Phuong D.H. Nguyen
Autonomous learning of visuo-tactile peripersonal space representation in humanoid robots
Principle Supervisor:
Prof. Dr. Giorgio Metta
Fondazione Istituto Italiano Di Tecnologia
Collaboration partners:
Competence Area: Situation
Biography
NGUYEN Dong Hai Phuong has moved to Knowledge Technology group, Department of Computer Sciences, University of Hamburg since February, 2019 as Postdoctoral Researcher, where he has been conducting research on Hierarchical and transferable reinforcement learning for robotic tasks.
Previously, within the SECURE project, he attended Istituto Italiano di Tecnologia (IIT) from January, 2016 as PhD Fellow and focused on research of perceptual and sensorimotor capabilities for humanoid robotics. He also holds Marie Curie Fellowship as an Early Stage Researcher.
He got Master degree in Advanced Robotics from Ecole Centrale de Nante, France and Universita degli Studi di Genova, Italy, where he conducted the Master thesis research on Control and Planning for UAV robots. Before that he graduated from Da Nang University of Technology, Da Nang, Vietnam with Bachelor degree in Electrical Engineering.
Detail CV can be found here
Download CV here
Objectives
To develop a complex spatial representation around the iCub humanoids robot utilizing visual (stereo cameras), tactile (artificial skin) and motor signals. This representation enables control of the robot in the presence of multiple potential or actual contacts. It will e.g. determine that certain configurations are convenient to support the robot during task execution and actively seek contact with the environment rather than avoiding it. This model will be also compared with an existing neuroscience model of the so-called peripersonal space representation.
Related research and results can be found here.
First demonstration result
Peripersonal space for safety in physical Human-Robot Interaction
Second demonstration result
Transferring Visuomotor Learning from Simulation to the Real World for Robotics Manipulation Tasks
News
- July, 2019: Our paper of "Reaching development through visuo-proprioceptive-tactile integration on a humanoid robot – a deep learning approach" has got accepted to the ICDL-Epirob 2019 conference in Olso, Norway. The paper has also been nominated for the Modelbot award.
- Apr, 2019: I successfully defended my PhD Thesis on the topic Toward Robots with Peripersonal Space Representation for Adaptive Behaviors and graduated with Doctor of Philosophy title.
- Feb, 2019: I have moved to Knowledge Technology Group, Department of Informatics, University of Hamburg to continue my research on robotics and learning.
- Dec, 2018: Our paper of "A Reconfigurable and Adaptive Human-Robot Collaboration Framework for Improving Worker Ergonomics and Productivity" has got accepted to publish in The IEEE Robotics and Automation Magazine. This is the results of joint work iCub Facility and HRI2, ADVR from IIT. The paper describes the technology of our CoAware team in KUKA Innovation Award 2018.
- Nov, 2018: Our paper of "Merging physical and social interaction for effective human-robot collaboration" has got accepted and presented at Humanoids2018 conference in Beijing, China. Pre-printed version can be found here.
- Oct, 2018: I attended IROS2018 at Madrid, Spain and present our paper of "Transferring Visuomotor Learning form Simulation to Real world for Robotics Manipulation Tasks". Pre-printed version can be found here.
- July, 2018: Our paper of "Transferring Visuomotor Learning form Simulation to Real world for Robotics Manipulation Tasks" has got accepted to IROS2018 conference in October 2018 at Madrid, Spain. This is the joint work of iCub Facility, IIT and Personal Robotics Lab, Imperial College London.
- Apr 26th, 2017: Our CoAware team from IIT is the winner of KUKA Innovation Award 2018.
- Apr 23rd-28th, 2017: Attended the final competition of the KUKA Innovation Award 2018 as a member of CoAware team from IIT, Italy. Part of this work, which was presented at HRI 2018 conference, will combine with CoAware team application for Human-Robot Interaction. A demo can be seen here.
- Jan, 2018: Our paper "Compact Real-time avoidance on a Humanoid Robot for Human-robot Interaction" has got accepted to HRI '18: 2018 ACM/IEEE International Conference on Human-Robot Interaction in March 2018, at Chicago, US. Final version can be found here.
- Nov 27th, 2017 - Dec 1st, 2017: Attended KUKA training on iiwa robot platform (for KUKA Innovation Award 2018 & Hannover Messe 2018) at KUKA Robotics, Augsburg, Germany.
- Oct, 2017 - Dec, 2017: Academic visit at Personal Robotics Lab, Imperial College London with Prof. Yiannis Demiris.
- July, 2017: Our joint IIT team Co-Aware (iCub Facility + ADVR) got accepted to final round (best 5 teams) of the KUKA Innovation Award 2018.
- July, 2017: Got accepted to Summer School on Foundations of Robotics and Autonomous Learning hold by TU Berlin, Germany from Sept, 4th-8th in Berlin, Germany.
- Jun, 2017: Got accepted to Deep Learning Summer School 2017 hold by University of Montreal, Canada from Jun, 26th-July, 1st 2017 in Montreal, Canada.
- May, 2017: Attended the Midterm review meeting of SECURE project from May, 6th-11th in Hamburg, Germany.
- Feb, 2017: Participated in Final Review Meeting of WYSIWYD project in Barcelona, Spain.
- Feb, 2017: Attended iCub Winter School 2017 (VVV17) from Jan, 31st-Feb, 8th in Santa Magherita, Italy. Our team demo won the 1st Prize Award.