Lavindra de Silva | Department of Engineering
Department of Engineering / Profiles / Prof. Lavindra de Silva

Department of Engineering

Prof. Lavindra de Silva PhD

lpd25

Lavindra de Silva

Research Professor in Digital Roads

Academic Division: Civil Engineering

Research group: Construction Engineering

Email: lpd25@cam.ac.uk

Personal website

Publications


Research interests

Lavindra de Silva is a Research Professor in the Cambridge University Engineering Department, accomplished in AI and theoretical computer science and in transferring theory into practice. His work on AI Agents spans over 20 years of R&D, and includes contributions to both traditional and contemporary agent systems. He joined the Engineering Department in February 2019 as Research Lead on the Digital Manufacturing on a Shoestring project, after which he took on the role of Programme Director on the Digital Roads of the Future Initiative.

Prof de Silva has collaborated extensively and spearheaded scientific publications in many of the most competitive venues in Computer Science and Engineering/Robotics, with over 30 of his Computer Science papers ranked A-A* (portal.core.edu.au/conf-ranks). He has also helped build numerous systems that were either supplied or showcased to UK manufacturing SMEs, and organisations including the Defence Science and Technology Group (Australia), Department for Transport (UK), Her Majesty's Government Communications Centre (UK), National Highways (UK), and the European Space Agency (Netherlands).

Research co-led by Prof de Silva has resulted in spin-off companies as well as BBC, French, Sri Lankan and other media coverage, and de Silva and his team have received multiple prestigious international accolades such as an SCP Excellence in Collaboration Award, IET Excellence & Innovation Award, International (AI) Planning Competition victory, AAAI award for outstanding scientific committee contributions, as well as awards for best papers and robotic system innovations.

Prof de Silva's focus has been on building provably correct, explainable, reliable, and resilient AI-based systems, through contributions to research areas including autonomous (agent) systems, automated planning and verification, robotics, digital twins, and machine learning.