University of Edinburgh

University: 
University of Edinburgh

Haptic Feedback System for Robots in Harsh Environments

Project number: 
200026
To develop a haptic feedback system for robots operating in harsh environments (e.g., space and nuclear)
Prof. Tughrul Arslan
University of Edinburgh

Space and nuclear robots are exposed to significant amounts of radiation which can lead to errors and system-crippling failures with great losses in economy.

The limited human intervention for safe operation necessitates the need for a remotely connected haptic feedback system to aid human-robot interactions.

University: 
University of Edinburgh
University: 
University of Edinburgh

A dandelion-inspired drone: how to translate natural flyer ability of passive hovering to enhance drone endurance

Project number: 
200025
This proposal builds on our recent discoveries, published in Nature (https://edin.ac/385DnRY) that reveal how the dandelion fruit can fly unpowered for hundreds of kilometres. In contrast, similar-size manmade drones have an endurance of few minutes. This PhD project aims to develop a deeper understanding of how the dandelion exploits wind gusts to remain airborne and to translate our insights from biology into the design of a new family of centimetre-scale drones with a step-change increase in the flight range and endurance.
Dr. Ignazio Maria Viola
University of Edinburgh

In the next decade, distributed sensor network systems made of insect-scale flying sensors will enable a step change in monitoring natural disasters and remote areas. They will contribute to protecting the environment by providing data on the contamination of physical and biological systems and on the impact of human activities. To date, a key limitation of this technology is that small drones such as the robobee can remain airborne only for few tens of minutes.

University: 
University of Edinburgh

Teaching Robots to Plan

Project number: 
124026
To develop and implement methods for instructing robots directly through natural language, where the instructions refer to temporally extended plans executed on physical robots (e.g., object manipulation)
Dr. Subramanian Ramamoorthy
University of Edinburgh

The vast majority of applications of robots do not involve just one isolated task (such as grasping an object) but instead carefully choregraphed sequences of such tasks, with dependencies between tasks not just in terms of what comes after what but also how the previous task should be performed (in a quantitative sense at the level of motor control) in order to set up for the next. Moreover, there are numerous subjective variables in these tasks, e.g., how close should it come to a delicate object or how hard should it pull on a cable?

Learning Dexterous Robotic Manipulation

Project number: 
124025
Learning autonomous grasping and manipulation skills that are safe to be deployed in human environment with data-efficient deep reinforcement learning and human-robot skill transfer
Dr. Zhibin Li
University of Edinburgh

Background

A large variety of robotic applications strongly involve handling various objects as the core process for task completion. To date, most of these jobs are still performed by people. Although some are automated by robots, those solutions primarily rely on pre-designed rules or tele-operation (limited operational time due to cognitive overload), which unavoidably limits the performance in changing environments. This project consists of multiple challenging research topics in robotic manipulation.

Project description

University: 
University of Edinburgh