11 citations · 16 across the 21 of their papers we have counts for
22 papers
Beyond Visual Quality: A Study of Test-Time Planning with World Action Models
Jianhao Yuan, Yu Yuan, Benjamin Ramtoula +5
World action models generate actions together with visual predictions of their consequences. These paired outputs create the potential for planning by sampling multiple actions fro…
Multi-Robot Planning and Control from CCTV Camera Networks in a Real Warehouse
Luke Robinson, Benjamin Ramtoula, Anas Izaaryene +2
Off-board control of mobile robots from cameras embedded in the environment offers a practical path to scalable autonomy, moving sensing and compute off the robots. We extend this…
Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models
Benjamin Ramtoula, Pierre-Yves Lajoie, Paul Newman +1
Foundation models (FMs) trained with different objectives and data learn diverse representations, making some more effective than others for specific downstream tasks. Existing ada…
LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
Jianhao Yuan, Fabio Pizzati, Francesco Pinto +5
Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such…
Watching Grass Grow: Long-term Visual Navigation and Mission Planning for Autonomous Biodiversity Monitoring
Matthew Gadd, Daniele De Martini, Luke Pitt +10
We describe a challenging robotics deployment in a complex ecosystem to monitor a rich plant community. The study site is dominated by dynamic grassland vegetation and is thus visu…
VDNA-PR: Using General Dataset Representations for Robust Sequential Visual Place Recognition
Benjamin Ramtoula, Daniele De Martini, Matthew Gadd +1
This paper adapts a general dataset representation technique to produce robust Visual Place Recognition (VPR) descriptors, crucial to enable real-world mobile robot localisation. T…
That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation
Georgi Pramatarov, Matthew Gadd, Paul Newman +1
This paper is about 3D pose estimation on LiDAR scans with extremely minimal storage requirements to enable scalable mapping and localisation. We achieve this by clustering all poi…
Open-RadVLAD: Fast and Robust Radar Place Recognition
Matthew Gadd, Paul Newman
Radar place recognition often involves encoding a live scan as a vector and matching this vector to a database in order to recognise that the vehicle is in a location that it has v…
OORD: The Oxford Offroad Radar Dataset
Matthew Gadd, Daniele De Martini, Oliver Bartlett +11
There is a growing academic interest as well as commercial exploitation of millimetre-wave scanning radar for autonomous vehicle localisation and scene understanding. Although seve…
Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data
David S. W. Williams, Daniele De Martini, Matthew Gadd +1
Knowing when a trained segmentation model is encountering data that is different to its training data is important. Understanding and mitigating the effects of this play an importa…
Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling
David S. W. Williams, Matthew Gadd, Paul Newman +1
This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation mod…
RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model
Jianhao Yuan, Shuyang Sun, Daniel Omeiza +4
We need to trust robots that use often opaque AI methods. They need to explain themselves to us, and we need to trust their explanation. In this regard, explainability plays a crit…
Robot-Relay : Building-Wide, Calibration-Less Visual Servoing with Learned Sensor Handover Network
Luke Robinson, Matthew Gadd, Paul Newman +1
We present a system which grows and manages a network of remote viewpoints during the natural installation cycle for a newly installed camera network or a newly deployed robot flee…
What you see is what you get: Experience ranking with deep neural dataset-to-dataset similarity for topological localisation
Matthew Gadd, Benjamin Ramtoula, Daniele De Martini +1
Recalling the most relevant visual memories for localisation or understanding a priori the likely outcome of localisation effort against a particular visual memory is useful for ef…
Doppler-aware Odometry from FMCW Scanning Radar
Fraser Rennie, David Williams, Paul Newman +1
This work explores Doppler information from a millimetre-Wave (mm-W) Frequency-Modulated Continuous-Wave (FMCW) scanning radar to make odometry estimation more robust and accurate.…
Visual Servoing on Wheels: Robust Robot Orientation Estimation in Remote Viewpoint Control
Luke Robinson, Daniele De Martini, Matthew Gadd +1
This work proposes a fast deployment pipeline for visually-servoed robots which does not assume anything about either the robot - e.g. sizes, colour or the presence of markers - or…
Off the Radar: Uncertainty-Aware Radar Place Recognition with Introspective Querying and Map Maintenance
Jianhao Yuan, Paul Newman, Matthew Gadd
Localisation with Frequency-Modulated Continuous-Wave (FMCW) radar has gained increasing interest due to its inherent resistance to challenging environments. However, complex artef…
Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations
Benjamin Ramtoula, Matthew Gadd, Paul Newman +1
Selecting appropriate datasets is critical in modern computer vision. However, no general-purpose tools exist to evaluate the extent to which two datasets differ. For this, we prop…
BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR
Georgi Pramatarov, Daniele De Martini, Matthew Gadd +1
This paper is about extremely robust and lightweight localisation using LiDAR point clouds based on instance segmentation and graph matching. We model 3D point clouds as fully-conn…
What Goes Around: Leveraging a Constant-curvature Motion Constraint in Radar Odometry
Roberto Aldera, Matthew Gadd, Daniele De Martini +1
This paper presents a method that leverages vehicle motion constraints to refine data associations in a point-based radar odometry system. By using the strong prior on how a non-ho…
Depth-SIMS: Semi-Parametric Image and Depth Synthesis
Valentina Musat, Daniele De Martini, Matthew Gadd +1
In this paper we present a compositing image synthesis method that generates RGB canvases with well aligned segmentation maps and sparse depth maps, coupled with an in-painting net…
Fast-MbyM: Leveraging Translational Invariance of the Fourier Transform for Efficient and Accurate Radar Odometry
Robert Weston, Matthew Gadd, Daniele De Martini +2
Masking By Moving (MByM), provides robust and accurate radar odometry measurements through an exhaustive correlative search across discretised pose candidates. However, this dense…