Related papers: Visual Task Progress Estimation with Appearance In…
Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic…
Vision Language Models (VLMs) play a crucial role in robotic manipulation by enabling robots to understand and interpret the visual properties of objects and their surroundings, allowing them to perform manipulation based on this multimodal…
Machine learning techniques have enabled robots to learn narrow, yet complex tasks and also perform broad, yet simple skills with a wide variety of objects. However, learning a model that can both perform complex tasks and generalize to…
In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning…
Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. The goal behind the network is to perform an inverse computer graphics task, and the network parameters…
Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…
In this work, an existing deep neural network approach for determining a robot's pose from visual information (RGB images) is modified, improving its localization performance without impacting its ease of training. Explicitly, the network's…
To complete a complex task where a robot navigates to a goal object and fetches it, the robot needs to have a good understanding of the instructions and the surrounding environment. Large pre-trained models have shown capabilities to…
Objects rarely sit in isolation in human environments. As such, we'd like our robots to reason about how multiple objects relate to one another and how those relations may change as the robot interacts with the world. To this end, we…
To have a robot actively supporting a human during a collaborative task, it is crucial that robots are able to identify the current action in order to predict the next one. Common approaches make use of high-level knowledge, such as object…
Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…
A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a…
Image Classification is a fundamental task in the field of computer vision that frequently serves as a benchmark for gauging advancements in Computer Vision. Over the past few years, significant progress has been made in image…
Recognising relevant objects or object states in its environment is a basic capability for an autonomous robot. The dominant approach to object recognition in images and range images is classification by supervised machine learning,…
Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations,…
Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has…
As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this…
Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…
Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. These "self-models" allow robots to consider outcomes of multiple possible future actions,…