ESP32
Wi-Fi and Bluetooth microcontrollers for sensor nodes and small gateways.
Technologies
Grouped by the layer of the system they belong to. Names here are the stack, not a certificate or a customer list.
Connected stack
Devices, software, data, and AI models meet in one processor.
01
Devices and firmware we use when the software has to live on the hardware.
Wi-Fi and Bluetooth microcontrollers for sensor nodes and small gateways.
ARM Cortex microcontrollers for tighter timing and industrial I/O.
Linux boards for gateways, vision hosts, and ROS 2 experiments.
Firmware and other device code where memory and timing are part of the design.
02
Languages and libraries for models, data preparation, and applied automation.
The main language for data work, model code, and tools that sit beside devices.
Model development and training when the team needs to see and change the network.
Training and export when a deployment target expects that stack.
Classical models for tabular sensor and operations data.
03
Capture, classical processing, and detectors for a defined camera task.
Capture, calibration, preprocessing, and classical vision steps.
Real-time detection and counting models for known object classes.
04
Robot software and simulation used before a platform is asked to move on a real floor.
Nodes, topics, and navigation for robot software more than one person will run.
Simulation of a route, a sensor layout, and a blocked path.
05
Interfaces and APIs for operators, this website, and services that sit above the devices.
Interfaces for operators and for device dashboards added later.
This website, and a base for server-rendered product interfaces.
Python APIs between models, devices, and web applications.
06
The everyday tools for building, running, and keeping history of the software.
Repeatable services for brokers, APIs, and model runtimes.
Source history for firmware, models, and application code.
The host for gateways, build machines, and servers, including this Ubuntu setup.