Connectionists: 4 Fully Funded PhD Positions at the Italian Institute of Technology in the Cognitive Robotics and Interaction Lab of the Robotics, Brain and Cognitive Sciences Department
Alessandra Sciutti
alessandra.sciutti at gmail.com
Tue May 22 12:25:56 EDT 2018
Apologies for cross-posting
==================================================================
PhD Openings at the Cognitive Robotics and Interaction Lab
Robotics, Brain and Cognitive Sciences Department
Italian Institute of Technology
===========================================================
In the spirit of the doctoral School on Bioengineering and Robotics the PhD
Program for the curriculum “Cognitive Robotics, Interaction and
Rehabilitation Technologies” provides interdisciplinary training at the
interface between technology and life-sciences. The general objective of the
program is to form scientists and research technologists capable of working
in multidisciplinary teams on projects where human factors play a crucial
role in technological development and design. Robotics and neuroscience
researchers in RBCS share, as a fundamental scientific objective, the study
of physical and social interaction in humans and machines (
<http://www.iit.it/rbcs> www.iit.it/rbcs ).
Among the different research themes proposed I would like to advertise these
topics:
· Visual cues for mutual understanding in human-robot interaction
· Computational Neuroscience models for auditory aware robots
· Transferring of human-robot interaction competencies: towards robot
symbiosis in the acquisition of new skills
· Cyber-physical social security applied to emergent innovative
technologies
The ideal candidates are students with a higher level university degree
willing to invest extra time and effort in blending into a multidisciplinary
team composed of neuroscientists, engineers, psychologists, physicists
working together to investigate brain functions and realize intelligent
machines, rehabilitation protocols and advanced prosthesis.
International applications are encouraged and will receive logistic support
with visa issues, relocation, etc.
Below you can find more details related to the positions and the
instructions on how to apply
=======================================================================
Application deadline: *****12 June 2018, Noon, Italian time*****
=======================================================================
===============
Themes
===============
Visual cues for mutual understanding in human-robot interaction
Tutors: Alessandra Sciutti, PhD; Francesco Rea, PhD; Prof. Giulio Sandini
Institute: IIT (Istituto Italiano di Tecnologia)
Research Unit: Robotics, Brain and Cognitive Sciences
(https://www.iit.it/rbcs)
Division: Cognitive Robotics and Human-Human Interaction
Description: The ability of humans at interacting and collaborating with
each other is based on mutual understanding and is supported by a continuous
exchange of information mediated only in minimal part by language. The
majority of messages are covertly embedded in the way the two partners move
their eyes and their body. This implicit information exchange allows to
anticipate the needs and intentions of the partner. The general goal of this
project will be to provide the humanoid iCub robot with the ability to
perceive these covert visual signals sent by its human partners, as well as
becoming able to send analogous cues with its own movements.
The pipeline of the computational system includes an attentional module able
to localize the portion of the scene containing biological motion and to
extract the visual properties of the observed movements, as speed,
trajectory, acceleration. Starting from this analysis, performed by modules
already available on the robot, iCub will need to use the derived movement
features to understand its partners’ actions and to decode their intentions,
needs and emotions. View-invariance will be one of the crucial aspects of
the system. Additionally, these movement features will guide the selection
of the appropriate robot behavior, to make it intuitively predictable and
legible to the partner. Robot motion planning could leverage existing tools
to design biologically plausible robot movements for the iCub.
Requirements: degree in robotics, bioengineering, computer science, computer
engineering, or related disciplines, attitude for problem solving, c++
programming. A background on computer vision and machine learning is an
asset.
References
1. Sciutti A., Mara M., Tagliasco V., Sandini G. 2018 Humanizing Human-Robot
Interaction: On the Importance of Mutual Understanding, IEEE Technology and
Society Magazine https://ieeexplore.ieee.org/document/8307144/
2. Sciutti A. & Sandini G. 2017 , ‘Interacting with Robots to Investigate
the Bases of Social Interaction’, IEEE Transactions on Neural Systems and
Rehabilitation Engineering, 10.1109/TNSRE.2017.2753879
http://ieeexplore.ieee.org/document/8068256/
3. Vignolo A., Noceti N., Rea F., Sciutti A., Odone F. & Sandini G. 2017,
‘Detecting biological motion for human-robot interaction: a link between
perception and action’, Frontiers in Robotics and AI, 4.
http://journal.frontiersin.org/article/10.3389/frobt.2017.00014/full
4. Sandini G., Sciutti A. & Rea F. (2018) ‘Movement-based communication for
humanoid-human interaction’. In: Section: Human-Humanoid Interaction,
Humanoid Robotics: a Reference
Contacts: alessandra.sciutti at iit.it, francesco.rea at iit.it,
giulio.sandini at iit.it - Applicants are strongly encouraged to contact the
perspective tutors before they submit their application.
============================================================================
=============================
Computational Neuroscience models for auditory aware robots
Tutors: Francesco Rea, PhD; Prof. Giulio Sandini
Institute: IIT (Istituto Italiano di Tecnologia)
Research Unit: Robotics, Brain and Cognitive Sciences
(https://www.iit.it/rbcs)
Division: Cognitive Robotics and Human-Human Interaction
Description: Selective attention is fundamental to any living being as a
prerequisite for action performance and social interaction. The process of
visually shifting attention on task-relevant targets has been studied
extensively in cognitive neuroscience and implemented computationally for a
variety of real-word problems. However multisensory attention has been only
partially exploited despite the evident advantages in attentional orienting
and explicit communication (speech) understanding in social realistic
contexts. The PhD program will implement a novel computational neuroscience
models of auditory processing by endowing the humanoid robot iCub with
auditory awareness in an unstructured acoustic world. In detail, iCub will
1) show proactive attention toward relevant salient sound sources, 2)
generate motor-control and integrate sensor input across successive
movements to reinforce the interpretation of the scene, and 3) provide a
reliable and novel speech recognition system [1],[2]. The activities carried
out in collaboration with with department of computational neuroscience at
University of Lethbridge (Alberta, Canada) aim: a) to consolidate audio
attention system in the existing robotics setup iCub[3]; b) to enable
experimentation involving ecological interaction with human subjects; c) to
enhance the existing multimodal attention system; d) to provide
deep-learning models of speech recognition based on DNNs; e) to integrate
the outcome in the iCub cognitive architecture [4].
Requirements: degree in robotics, bioengineering, computer science, computer
engineering, or related disciplines, attitude for problem solving, c++
programming. A background on machine learning is an asset.
References:
1. Mosadeghzad M., Rea F., Tata M., Brayda L. & Sandini G. 2015, ‘Saliency
Based Sensor Fusion of Broadband Sound Localizer for Humanoids’, 2015 IEEE
International Conference on Multisensor Fusion and Information Integration
(MFI 2015), San Diego, CA, USA, September 14-16, 2015;
2. Ilievski M., Rea F.IIT, Sandini G., Tata M., ‘A Binaural Beamforming
Approach to Resolve Complex Auditory Scenes for Humanoid Robots’ 2017
IEEE/RSJ International Conference on Intelligent Robots and Systems,
Vancouver, BC, Canada, September 24-28, 2017
3. Rea F., Sandini G., Metta G., ‘Motor biases in visual attention for a
humanoid robot’, IEEE-RAS International Conference on Humanoid Robots, vol.
2015-February, pp. 779-786
4. Mohan V, Sandini G, Morasso P. (2014), ‘A neural framework for
organization and flexible utilization of episodic memory in "cumulatively"
learning baby humanoids’, Neural Computation 26(12), 2692-2734, MIT Press
Contacts: francesco.rea at iit.it , giulio.sandini at iit.it - Applicants are
strongly encouraged to contact the perspective tutors before they submit
their application.
============================================================================
=============================
Transferring of human-robot interaction competencies: towards robot
symbiosis in the acquisition of new skills
Tutor: Jacopo Zenzeri, PhD; Alessandra Sciutti, PhD; Francesco Rea, PhD
Institute: IIT (Istituto Italiano di Tecnologia)
Research Unit: Robotics, Brain and Cognitive Sciences
(https://www.iit.it/rbcs)
Division: Motor Learning, Assistive and Rehabilitation Robotics & Cognitive
Robotics and Human-Human Interaction
Description: In the recent years many studies focused on how to optimize
human-robot collaboration tasks. Here we focus on a fundamental case where a
human agent has to learn how to use a tool while collaborating with an
expert humanoid robot agent which, in this case, plays the active role of
maximizing the learning of the human. In this new perspective the process
will proceed in two steps: 1) the humanoid robot acquire the knowledge of
the collaborative tasks and becomes the “robot teacher” by interacting
(through the tool) with an expert human; 2) the naïve human interact
(through the tool) with the “robot teacher” in order to learn the task in an
optimal way.
Behavioral experiments on motor learning will be conducted using haptic
interfaces to study motor control mechanisms and how motor control
strategies emerge during the interaction with specific set of tools. This
activity is based on recent studies on dyadic interaction [1-2] and will
contribute to define human inspired models of interaction. The model is
transferred to the humanoid agent to acquire the human expert knowledge (in
step 1) and to teach it to the naïve one (in step 2). Behavioral experiments
will then be conducted with the humanoid robot iCub to implement real use
cases. In this context, the proactive role of the iCub will enrich existing
cognitive framework for human robot interaction. The candidate will also
exploit measure of engagement in the task (attentional level, cognitive load
and fatigue).
Requirements: a master degree in Bioengineering, Computer Science or
equivalent, with experience in the analysis and modeling of human movements
and in robot programming.
References:
1. Avila-Mireles, E.J. et al., 2017. Skill learning and skill transfer
mediated by cooperative haptic interaction. IEEE Transactions on Neural
Systems and Rehabilitation Engineering, 25(7), pp.832–243.
2. Galofaro, E., Morasso, P. & Zenzeri, J., 2017. Improving motor skill
transfer during dyadic robot training through the modulation of the expert
role. In IEEE International Conference on Rehabilitation Robotics. London.
3. Vignolo A., Noceti N., Rea F., Sciutti A., Odone F. & Sandini G. 2017,
‘Detecting biological motion for human-robot interaction: a link between
perception and action’, Frontiers in Robotics and AI, 4.
Contacts: jacopo.zenzeri at iit.it alessandra.sciutti at iit.it
francesco.rea at iit.it - Applicants are strongly encouraged to contact the
perspective tutors before they submit their application.
============================================================================
=============================
Cyber-physical social security applied to emergent innovative technologies
Tutor: Francesco Rea, Stefano Bencetti
Institute: IIT (Istituto Italiano di Tecnologia)
Department: ICT/ Robotics, Brain and Cognitive Sciences
(https://www.iit.it/rbcs)
Description: The field of cyber security is a fast-growing discipline that
impacts on the interaction between people and technology. Even though the
effectiveness of security measures to protect personal data is increasing,
people remain susceptible to manipulation and thus the human element remains
the weakest link. Social engineering. Such weakness is often is exploited by
the use of various manipulation techniques aiming at the disclosure of
sensitive information, namely social engineering. The field of social
engineering is still in its early stages however the interaction between
individuals and new technologies ( assistive robotics, robot companion) and
new ways of working (smart working) might be exposed to yet unknown risks
associated with the misuse of protected data only partially addressed by
traditional computer security.
The overall aim of the project is to investigate how to prevent disclosure
of sensitive information applied to the areas where humans use
interconnected technologies (e.g. :robotics, IOT, Big Data Analytics
systems) especially in the context of human machine interactions (e.g.:
robot companion, assistive robotics, home assistance, etc.). The aim unfolds
into two goals for the candidate. First, the ideal candidate is required to
develop algorithms of human machine interaction that adapts to the person.
The technology autonomously decides what sensitive information is acquired
from the person in relation to the specific objective of the interaction
(medical assessment, adaptation to user`s needs, etc). For example, the
assistive robot autonomously adapts the data acquisition strategy to the
goal of improving the provided assistance without the acquisition of
personal data, which is irrelevant to the assistance. The second goal is to
improve the robustness and high integrity of system architectures
(cyber-physical security) adopted for above-mentioned cutting-edge
technologies. The solutions defined by the candidate can also help the
security risk management and the analysis of social engineering threats.
As outcome of the project, such methodologies will be concretely applied to
innovative applications designed at the Istituto Italiano di Tecnologia in
collaboration with the robotic labs of the institute to make the
applications socially aware and socially acceptable.
Requirements: a degree in Computer Science with high interests in life
sciences. Programming skills, familiarity with social network
Contacts: francesco.rea at iit.it stefano.bencetti at iit.it - Applicants are
strongly encouraged to contact the perspective tutors before they submit
their application.
===============
How to apply
===============
Please note that the positions are available through the PhD course of
Bioengineering and Robotics, curriculum on Cognitive Robotics, Interaction
and Rehabilitation Technologies, offered jointly by IIT and the University
of Genoa.
The official calls are available here:
<https://www.iit.it/phd-school/phd-school-genoa>
https://www.iit.it/phd-school/phd-school-genoa under the Curriculum
“Cognitive Robotics, interaction and rehabilitation technologies”.
Please have a look at the "ADMISSION GUIDE" section, which contains detailed
instructions on how to apply and a list of documents you have to present.
In particular, note that the preparation of a short project proposal is
required and is important in the evaluation of prospective candidates.
Please find here a template (PDF) :
http://phd.dibris.unige.it/biorob/media/Template%20for%20Research%20Project_
v2.0.pdf
The link to the on-line application page is:
https://www.studenti.unige.it/postlaurea/dottorati/XXXIV/EN/
In case of problems or questions related to the application procedure,
please contact: <mailto:anastasia.bruzzone at iit.it>
anastasia.bruzzone at iit.it
============================================================
Application deadline: *****12 June 2018, Noon, Italian time******
============================================================
----------------------------------------
Alessandra Sciutti (PhD)
Researcher, Robotics Brain and Cognitive Sciences Unit
Istituto Italiano di Tecnologia
Center for Human Technologies
Via Enrico Melen 83, Building B
16152 Genova, Italy
tel: +39 010 8172 210
email: <mailto:alessandra.sciutti at iit.it> alessandra.sciutti at iit.it
website: <https://www.iit.it/people/alessandra-sciutti>
https://www.iit.it/people/alessandra-sciutti
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20180522/9fdecda8/attachment.html>
More information about the Connectionists
mailing list