Maxence Boels

I am a postdoctoral researcher in the Prorok Lab at the University of Cambridge, working with Prof Amanda Prorok. My research focuses on enabling swarm coordination for aerial robotic systems on custom-designed and built quadrotors. Drawing on my background in surgical video understanding and robotics, I develop vision-based perception and control algorithms that allow multi-agent systems to coordinate in real time. Previously, I completed my PhD in Surgical AI at King's College London (2021–2025) on surgical workflow prediction in robotic surgery, supervised by Prof. Sebastien Ourselin.

Curriculum Vitae | |

mboels/neural-interface-106

visitor@neural-interface-106:~$

Research Interests

Multi-Agent Aerial Robotics

Vision-based perception and control algorithms for autonomous multi-agent quadrotor systems flying fast through cluttered indoor environments with real-time multi-agent coordination and collision avoidance.

The work spans the whole stack: a CUDA kernel for policy training, a C++ onboard control loop and comms, and custom quadrotors built from CAD and 3D-printed frames through power budgeting to flight-stack bring-up.

PhD Research (KCL, 2021–2025)

Surgical Video Understanding: Recognising surgical anatomical structures and procedural steps—instruments, organs, gestures, and phases— from long and complex surgical videos using deep learning models [ LoViT ],
Expert Imitation Learning: Generating and mimicking expert-level surgical workflows by learning from expert demonstrations using video recordings for planning and decision-making in surgical procedures [ SuPRA | SWAG ],
Workflow Discovery and Planning: Selecting optimal next surgical actions through reasoning and planning about expected future rewards using reinforcement learning, and discovering optimal surgical workflows that maximise desired procedural outcomes for patients, searching for new pathways beyond expert demonstrations [ DARIL ].