A2I

Home/A2I

This is the category for all pages / news posts related to A2I.

For research topics / papers that fall into AI, use the Topics –> AI category instead

Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis

Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis   In this paper we explore the richness of information captured by the latent space of a vision-based generative model – and how to exploit it. The context of our work is an artificial agent’s ability to perform task-focused tool synthesis for 3D reaching tasks based [...]

By |2020-05-12T07:33:37+01:00May 11th, 2020|A2I, A2I Highlights, AI|Comments Off on Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis

Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar

Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar Abstract - This paper presents a self-supervised framework for learning to detect robust keypoints for odometry estimation and metric localisation in radar. By embedding a differentiable point-based motion estimator inside our architecture, we learn keypoint locations, scores and descriptors [...]

By |2020-02-06T12:42:36+00:00January 30th, 2020|A2I, A2I Highlights, AI|Comments Off on Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar

Permutation Invariance and Relational Reasoning in Multi-Object Tracking

Permutation Invariance and Relational Reasoning in Multi-Object Tracking Relational Reasoning is the ability to model interactions and relations between objects. A machine learning model performing relational reasoning often has access to a list of object representations. The ordering of the list could carry information for the task at hand, but that is not necessarily the [...]

By |2019-11-03T10:55:33+00:00November 1st, 2019|A2I, A2I Highlights, AI|Comments Off on Permutation Invariance and Relational Reasoning in Multi-Object Tracking

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations   Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, [...]

By |2019-11-01T16:05:02+00:00October 1st, 2019|A2I, A2I Highlights, AI|Comments Off on GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

Learning Robust, Distraction-Free Radar Odometry from Pose Information

Masking by Moving: Learning Robust, Distraction-Free Radar Odometry from Pose Information Abstract - This paper presents an end-to-end radar odometry system which delivers robust, real-time pose estimates based on a learned embedding space free of sensing artefacts and distractor objects. The system deploys a fully differentiable, correlation-based radar matching approach. This provides the same level of [...]

By |2020-01-30T01:48:32+00:00September 26th, 2019|A2I, A2I Highlights, AI|Comments Off on Learning Robust, Distraction-Free Radar Odometry from Pose Information

The Oxford Radar RobotCar Dataset

The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset Abstract - In this paper we present The Oxford Radar RobotCar Dataset, a new dataset for researching scene understanding using Millimetre-Wave FMCW scanning radar data. The target application is autonomous vehicles where this modality remains unencumbered by environmental conditions such as fog, [...]

By |2020-02-06T12:42:15+00:00September 26th, 2019|A2I, A2I Highlights, AI, Robotcar|Comments Off on The Oxford Radar RobotCar Dataset

Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes

Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes Predicting the stability of block towers is a popular task in the domain of intuitive physics. Previously, work in this area focused on prediction accuracy, a one-dimensional performance measure. We provide a broader analysis of the learned physical understanding of the final model and how the learning [...]

By |2019-11-03T10:51:08+00:00September 1st, 2019|A2I, A2I Highlights, AI|Comments Off on Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes

Deep Inverse Sensor Modelling in Radar

In the last decade, systems utilising camera and lasers have been remarkably successful increasing our expectations for what robotics might achieve in the decade to come. Our robots now need to see further, not only operating in environments where humans can operate, but also in environments where humans cannot! To this end radar is a [...]

By |2019-04-17T15:55:44+01:00April 16th, 2019|A2I, A2I Highlights, AI|Comments Off on Deep Inverse Sensor Modelling in Radar

On the Limitations of Representing Functions on Sets

Our recent work on analysing a set of permutation invariant neural network architectures is probably on the theoretical end of the spectrum of the type of work we do at the A2I lab. Nevertheless it is equally exciting as it has concrete implications for real-world robotics such as working with point clouds from Lidars. [...]

By |2019-03-27T15:10:25+00:00March 27th, 2019|A2I, A2I Highlights, AI|Comments Off on On the Limitations of Representing Functions on Sets