoboticsWatch now
Building end-to-end ML workflows with Arm
By Austin Blackstone, Neil Tan, Wei Xiao and Gian Marco Iodice, Arm
Machine learning workflows consist of tasks including data collection, aggregation, ML model training, evaluating, fine-tuning and model deployment. Arm not only provides processors that perform complex ML workflow locally, but also SDKs and tools that enable rapid application development and optimization, as well as services that orchestrate and automate the end-to-end ML tasks.
In this series of ML end-to-end workshops, we are going to introduce how to use Pelion Device Management and Treasure Data to train, validate and deploy your ML models, run and optimize ML algorithms on CPUs, GPUs, and NPUs with Arm NN and Arm Compute Library, and use ML frameworks to push machine intelligence to the tiniest Arm MCUs.
Building end-to-end ML frameworks for IoT/endpoint applications built with Arm Pelion Device Management, Data management, and Mbed OS:
Building end-to-end ML frameworks for gateways built with Arm NN, Compute Library and Arm Cortex-A CPUs:
TinyML application development for everyone
By Sandeep Mistry, Arduino
Step through sensor data capture, training, and model deployment to build an ML application, based on data that you will sample yourself. Learn how to use your gestures to train a classifier in TensorFlow and then deploy to an Arm Cortex-M-based board running Mbed OS.
This easy-to-follow workshop focuses on gesture recognition, but the sensor sources onboard the hardware provided, include accelerometer, gyroscope, color, Ambient Light, proximity, temperature, humidity, and pressure.
Privacy-focused voice AI in intelligent robotics
By Samreen Islam, Carlos Chacin and Alfred Gonzalez-Cuzan, MATRIX Labs
We are at a point in time when voice AI is integrating seamlessly into our lives. We have them in our homes, on-the-go through our phones, and increasingly embedded into our everyday devices- headphones, cars, and TVs to name a few.
It should come as no surprise that voice-control for robots is also becoming increasingly popular due to its hands-free and potentially conversational nature, whether it be with a humanoid, robot arm, or autonomous rover. This workshop goes over how you can easily employ a privacy-focused voice assistant, Snips, with MATRIX devices, an edge, and IoT development platform that is powered by Arm microcontrollers and Xilinx FPGAs, to quickly deploy an effective voice-enabled robot of your choice, complete with sensors, feedback loops, and motor control.Access workshop
Get started with drone development on PX4
PX4 is the open-source flight control stack for drones, rovers and other autonomous robots. It's the de-facto standard for open source drone development. In this workshop, you will see the different components of a standard quadcopter, then use developer tools and SDK to do basic programming to enable the drone to be an IoT device and intelligent sensor platform. This workshop was delivered by Auterion and NXP.
Agora – develop, deploy, and maintain devices profitably
By Garrett LoVerde, Embedded Planet
Embedded Planet introduces a general-purpose hardware platform and guide to deploy application-specific IoT devices on budget and on time. Agora is a multi-connectivity, multi-sensor IoT development platform that enables prototyping of Cellular, Bluetooth, and LoRaWAN applications. It also has seven sensors.
During this workshop, learn how to:
- Ease development with a versatile MCU-based IoT hardware platform that is driven by Mbed OS
- Develop intelligent applications that transform environmental factors such as temperature humidity, air quality, audio, proximity, and force into Information
- Discover the value add for business utilizing this information
- Go to production immediately with the preconfigured subset of the development kit that most closely meets your application need
- Go to production at scale with a fully customized subset of the development kit that matches your application need most optimally
End-to-end security with Arm-based edge devices and IoTeX blockchain
By Raullen Chai, IoTeX
Trusted Tracker is a GPS and environmental tracking device, developed by IoTeX with Arm TrustZone and CryptoCell technology. This workshop provides an overview of the hardware components of Trusted Tracker with an Arm Cortex-M33 processor with Arm TrustZone and Arm CryptoCell-310 security subsystem, Connectivity module (LTE-M, NB-IoT), and sensors. It introduces the high-level design of IoTeX blockchain, including system architecture, trusted computing framework, smart contracts, and core APIs and then showcase end-to-end security architecture of Trusted Tracker.Download workshop
Secure IoT with Mircochip and Kinibi-M
By Richard Hayton, Trustonic
In this session, you learn how to program a MicroChip SAML11 microcontroller to generate secure messages that a server or cloud can validate came from your device and can decrypt and display. The session covers an introduction to Kinibi-M and the steps that are required to write the Secure on-device code to talk to your PC or a provided cloud service.
Unlock the potential of IoT security with Microsoft's Azure Sphere
By Brian Willess, Avnet
As billions of new devices are connected, organizations need to secure them to help protect data, privacy, physical safety, and infrastructure. In this hands-on Azure Sphere workshop, you can learn how this new security solution has integrated hardware, software, and cloud to provide a turnkey solution for IoT devices.
Build your own Harry Potter wand with TensorFlow Lite Micro
By Pete Warden (Google), Kirk Benell and Rob Reynolds (SparkFun) and Scott Hanson and Arpit Shah (Ambiq Micro)
This is an experiential workshop that focuses on the use of TensorFlow Lite on a low-power microcontroller to perform machine learning. Modalities that are covered include word recognition in speech; gesture recognition using accelerometer values; and human presence detection using imagery.
The workshop covers machine learning model training, deployment, and operation, with a majority of time that is spent on a gesture-recognition activity, “Magic Wand”, that is based on the content of Pete Warden’s book, TinyML: Machine Learning with TensorFlow on Arduino and Ultra-Low-Power Microcontrollers.Download workshop
Containers in an IoT world: how Docker can make it easier to deploy your application on an edge device
By Jenny Fong (Docker) and Maurizio Caporali and Alessandro Genovese (SECO)
The growth of Arm-based devices in recent years is exponential. Last year alone, Arm, and its partners have shipped 23 billion Arm processors. With such growth in Arm devices, IoT and embedded software developers are looking for easier and more scalable ways of creating portable code which can be deployed easily on different platforms while reducing the time to market.
With the partnership between Arm and Docker, it is now possible to easily build and deploy containerized applications everywhere from edge to cloud, this allows software developers to scale from a PoC to a manageable and robust IoT solution.
During this workshop you will gain hands-on experience in developing and deploying a reusable Docker application on an IoT device. You will also learn about specific benefits containerization has over more classical software development approaches.
Ahead of accessing the workshop, please complete this survey by SECO.Access workshop
AI on Adafruit's edge badge
By Alex Glow, Hackster
Watch this video and play with the Adafruit Edge Badge! This demo will show the "Micro Speech" demo — using TensorFlow with Arduino.
Changing the landscape of AIoT
Artificial Intelligence of Things, (AIoT) is a combination of AI and IoT to achieve more efficient and smarter connected technologies. The term AIoT is the convergence of these two technologies helping to take artificial intelligence into all commercial and social sectors, enhancing business operations and making our world more efficient.
Watch the panel session with industry experts to see how we can change the landscape of AI and IoT together.
Arm Innovator Program
Stay in touch and do not miss out on future events. Get access to more AIoT resources from Arm and our ecosystem partners.
Arm AIoT developer contest
Join the AIoT Dev Contest for the chance to win $3,000 in cash and $1,000 in Ponoko credits. Share with the developer community what you have learnt about AIoT on Arm, and how this can be used to solve real-world problems in innovative ways.