A2I

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 [...]

Imagine That! Leveraging Emergent Affordances for Tool Synthesis in Reaching Tasks   In this paper we investigate an artificial agent’s ability to perform task-focused tool synthesis via imagination. Our motivation is to explore the richness of information captured by the latent space of an object-centric generative model –and how to exploit it. In particular, our [...]

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 [...]

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, [...]

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 [...]

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 [...]

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 [...]

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. [...]