Digital Twins to AI-Enabled Autonomy: Keeping Humans at the Centre of Integrated Systems  

As systems become increasingly connected, software-defined, and autonomous, organisations face the challenge of integrating new digital capabilities while maintaining confidence in system performance, safety, and usability.

This presentation explores how digital engineering, digital twins, and Human-in-the-Loop approaches can support the development, integration, and verification of AI-enabled autonomous systems. Drawing on practical experience across defence, automotive, electronics, and software-intensive environments, the session demonstrates how digital technologies can improve system understanding, support decision-making, and reduce integration risk throughout the engineering lifecycle.

Through real-world examples, attendees will see how digital twins and human-centred visualisation techniques can transform complex system data into actionable insights, helping engineers and operators better understand system behaviour and make informed decisions. The talk will also discuss lessons learned when introducing intelligent capabilities into existing systems, highlighting the importance of maintaining trust, transparency, and human oversight.

Attendees will gain practical insights into how digital engineering and AI-enabled autonomy can be successfully integrated into complex systems while keeping humans at the centre of system operation and decision-making.

Biography

Deepaa Yoharani Ganesh is a Fellow at QinetiQ, Chair of the INCOSE Systems and Software Interface Working Group, and a Visiting Lecturer and Industry Advisor at Cranfield University. With more than 30 years of experience across defence, automotive, semiconductor, and electronics industries, she specialises in digital engineering, digital twins, AI-enabled autonomy, and human-centred systems engineering. Deepaa is passionate about translating complex technologies into practical solutions that improve human understanding, decision-making, and operational effectiveness.