Research

Multi-Robot Planning and Control from CCTV Camera Networks

• Daniele De Martini
• Deployment , Site driven robotics

In many robotics applications, we assume that every robot must carry its own suite of sensors and powerful onboard computers to understand where it is and how to move. Our latest research, “Multi-Robot Planning and Control from CCTV Camera Networks in a Real Warehouse”, explores a different approach.

PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving

• Kyuhwan Yeon
• Autonomous driving , Memory

Scaling Robotic Infrastructure: A Case Study in Orchestration

• Daniele De Martini
• Deployment , Site driven robotics

This research project, conducted in collaboration with Omniscient Innovations Ltd, Gompels Healthcare Ltd, and the Mobile Robotics Group (MRG), explored the transition from manual container orchestration to a configuration-driven deployment model for infrastructure-led robotics.

Building-Scale Robot Navigation via a Relay of External Cameras

• Daniele De Martini
• Deployment , Site driven robotics

Most robotic navigation systems rely on a familiar stack: onboard sensors, carefully calibrated cameras, detailed maps, and expensive localisation pipelines. We wanted to explore the opposite direction: what happens if the robot itself becomes extremely simple, and the intelligence moves into the environment instead?

LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference

• Jianhao Yuan
• Foundational models , Video generation

Fantastic Features and Where to Find Them: A Probing Method to Combine Features from Multiple Foundation Models

• Benjamin Ramtoula
• Foundational models , Model fusion

Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval

• Davide Buoso
• Generative models , Navigation

GraphSCENE: On-Demand Critical Scenario Generation for Autonomous Vehicles in Simulation

• Efimia Panagiotaki
• Gnns , Scenario generation , Autonomous vehicles

Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations

• Benjamin Ramtoula
• Foundational models , Dataset analysis