Topic Questions
Why do you think Edge AI has grown so much over the past 5 years?
- Edge AI has grown because devices are generating more data, and companies increasingly need to turn that data into useful intelligence. At the same time, hardware and AI models have become smaller, faster, and more efficient, making AI practical on edge devices. Processing data locally also reduces latency, bandwidth, cloud costs, and security concerns. Overall, it’s the combination of greater demand for smarter devices, improved technology, and the benefits of local processing.
What are some examples of smart devices that consumers may have at home?
-
Examples of smart home devices include smart thermostats such as Ecobee, smart refrigerators, smart doorbells, and security cameras.
-
AI can make these devices more useful by recognizing specific activity and reducing unnecessary alerts. For example, a smart doorbell can distinguish between people, vehicles, and animals, providing notifications only when relevant. Adoption of these technologies can also vary by region and culture.
What are the right metrics for developers to be looking for?
- Developers should evaluate edge AI platforms across performance and power efficiency, cost, software/developer experience, reliability and supply longevity, and vendor support. While TOPS is an important measure of AI capability, the best platform is one that can move efficiently from prototype to a cost-effective, reliable, and supportable production product.
What constraints are you seeing as bottlenecks for Edge AI deployment?
-
The main bottlenecks for Edge AI deployment are engineering adoption, uncertainty around AI, and market fragmentation. Traditional embedded engineers may still be hesitant or unfamiliar with incorporating AI into their systems, while the broad and sometimes overwhelming scope of AI can lead some companies to delay or pause adoption.
-
In addition, the rapid proliferation of AI tools and diverse hardware architectures has created fragmentation, making it difficult for companies to determine which technologies and approaches to adopt. As engineers gain experience and the market matures, organizations will need time to navigate these options and identify the right path forward.
What applications are the most demanding for Edge AI?
-
The most demanding Edge AI applications are those that require real-time processing of sensor, perception, and generative AI data directly on devices, often in high-volume or high-stakes environments. Key examples include arc-fault detection, vibration and other time-series sensor analysis, computer vision such as license-plate detection, and audio processing. These applications can span industries from agriculture and industrial systems to military communications and consumer products.
-
An emerging and potentially much larger area is multimodal Edge AI, which combines sensors, vision, audio, and generative AI/LLMs to interact with the physical world. For example, Edge AI can enable hands-free, contactless control of anesthesia machines, where reliability, low latency, privacy, and continuous operation are critical. Overall, the most demanding applications are moving toward systems that combine perception, real-time decision-making, and human interaction at the edge, particularly in environments where cloud connectivity is impractical or where latency and reliability are essential.
What is Physical AI and how is it different from traditional Edge AI?
-
Physical AI refers to AI systems that can not only perceive and interpret the physical world but also take action within it. Traditional Edge AI has primarily focused on perception, such as analyzing sensor data for anomalies or using computer vision to identify people or objects, with humans or other systems ultimately responsible for responding. Physical AI adds the ability to act through actuators such as robotic arms, motors, or autonomous vehicles - for example, a rover understanding a command and physically moving an object.
-
The key distinction is that Physical AI moves from “seeing and informing” to “seeing, reasoning, and acting.” Because these systems must operate autonomously and safely in the real world, they generally require significantly more computation and more sophisticated safety controls. Examples include humanoid robots, autonomous mobile robots, robotic manipulators, and self-driving vehicles.
YouTube Video Sources
If you would like to watch this video or any other Let’s Talk Technical Series, please utilize the sources below.
Video on this Topic
Let’s Talk Technical: Edge AI Part 2, From Smart Devices to Physical AI | DigiKey
Other Videos from this Series
Let’s Talk Technical Playlist - YouTube
Suppliers Featured in Video
NXP Semiconductors
NXP enables secure connections and infrastructure for a smarter world, advancing solutions that make lives easier, better and safer. As the world leader in secure connectivity solutions for embedded applications, NXP is driving innovation in the secure connected vehicle, end-to-end security and privacy and smart connected solutions markets.
STMicroelectronics
STMicroelectronics is a global independent semiconductor company and is a leader in developing and delivering semiconductor solutions across the spectrum of microelectronics applications. An unrivaled combination of silicon and system expertise, manufacturing strength, Intellectual Property (IP) portfolio and strategic partners positions the Company at the forefront of System-on-Chip (SoC) technology and its products play a key role in enabling today’s convergence trends.
Microchip Technology
Microchip Technology Inc. is a leading provider of microcontroller and analog semiconductors, providing low-risk product development, lower total system cost and faster time to market for thousands of diverse customer applications worldwide. Headquartered in Chandler, Arizona, Microchip offers outstanding technical support along with dependable delivery and quality.
Silicon Laboratories
Silicon Labs is the leading innovator in low-power wireless connectivity, building embedded technology that connects devices and improves lives. Merging cutting-edge technology into the world’s most highly integrated SoCs, Silicon Labs provides device makers with the solutions, support, and ecosystems needed to create advanced edge connectivity applications. Headquartered in Austin, Texas, Silicon Labs has operations in over 16 countries and is the trusted partner for innovative solutions in the smart home, industrial IoT, and smart cities markets.
Nordic Semiconductor
Nordic Semiconductor is a fabless semiconductor company specializing in short-range wireless and low-power cellular IoT. Nordic pioneered ultra-low-power wireless and helped develop Bluetooth Low Energy, a widely-adopted wireless technology. The company’s award-winning Bluetooth LE solutions have made it the market leader, and are complemented by ANT+, Thread, and Zigbee products. Nordic’s reputation is built on the supply of leading-edge wireless technologies and development tools that shield designers from RF complexity. This approach extends to Nordic’s latest technology, cellular IoT. Launched in 2018 after four years of development, this NB-IoT and LTE-M solution leverages cellular infrastructure to extend the IoT.