[robotics-worldwide] [jobs] PostDoc and PhD positions in Visual/Force Shared Control Architectures (RoMaNS EU H2020 project) at INRIA/IRISA-CNRS, Rennes, France

Paolo Robuffo Giordano paolo.robuffo_giordano at irisa.fr
Tue Mar 3 03:53:34 PST 2015



The Lagadic group at Inria/Irisa Rennes, France

http://www.irisa.fr/lagadic/welcome-eng.html

has

- *one* funded PhD position (*PhD1*, 3 years)

and

- *two* funded PostDoc positions (*PostDoc1* and *PostDoc2*, 3 years)

in the context of the new EU H2020 project *RoMaNS* (Robotic 
Manipulation for Nuclear Sort and Segregation).


The RoMaNS project involves 5 top institutions across Europe (UK, France 
and Germany), and its goal is to advance the state-of-the-art in mixed 
autonomy for automatically sorting, segregating and cleaning up nuclear 
waste by exploiting robotics arms equipped with onboard sensors (e.g., 
cameras) and under the partial guidance of a human operator.
In particular, the following meta-tasks will be addressed withing RoMaNS:

1) Developing novel hardware and software solutions for advanced 
bilateral master-slave teleoperation

2) Developing advanced autonomy methods for highly adaptive automatic 
grasping and manipulation actions

3) Combining autonomy and teleoperation methods using state-of-the-art 
understanding of mixed initiative planning, variable autonomy and shared 
control approaches

4) Delivering a final demonstrator in an industrial plant-representative 
environment




-- DESCRIPTION OF THE ACTIVITIES --

The Lagadic group will contribute to the RoMaNS project by addressing 
the following topics with the three offered positions (*PhD1*, 
*PostDoc1* and *PostDoc2*):


- *PostDoc1*: development of robust visual servoing and visual tracking 
techniques for precisely positioning a robot arm over an object to be 
grasped (also articulated or deformable) in presence of several 
constraints (e.g., limited field of view, forbidden/dangerous zones for 
the robot manipulator) and/or limited knowledge of the object 3D model 
(by both exploring model-based and model-free servoing solutions). 
Exploitation of sensory redundancy for minimizing the effects of 
occlusions or difficult tracking of the objects of interest. The 
possible presence of a second robotic arm acting as "supporting eye" 
will be considered for improving the robustness of the system to 
real-world conditions


- *PostDoc2*: algorithms for shared control architectures for allowing a 
human operator to partially control the robot motion by providing a 
force/visual feedback informative of how well the task is being 
executed. The goal is to suitably apply and extend the classical 
force-feedback bilateral teleoperation framework to the particular tasks 
addressed in the project (visual/sensor-based shared control of a 
robotic arm approaching objects of interest to be grasped).
The PostDoc will be in charge of the scientific advancements in this 
area by, e.g., investigating different combinations of force cues 
displayed to the human operator (possibly varying with the particular 
phase: free-motion, approaching, in contact, grasping, etc.), by 
considering the possible use of "local planners" for quickly exploring 
the future consequences of the operator's commands against the system 
constraints (e.g., limited camera fov, joint limits, occlusions, 
forbidden regions), and by participating to the design and 
implementation of user evaluation studies for assessing the 
performance/effectiveness of the proposed shared control architecture. 
The PostDoc will also directly supervise the PhD student *PhD1*



- *PhD1*: algorithms for shared control architectures for allowing a 
human operator to partially control the robot motion by providing a 
force/visual feedback informative of how well the task is being executed.
The PhD student will be in charge of designing and implementing the 
algorithmic component of the shared control architecture by, e.g., 
testing different possibilities for the displayed force cues (task 
error, violation of constraints such as joint limits or loss of 
tracking, presence of obstacles/forbidden regions, and so on), and by 
running evaluation studies meant to assess the effectiveness of the 
shared control architecture. The PhD student will be under the direct 
supervision of *PostDoc2* and is expected to also work in close 
collaboration with *PostDoc1*.


Opportunities to actively collaborate with the several RoMaNS partners 
will be highly encouraged.
Finally, the two PostDocs are also expected to contribute to the project 
management and related administrative tasks.





-- CANDIDATES' EXPECTED PROFILE --


- *PostDoc1*: the ideal candidate is expected to have a strong 
background in the field of robotics, estimation and control with a focus 
on visual-based applications.
Familiarity with computer vision and image processing is a plus. 
Successful participation to previous EU projects is a plus.

The candidate must be a proficient user of C/C++ and ROS and any 
relevant computer vision library (e.g., ViSP, OpenCV, PCL). Scientific 
curiosity, large autonomy and ability to work independently are also 
expected.

A PhD degree in computer science, engineering, applied mathematics (or 
related fields) is required.




- *PostDoc2*: the ideal candidate is expected to have a strong 
background in the field of robotics, estimation and control with a focus 
on force-feedback bilateral teleoperation and shared control.
Familiarity with planning algorithms and numerical optimization is a 
plus. Familiarity with psychophysics and experimental design for 
evaluating shared control architectures is a plus. Successful 
participation to previous EU projects is a plus.

The candidate must be a proficient user of C/C++ and ROS. Familiarity 
with matlab/simulink is a plus. Scientific curiosity, large autonomy and 
ability to work independently are also expected.

A PhD degree in computer science, engineering, applied mathematics (or 
related fields) is required.




- *PhD1*: The ideal candidate is expected to have a strong background in 
the field of robotics, estimation and control.

The candidate must be a proficient user of C/C++ and ROS. Familiarity 
with matlab/simulink is a plus. Scientific curiosity, autonomy and 
ability to work independently are also expected.

A M.Sc. degree in computer science, engineering (or related fields) is 
required.




-- SALARY --

The three positions are full-time for 3 years and will be paid according 
to French salary schemes.





***********  ENVIRONMENT ***********


The Lagadic group, headed by Francois Chaumette,

http://www.irisa.fr/lagadic/welcome-eng.html

is internationally recognized for its scientific activity as well as for 
technology transfer experiences in the field of visual tracking, visual 
servoing, computer vision and sensor-based control for robotics 
applications. The facilities available in the group include three 6-dof 
manipulator arms, a pioneer indoor mobile robot, a state-of-the-art 
human-size humanoid robot (Romeo), a fleet of quadrotor UAVs, and an 
indoor large testing arena instrumented with Vicon.

The candidates will be under the supervision of *Dr. Paolo Robuffo Giordano*

http://www.irisa.fr/lagadic/team/Paolo.Robuffo_Giordano.html

and will work in close collaboration with other members of the Lagadic 
group involved in the project.


The Lagadic group is part of the Inria/Irisa lab that spreads its 
activities in 30 research teams working in computer science, signal 
processing, and control. It involves about 650 people, including 120 
professors and assistant professors, 100 full-time researchers, 80 
administrative staff, and 250 PhD students.




***********  HOW TO APPLY  ***********

Interested candidates must send to Dr. Paolo Robuffo Giordano (prg [at] 
irisa.fr) the following material:

- motivation letter
- detailed CV
- name of at least two referees
- any relevant information for proving a good match with the description 
of the activities and expected profile of the candidates

The three positions will remain open until a satisfactory candidate will 
be found.




-- 
Dr. Paolo Robuffo Giordano

Centre National de la Recherche Scientifique (CNRS)
Lagadic Team, Irisa and Inria Bretagne Atlantique
Campus Universitaire de Beaulieu
35042 Rennes cedex, France
Tel: +33 (0)2 99842545
Fax: +33 (0)2 99847171
Email: prg at irisa.fr
Website: http://www.irisa.fr/lagadic/team/Paolo.Robuffo_Giordano.html
YouTube: http://www.youtube.com/user/MPIRobotics


More information about the robotics-worldwide mailing list