Daphne Antotsiou

ISN Group · Electrical and Electronic Engineering · Imperial College London · South Kensington Campus · London SW7 2AZ · UK d.antotsiou17@imperial.ac.uk

I am currently a PhD candidate at Imperial College London and a member of the Imperial Computer Vision and Learning Lab. My main research interests are Computer Vision and Imitation Learning.


Timeline

PhD Candidate

Imperial College London, UK
September 2017 - Present

Research Software Engineer

Nordson DAGE, UK

Developing algorithms for Image Analysis and Automation on Manual X-ray Inspection Systems.

July 2015 - August 2017

MSc in Advanced Computing: Creative Technology

University of Bristol, UK

Thesis: Introducing Programming Concepts With WebGL.

2013 - 2014

Master's Diploma in Electrical and Computer Engineering

Aristotle University of Thessaloniki, Greece

Thesis: Detection and Classification of Gestures During the Eating Process Using Camera Feed.

2007 - 2013

Publications

Task Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation

ECCV HANDS Workshop

Abstract: Human hand actions are quite complex, especially when they involve object manipulation, mainly due to the high dimensionality of the hand and the vast action space that entails. Imitating those actions with dexterous hand models involves different important and challenging steps: acquiring human hand information, retargeting it to a hand model, and learning a policy from acquired data. In this work, we capture the hand information by using a state-of-the-art hand pose estimator. We tackle the retargeting problem from the hand pose to a 29 DoF hand model by combining inverse kinematics and PSO with a task objective optimisation. This objective encourages the virtual hand to accomplish the manipulation task, relieving the effect of the estimator's noise and the domain gap. Our approach leads to a better success rate in the grasping task compared to our inverse kinematics baseline, allowing us to record successful human demonstrations. Furthermore, we used these demonstrations to learn a policy network using generative adversarial imitation learning (GAIL) that is able to autonomously grasp an object in the virtual space.

September 2018