MathWorks has joined the Edge AI Foundation, a nonprofit organization focused on energy-efficient artificial intelligence for edge devices, aimed at widespread adoption of embedded AI in engineering systems.
This membership connects MathWorks to the Foundation’s network of supporters and contributors. This collaboration will focus on building AI models using MATLAB and Simulink, integrating them into system simulations, and deploying them to embedded hardware.
Edge AI runs models on devices such as microcontrollers, FPGAs, and embedded GPUs rather than relying on cloud infrastructure. This approach is promoted as a way to reduce latency, keep data local, and reduce power consumption. The foundation, formerly the tinyML Foundation, positions itself as a forum for standards, education, and industry coordination aligned with these goals.
Engineers often face constraints such as compute, memory, and power limitations when moving AI workloads from servers to embedded devices. Teams also need a way to validate how AI components operate within a broader system that includes sensors, controls, and safety requirements.
Workflow focus
MathWorks is best known for MATLAB, a programming environment widely used in engineering and science, and Simulink, a graphical environment for simulation and model-based design. The tool is described as providing an end-to-end workflow for embedded AI across training, integration, and deployment.
Simulink supports system-level simulation to test the behavior of your software before deploying it to target hardware. The tool also supports validation and validation of safety and mission-critical environments.
For deployment, MathWorks supports generation of optimized C/C++, CUDA, and HDL code from the same Simulink model. We also talked about compression techniques for resource-constrained devices and the ability to work across multiple AI frameworks, including MATLAB, PyTorch, TensorFlow, ONNX, and XGBoost.
“MathWorks joining the EDGE AI FOUNDATION strengthens our shared mission to make edge AI more accessible,” said Pete Bernard, executive director of the EDGE AI FOUNDATION.
“MathWorks, a recognized leader in embedded AI for engineering systems, offers proven capabilities for AI model integration, system-level simulation, and optimized code generation. These contributions will be invaluable to our community as we work together to accelerate advances in edge AI.”
industrial
MathWorks outlined examples of embedded AI efforts in automotive, aerospace, and industrial automation. In automotive engineering, you can use MATLAB and Simulink to create virtual sensors such as battery state of charge or motor temperature estimation. These models can run in real time on a microcontroller in a constrained environment.
In the aerospace field, the team will develop anomaly detection and predictive maintenance algorithms that can be deployed on FPGAs. Latency and safety requirements in flight-critical systems are key drivers of this approach.
In industrial automation, this tool can be used to develop defect detection algorithms for visual inspection and deployed on embedded GPUs for fast quality control.
The Edge AI Foundation describes itself as a global community for efficient and scalable edge AI technology. The company’s network includes more than 100 Fortune 500 technology companies and cites engagement across online channels and participation in tinyML education programs.
MathWorks has long had a strong influence on engineering organizations that combine control systems, signal processing, and embedded software development. Interest in embedded AI is growing as these teams incorporate machine learning into products that must operate under strict constraints such as deterministic behavior and safety guarantees.
Lucas Garcia, product manager for AI at MathWorks, said: “Joining the EDGE AI FOUNDATION is a natural extension of our commitment to empowering engineers and scientists to innovate in AI, machine learning, and edge computing.”
“Our workflow allows teams to validate AI models developed in MATLAB and PyTorch through full-system simulation, optimize them for tight compute and memory constraints, and deploy them to a wide range of embedded hardware platforms,” said Garcia.
“We look forward to working with the Foundation and its members to advance the deployment of reliable and efficient AI solutions that address real-world challenges,” he added.
