Machine learning and edge computing prototype for Toradex Development Board

  • Industry High-Tech
  • Solution IoT


SaM Solutions’ and Toradex R&D labs were tasked to discover the latest edge computing and machine learning technologies. The goal was to have the latest Toradex board connect to the Amazon Cloud to apply machine learning algorithms to the data collected from the sensor using edge computing capabilities.


The edge computing prototype was created using Amazon Greengrass technologies implemented on Toradex Aster Carrier Board with Colibri Module and connected to the Amazon Cloud platform to apply machine learning algorithms to the data collected from a vibration sensor. SaM Solutions successfully built a prototype in which the sensor is attached to the DC brushless motor and passes parameters of the motor to the Toradex board. Amazon Greengrass is running on the Board and is taught to recognize the states of the motor (stop/run/malfunction) on the fly. Machine Learning model is deployed from AWS to the device using Amazon Lambda to adjust the motor behavior recognition algorithms, after which it can run on the Board standalone without connection to the Internet and AWS (as an EDGE computing device).

Toradex specializes in embedded computing technology, offering ARM®-based System on Modules (SOMs) and Customized SBCs. Complemented with direct online sales and long-term product availability, Toradex offers direct premium support and ex-stock availability with local warehouses.


Aster Carrier Board, Colibri iMX6ULL 512MB Wi-Fi, DC brushless motor, vibration sensor MPU-6050
Services & Libraries
Amazon Greengrass, Amazon Lambda, TensorFlow, Keras, Amazon SageMaker


SaM Solutions was able to institute dual technologies to create a solution that allowed a DC brushless motor to be analyzed as a standalone solution and connect a machine learning technology to a database on the internet. Toradex successfully partnered with SaM Solutions to enable a Machine Learning prototype.

For more information follow the link.

Please fill out contact information or call us directly at (857) 777‑6073