University of Edinburgh

Endoscopic Robot for Distal Lung Sampling

Project number: 
240011
Develop image-guided control algorithms for autonomous pulmonary sampling using a robotic endoscopic platform.
Dr. Mohsen Khadem
University of Edinburgh

Pulmonary infiltrates such as pus, blood, or protein, which lingers within the parenchyma of the lungs are the leading cause of pneumonia, tuberculosis.  Pulmonary infiltrates in mechanically ventilated (MV) critically ill patients in the intensive care unit (ICU) are a major diagnostic challenge and due to the poor sampling methods available.

Human-Machine Collaboration for Efficient Spatio-Temporal Biodiversity Monitoring

Project number: 
230021
Efficient estimation of changes in spatio-temporal distributions of wildlife via active data collection
Dr. Oisin Mac Aodha
University of Edinburgh

There is a critical need for robust and accurate tools to scale up biodiversity monitoring and to manage the impact of anthropogenic change. For example, the monitoring of individual species that are particularly sensitive to habitat conversion and climate change can act as an important indicator of ecosystem health. Existing approaches for collecting data on individual species in the wild have traditionally been based on manual surveys performed by human experts.

Deep Learning of Object Shape from Video

Project number: 
400006
Learning visual representations of objects that encode both shape and appearance
Dr. Oisin Mac Aodha
University of Edinburgh

The shape and 3D structure of the world provides us with rich signal that enables us to interact with objects and to navigate in novel and dynamic environments. Despite the importance of this information to human visual reasoning it still remains largely underutilized in modern deep learning based semantic image understanding pipelines commonly used in robotics. For example, current best performing approaches for object classification in images are predominantly based on heavily supervised feedforward convolutional neural networks.

Variable Stiffness Actuation for Bioinspired Underwater Propulsion

Project number: 
140029
This project aims to study the use of Variable Stiffness Actuators (VSA) embedded in aquatic propulsors to ensure persistent operation at maximum propulsive efficiency.
Dr. Francesco Giorgio-Serchi
University of Edinburgh

Fish and other aquatic organisms propel themselves via flapping foil. Similarly, aquatic organisms such as squids and octopuses perform pulsation of a hollow, flexible chamber of their body in order to recursively ingest and expel fluid and in this way perform a pulsed-jetting locomotion routine. In order to enhance swimming efficiency, many aquatic organisms exploit resonance-based phenomena where activation frequency and natural frequency of the system (combined fluid and body) are matched.

Autonomous Driving in Urban Environments

Project number: 
100017
Develop and evaluate algorithms for autonomous driving in urban environments
Dr. Stefano Albrecht
University of Edinburgh

The coming decades will see the creation of fully autonomous vehicles (AVs) capable of driving without human intervention. Among the expected benefits of AVs are a significant reduction in traffic incidents, congestion, and pollution, while dramatically improving cost-efficiency.

University: 
University of Edinburgh
University: 
University of Edinburgh

Analysis of Controlled Stochastic Sampling for training RL Agents for Robotics Tasks

Project number: 
123406
For tasks where path-planning of real robots is guided via a simulation of a virtual agent, this project aims to understand the role and impact of the randomisation scheme on the efficiency and generalisability of the agent.
Dr. Kartic Subr
University of Edinburgh

Data-driven machine learning techniques are popularly used in the field of robotics to inform autonomous decision-making and to perform control or path-planning. Supervised learning and reinforcement learning have been shown to be particularly amenable to canonical tasks that are integral to robotics applications. However, these techniques rely on data in the form of action-label (supervised), action-value (regression) or action-reward (RL) pairs, where the action is a path (or some other) execution by a real robot. e.g.

Curiosity-driven Learning for Visual Understanding

Project number: 
400005
The goal of this project is to enable learning systems with the ability to have curiosity, based on their ability to already understand the world around them, to make learning faster and more efficient.
Dr. Laura Sevilla-Lara
University of Edinburgh

Curiosity guides humans to learn efficiently. It incentivizes us to spend more energy and time examining new, unexpected things, and to disregard those we fully understand already, to make our learning more efficient. Much of the vision learning that is done today is passive: learning systems are exposed to large amounts of training data, and learn from each sample multiple times, regardless of their current ability to recognize them at the time. This makes the process slow, specially given the increasingly large number of samples on datasets.

Perceiving Humans in Detail: Fine-grained Classification of Human Action Recognition

Project number: 
400004
The goal of this project is to push the current ability of robots to understand humans at a more sophisticated, fine-grained level.
Dr. Laura Sevilla-Lara
University of Edinburgh

Human action recognition is a fundamental problem that underlies many applications in robotics, including interaction, home care, collaboration, etc. The actions that can be recognized by robots or computers today are often coarse and simplistic, in the sense that they are very different from each other; for example eating vs playing piano, or sitting vs standing. Both datasets and technology tend to be broad and crude. As human-robot-interaction becomes more natural we require more sophisticated technology for perceiving humans.