Imagimob Edge AI now compatible with AURIX™ MCU family

Autonomous and automated driving rely heavily on Edge AI systems equipped with machine learning capabilities and processors or MCUs capable of handling large volumes of data in parallel, securely, and in real time.

Thomas Boehm, Senior Vice President Microcontroller at Infineon, emphasized the importance of integrating secure and reliable AI capabilities into microcontroller families to drive advancements in autonomous driving applications within the automotive industry. He stated, "Our AURIX microcontrollers are now supported by Imagimob Studio, making them accessible to developers worldwide, showcasing our leadership in innovation."

Alexander Samuelsson, CTO of Imagimob, highlighted the significance of integrating AURIX into Imagimob Studio, bringing full machine learning compatibility and capabilities to the automotive sector. This integration allows all supported use cases on the platform to be available for Infineon's AURIX microcontrollers.

Developers can leverage Imagimob Studio to create robust ML models for the Edge and deploy them onto Infineon's proven AURIX MCUs. The process involves creating machine learning models within Imagimob Studio and deploying them directly onto the MCUs within the platform. Users are guided through seamless deployment steps, simplifying the implementation of machine learning on MCUs and enabling the development of sophisticated ML models.

Imagimob Studio also provides a sample project for siren detection, showcasing model creation and deployment. By utilizing the code example, users can learn to create acoustic models with AURIX MCUs and a microphone shield. Additionally, Imagimob has introduced new regression models for calculating remaining battery power, health status, and usage time.

The AURIX TC4x scalable MCU family offers a smooth upgrade path from the AURIX TC3x family of ASIL-D compliant automotive MCUs. Enhanced performance is driven by the next-generation TriCore™ 1.8, with the AURIX TC4x featuring a scalable accelerator suite comprising a parallel processing unit (PPU) and multiple intelligent accelerators to facilitate cost-effective AI integration. These advancements in the AURIX TC4x family enhance machine learning capabilities, enabling developers to deploy multiple models simultaneously or more complex ones. For example, while the AURIX TC3x can manage basic siren detection, the AURIX TC4x allows for simultaneous siren detection and voice interaction.