28 accepted papers
Transformers have achieved remarkable success across a wide range of applications, a feat often attributed to their scalability. Yet training them without residual (skip) connections remains notoriously difficult. While skips stabilize optimization, they also disrupt the hierarchical structure of re…
In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vi…
For Deep Reinforcement Learning (DRL) models to deliver actual utility, they must function within production environments, which often lack the extensive computational resources of training environments. This requirement for dedicated GPU resources is not economically feasible and can be especially …
A central challenge in lifelong imitation learning (LIL) is enabling agents to acquire new skills from expert demonstrations while retaining knowledge of previously learned tasks. Achieving this requires preserving the low-dimensional manifolds and geometric structures that underlie task representat…
Recent years have seen a significant increase in demand for robotic solutions in unstructured natural environments, alongside growing interest in bridging 2D and 3D scene understanding. However, existing robotics datasets are predominantly captured in structured urban environments, making them inade…
We highlight a curious empirical result within modern Vision Transformers (ViTs). Specifically, self-attention catastrophically fails to train unless it is used in conjunction with a skip connection. This is in contrast to other elements of a ViT that continue to exhibit good performance (albeit sub…
Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often rely on unsupervised skill discovery to construct an ever-growing skill library or distillation from multiple policies, which ca
In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vi
This paper proposes SOLVR, a unified pipeline for learning based LiDAR-Visual re-localisation which performs place recognition and 6-DoF registration across sensor modalities. We propose a strategy to align the input sensor modalities by leveraging stereo image streams to produce metric depth predic
Accurate modelling of object deformations is crucial for a wide range of robotic manipulation tasks, where interacting with soft or deformable objects is essential. Current methods struggle to generalise to unseen forces or adapt to new objects, limiting their utility in real-world applications. We
LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak performance. However, obtaining accurate ground truth data
This letter proposes a pose-graph attentional graph neural network, called P-GAT, which compares (key)nodes between sequential and non-sequential sub-graphs for place recognition tasks as opposed to a common frame-to-frame retrieval problem formulation currently implemented in SOTA place recognition
Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a decoder, which encourages the network to capture and learn struct…
Neural fields, coordinate-based neural networks, have recently gained popularity for implicitly representing a scene. In contrast to classical methods that are based on explicit representations such as point clouds, neural fields provide a continuous scene representation able to represent 3D geometr…
LiDAR Upsampling is a challenging task for the perception systems of robots and autonomous vehicles due to the sparse and irregular structure of large-scale scene contexts. Recent works propose to solve this problem by converting LiDAR data from 3D Euclidean space into an image super-resolution prob…
The success of re-localisation has crucial implications for the practical deployment of robots operating within a prior map or relative to one another in real-world scenarios. Using single-modality, place recognition and localisation can be compromised in challenging environments such as forests. To…
Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolutional feature maps. However, pairwise correlation will become misleading once there is another channel correlating with…
In large-scale metric localization, an incorrect result during retrieval will lead to an incorrect pose estimate or loop closure. Re-ranking methods propose to take into account all the top retrieval candidates and re-order them to increase the likelihood of the top candidate being correct. However,
State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments. To address this issue, we investigate the task of uncertainty-aware lidar place recognition,…
Many existing datasets for lidar place recognition are solely representative of structured urban environments, and have recently been saturated in performance by deep learning based approaches. Natural and unstructured environments present many additional challenges for the tasks of long-term locali…
Place recognition is a fundamental component of robotics, and has seen tremendous improvements through the use of deep learning models in recent years. Networks can experience significant drops in performance when deployed in unseen or highly dynamic environments, and require additional training on…
Retrieval-based place recognition is an efficient and effective solution for re-localization within a pre-built map, or global data association for Simultaneous Localization and Mapping (SLAM). The accuracy of such an approach is heavily dependant on the quality of the extracted scene-level represen…
In object detection, false negatives arise when a detector fails to detect a target object. To understand <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">why</i> object detectors produce false negatives, we identify five ‘false negative mechanisms,’
Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper presents Locus, a novel place recognition method using 3D LiDAR point clouds in large-scale environments. We propose a m…
The demand for multimodal sensing systems for robotics is growing due to the increase in robustness, reliability and accuracy offered by these systems. These systems also need to be spatially and temporally co-registered to be effective. In this letter, we propose a targetless and structureless spat
Map-centric Simultaneous Localization And Mapping (SLAM) is emerging as an alternative of conventional graph-based SLAM for its accuracy and efficiency in long-term mapping problems. However, in map-centric SLAM, the process of loop closure differs from that of conventional SLAM and the result of in
The concept of continuous-time trajectory representation has brought increased accuracy and efficiency to multi-modal sensor fusion in modern SLAM. However, regardless of these advantages, its offline property caused by the requirement of global batch optimization is critically hindering its relevan…
Legged robots offer the potential of locomotion across various types of terrains. Different terrains require different gait patterns to enable greater traversal efficiency. Consequently, as a legged robot transitions from one type of terrain to another, the gait pattern should be adapted so as to ma…