Professor Weisi Guo
Chair of Human Machine Intelligence
Head of Centre for Assured & Connected Autonomy
Head of Human Machine Intelligence Group
Visiting Fellow at the Alan Turing Institute
Cambridge: MEng, MA, PhD
Address:
Office: F411 (1st floor iMech, B83)
Labs:
AI Lab - DARTeC F105
HUMAX Lab - AIRC G008
Distributed & Causal Computing - B83 F409
Address:
Centre for Autonomous and Cyber-Physical Systems, SATM,
Cranfield University,
MK43 0AL, BEDS, UK
Email: weisi.guo@cranfield.ac.uk
Vision & Expertise - As human society is becoming increasingly interconnected, human and machine intelligence is more closely interfaced than ever. My expertise is in connected intelligence systems, comprised of: machine learning, communication networks, and socio-technical assets. In particular, I research future AI and information networks for challenging environments or tasks, whilst integrating human domain knowledge and providing trustworthy safety assurance.
Background - I obtained MEng, MA, and PhD degrees from the University of Cambridge. From 2012 to 2019, I built an award-winning team at the University of Warwick. Since 2019, I joined Cranfield University (Engineering: REF UK 2021 #7, Mech/Aero Engineering: QS Top-30 world 2022-24) at the Centre for Autonomous and Cyber-Physical Systems [Link]. Here, I lead the Human Machine Intelligence Research Group, where I work closely with the new £65m Digital Aviation Research and Technology Centre (DARTeC).
I was a Turing Fellow at the Alan Turing Institute from 2017 and remain a researcher there. I have published over 150 journal papers (total IF 900+) and 90+ IEEE/ACM conference papers, with 7000+ citations (h-index 41). My key papers include: a Nature, Nature Communication, Nature Computation Science, Nature Machine Intelligence, a top 10% cited PLOS One paper, and several cover issues in Royal Society and IEEE Transactions.
Track-record - I have been PI on over £8.1m and an investigator on over £35m of research funding. My group has been recipient of 2 Marie-Curie and 2 RAEng fellowships. I current co-lead EPSRC 6G Future Communications Hub on Distributed Computing (£3+8.5m), EPSRC Trustworthy Autonomous Systems Security Node (£3m), and was the coordinator for H2020 Data Aware Wireless Networks for IoE (€1m). I currently serve as editor on several IEEE & Royal Society journals and reviewer for EPSRC (full college), ESRC, UKRI FLF, MRC, NSF, NSERC, H2020, RAEng, Royal Society, Leverhulme, and other international grant awarding bodies. I have been an IET Innovation Award winner (2015) and been a runner-up in the Bell Labs Prize three times.
Research Expertise - I welcome engagement in the following areas (underpinning papers) [highlights]:
-
Physics informed signal processing and machine learning:
"how do we encode nonlinear physics into sensing, communication, and learning actions?"
(1) physics-driven cybersecurity (control layer security in drone swarms, graph layer in infrastructure)
(2) control physics-informed inverse learning (AI intention prediction for safety) [Nature Comm. Eng.]
(3) physical graph compression (minimal sensing in digital twins) & prediction [Nature Communication]
(4) social-physics conflict model learning with tipping dynamics (learning networked tipping points, Earth System Dynamics) [Nature] [New Scientist] [Parliament Briefing] [IPCC COP28 Global Tipping Repprt]
-
Trustworthy autonomy via explainable AI:
"how do we design autonomy to increase trust perception amongst diverse stakeholders?"
(1) neuro-symbolic models (meta-symbolic twins, control neuro-symbolic)
(2) cognitive intuitive models for diverse stakeholders (XAI for 6G)
(3) adversary robust reinforcement learning (action robust)
(4) guarantees in evolutionary optimisation [Nature Machine Intelligence, cover issue]
-
Networking in adversarial & contextual environments:
"how do we network better in challenging circumstances?"
(1) molecular communications (mutual information of fluids) [The Economist]
(2) user driven network specification and optimisation using language models (LLM enabled 6G specification, NLP contextualises blackspot)
(3) federated learning under adversarial attacks (spoofing attacks) and using tiny AI [Nature Comp. Science]
Personal Life - I have worked in an UNHCR refugee camp in N. Africa, been part of the victorious Cambridge Varsity archery team, solo climbed two of the highest sub-continent peaks (Toubkal-Atlas Mt, Jade Mt), served as badminton captains at both Cambridge (Fitz) and Sheffield Universities, and completed both the London (2007) and full Sahara (2010) full marathons. My personal interests lie in fitness, travel, photography, and world peace.