LF Edge Akraino Release 8 Focuses on Physical AI

SAN FRANCISCO – April xx, 2025 – LF Edge, an umbrella organization within the Linux Foundation that aims to establish an open, interoperable framework for edge computing independent of hardware, silicon, cloud, or operating system, today announced the availability of Akraino Release 8 (“Akraino R8”).

About Akraino R8
Akraino R8 focuses on Physical AI, including small language models (SLMs) that facilitate human-machine interaction. Safe operating environments for humans in the presence of robots, AI agents, and other AI-driven technologies is a primary objective of Physical AI. Akraino R8 blueprints include robotics sensors and actuators, automatic speech recognition (ASR), and predictive maintenance, delivering fully functional open source edge stack "Blueprints" related to physical AI.

Robot basic architecture based on SSES
Release 8 modifications include Edge AI improvements to reduce false positives and negatives in human commands to robots in safety oriented environments, where factory or heavy equipment is involved. Specifically, an R&D version of a small language model (SLM) has been implemented to identify and correct “sound alike” word errors that occur in ASR output. The method is independent of ASR model (e.g. Kaldi, Whisper, other) and is suitable for severely constrained SWaP (size, weight and power consumption) form-factors operating either wholly or partially self-contained (i.e. disconnected from the cloud). Small form-factor, self-contained operation is crucial for robotics use cases requiring verbal communication, such as factory floor, first-responders, stalled or disabled autonomous vehicles, drones operating in remote areas.

SSES Robotics Release 8 Documentation
Signalogic and Fujitsu

Predictive maintenance of hardware :

Release 8 for Predictive Maintenance of Hardware will include first official release of the Smart Drive Monitor where PM focus is on Hard Drive failure detection. This release provides a basic framework for installing the PalC-SDM modules and AI models for failure predictions. This generic code base , model and algorithm design can be extended to support other Hardware components failure predictions in next releases.