Periodic Reporting for period 2 - A-IQ Ready (Artificial Intelligence using Quantum measured Information for realtime distributed systems at the edge)
Reporting period: 2024-01-01 to 2024-12-31
The A-IQ Ready project aims to establish a strong, autonomous, and resilient Europe through disruptive technologies. By developing an Edge Continuum Orchestration for AI, the project provides a resource-efficient, low-energy distributed system infrastructure for multi-agent applications utilizing advanced sensor technologies, AI, and machine learning. This infrastructure addresses critical challenges in civil safety, digital health, and logistics, contributing to the advancement of digital society 5.0.
The project focuses on integrating AI and quantum sensors across various domains to demonstrate their capabilities and compare them with existing solutions. Key objectives include developing system designs, architectures, and simulators for demonstrators, enhancing real-time edge systems, and creating computational hardware and algorithms for AI-driven perception, control, and diagnostics. The expected impact includes increased EU competitiveness, improved trustworthiness, and enhanced sensing, with a strong emphasis on human-machine interfaces and ethical AI.
The project focuses on integrating AI and quantum sensors across various domains to demonstrate their capabilities and compare them with existing solutions. Key objectives include developing system designs, architectures, and simulators for demonstrators, enhancing real-time edge systems, and creating computational hardware and algorithms for AI-driven perception, control, and diagnostics. The expected impact includes increased EU competitiveness, improved trustworthiness, and enhanced sensing, with a strong emphasis on human-machine interfaces and ethical AI.
WP2 focused on system design, architecture development, and digital twin simulations for demonstrators, ensuring alignment with project objectives. In RP1, efforts centered on defining use cases, requirements, and initial designs. By RP2, all objectives were met, and deliverables were submitted, marking the successful completion of WP2.
WP3 progressed with sensor and electronic component evaluations, initial testing, and compact quantum sensor development under extreme conditions, refining requirements for WP1 and WP2.
WP4 advanced AI-driven control and diagnostics, targeting edge and HPC applications. Early-stage work in RP1 transitioned to hybrid computing platform development in RP2, including demonstrators for autonomous transport, digital health, and quantum sensor integration for motor control.
WP5 addressed technology integration in SCs, overcoming challenges in quantum sensor placement and AI application. RP1 established coordination efforts, while RP2 focused on merging requirements into demonstrators for WP6 testing.
WP6 launched at the end of RP2, with substantial progress expected in future phases.
WP7 initiated dissemination efforts in RP1, establishing communication channels, branding, and online presence. By RP2, 15 scientific publications were produced, reflecting the project’s research contributions.
WP3 progressed with sensor and electronic component evaluations, initial testing, and compact quantum sensor development under extreme conditions, refining requirements for WP1 and WP2.
WP4 advanced AI-driven control and diagnostics, targeting edge and HPC applications. Early-stage work in RP1 transitioned to hybrid computing platform development in RP2, including demonstrators for autonomous transport, digital health, and quantum sensor integration for motor control.
WP5 addressed technology integration in SCs, overcoming challenges in quantum sensor placement and AI application. RP1 established coordination efforts, while RP2 focused on merging requirements into demonstrators for WP6 testing.
WP6 launched at the end of RP2, with substantial progress expected in future phases.
WP7 initiated dissemination efforts in RP1, establishing communication channels, branding, and online presence. By RP2, 15 scientific publications were produced, reflecting the project’s research contributions.
For autonomous work machines to operate effectively in mixed-fleet production environments, full technological acceptance is necessary to ensure that operational risks are mitigated across different domains. Risk mitigation strategies must be adaptable and cost-efficient while maintaining safety. Additionally, human operators must have reliable monitoring systems to oversee machine operations and respond to potential risks. Initial efforts focused on developing concepts for monitoring, adapting status information for operators, and ensuring the resilience of monitoring functions under critical conditions.
WP2 contributed significantly to advancing system design, digital twins, and AI applications across multiple domains. RP1 focused on defining demonstrator architectures, interfaces, and conducting state-of-the-art studies. By RP2, WP2 achieved notable advancements in quantum sensing, hybrid computing, and real-time fault detection. The introduction of ontology-driven AI for digital health and the standardization of AI models ensures scalability and industrial applicability, positioning these technologies for broader impact.
WP3 concentrated on defining sensors, components, and architectures for different use cases. While the first year primarily involved preliminary evaluations, the second year allowed for more concrete advancements. These developments will become more tangible as integration progresses in subsequent reporting periods.
WP4 worked on AI-driven control and diagnostics. Early efforts involved studying existing approaches and defining novel solutions beyond the current state of the art. By RP2, quantum sensor experiments were conducted under laboratory conditions, focusing on miniaturization and customization. These efforts aim to enable practical applications such as localization in tunnels and motor control diagnostics, bringing quantum technology closer to real-world deployment.
WP5 focused on the integration of quantum sensors into automotive applications. While significant progress has been made in developing and improving the Q-sensor, challenges remain, particularly in miniaturizing the sensor head and managing the complexity of excitation and reading equipment. These obstacles must be addressed before full integration into vehicle systems is feasible.
WP7 played a key role in communication and standardization efforts. During RP1, foundational work was carried out, including engagement with relevant standardization committees and working groups. By RP2, scientific impact was demonstrated through multiple research publications, solidifying the project’s contributions to advancing AI and quantum technologies in industry.
WP2 contributed significantly to advancing system design, digital twins, and AI applications across multiple domains. RP1 focused on defining demonstrator architectures, interfaces, and conducting state-of-the-art studies. By RP2, WP2 achieved notable advancements in quantum sensing, hybrid computing, and real-time fault detection. The introduction of ontology-driven AI for digital health and the standardization of AI models ensures scalability and industrial applicability, positioning these technologies for broader impact.
WP3 concentrated on defining sensors, components, and architectures for different use cases. While the first year primarily involved preliminary evaluations, the second year allowed for more concrete advancements. These developments will become more tangible as integration progresses in subsequent reporting periods.
WP4 worked on AI-driven control and diagnostics. Early efforts involved studying existing approaches and defining novel solutions beyond the current state of the art. By RP2, quantum sensor experiments were conducted under laboratory conditions, focusing on miniaturization and customization. These efforts aim to enable practical applications such as localization in tunnels and motor control diagnostics, bringing quantum technology closer to real-world deployment.
WP5 focused on the integration of quantum sensors into automotive applications. While significant progress has been made in developing and improving the Q-sensor, challenges remain, particularly in miniaturizing the sensor head and managing the complexity of excitation and reading equipment. These obstacles must be addressed before full integration into vehicle systems is feasible.
WP7 played a key role in communication and standardization efforts. During RP1, foundational work was carried out, including engagement with relevant standardization committees and working groups. By RP2, scientific impact was demonstrated through multiple research publications, solidifying the project’s contributions to advancing AI and quantum technologies in industry.