Supporting AI-powered real-time cyber-physical systems on heterogeneous platforms via hypervisor technology

The heavy use of machine learning algorithms in safety-critical systems poses serious questions related to safety, security, and predictability issues, requiring novel architectural approaches to guarantee such properties. This paper presents an architecture solution that leverages heterogeneous platforms and virtualization technologies to support AI-powered applications consisting of modules with mixed criticalities and safety requirements. The hypervisor exploits the security features of the Xilinx ZCU104 MPSoCs to create two isolated execution environments: a high performance domain running deep learning algorithms under the Linux operating system and a safety-critical domain running control and monitoring functions under the freeRTOS real-time operating system. The proposed approach is validated by a use case consisting of an unmanned aerial vehicle capable of tracking moving targets using a deep neural network accelerated on the FGPA available on the platform.

Automated summary

This paper presents an architecture solution that leverages heterogeneous platforms and virtualization technologies to support AI-powered applications with mixed criticalities and safety requirements. The hypervisor creates two isolated execution environments, one running deep learning algorithms under Linux and the other running control and monitoring functions under freeRTOS. A use case of an unmanned aerial vehicle using a deep neural network accelerated on the FGPA is used to validate the proposed approach.