Tiến sĩ[Học bổng du học Pháp – PhD]-INRIA
Nội dung Học bổng
INRIA Grant for a PhD TITLE : Diagnosis-free Damage Recovery in Robotics with Machine Learning and Evolutionary Computation
Position type: PhD Student
Functional area: Nancy
Research theme: Perception, cognition, interaction
Scientific advisor: firstname.lastname@example.org
HR Contact: email@example.com
Application deadline: 01/07/2015
About Inria and the job
Established in 1967, Inria is the only public research body fully dedicated to computational sciences.
Combining computer sciences with mathematics, Inria’s 3,500 researchers strive to invent the digital technologies of the future. Educated at leading international universities, they creatively integrate basic research with applied research and dedicate themselves to solving real problems, collaborating with the main players in public and private research in France and abroad and transferring the fruits of their work to innovative companies.
The researchers at Inria published over 4,500 articles in 2013. They are behind over 270 active patents and 110 start-ups. The 180 project teams are distributed in eight research centers located throughout France. »
Inria Nancy – Grand-Est centre, one of the eight research centre, has 430 researchers, engineers and technicians in its project teams and departments.
The position will be in the LARSEN team, which consists in 4 full-time researchers, 2 assistant professors, 1 post-doc researcher, 5 PhD students, and 5 engineers. The team vision is to have robots outside of the research labs and manufacturing industries: in the real world. To reach this goal, LARSEN is developing methods to endow robots with long-term autonomy and interaction skills, taking into account the embedded and/or external sensors in the environment. These skills are grounded on physical and social interaction, machine learning, and planning under uncertainty. Experiments, especially in service and assistive robotics, are at the core of the methodology.
For more information, see: http://team.inria.fr/larsen
The selected PhD student will work in the ERC project ResiBots (funded by the European Research Commission). The overall goal of the project is to develop novel learning algorithms that make it possible for autonomous robots to quickly discover compensatory behaviors when they are damaged (e.g. a broken motor) or when they encounter an unforeseen situation.
See also: http://pages.isir.upmc.fr/~mouret
The team of the ResiBots project will (on average) be made of 1 researcher (Jean-Baptiste Mouret), 1 post-doc researcher, 1 PhD student, and 1 engineer. The selected engineer will interact with the engineers of the SED (Service of Developments and Experimentations of Inria) to mutualize some developments and experiences.
The objective of this PhD is to develop and evaluate novel algorithms for damage recovery in robotics. The algorithms will be based on a combination of off-line evolutionary algorithms  and on-line learning based on Bayesian optimisation  with Gaussian processes . A central idea is that no diagnosis of the damage will be performed: the recovery process will be based on a trial-and-error process. We already obtained promising results with a hexapod robot (see https://www.youtube.com/watch?v=p6oegqDrCDs and ).
The first objective is to generalize this approach to two other robotics platforms : (1) a mobile manipulator, and (2) the iCub robot (humanoid). The second objective is to make the robots able to take the environment into account during the trial-and-error learning process. For instance, a damaged, walking robot needs to avoid the obstacles while learning a compensatory behavior. As many experiments as possible will be performed on real robots, but the PhD student will benefit from the help of a robotics engineer who will be dedicated to the project.
The day-to-day activities will be:
-develop novel algorithms for damage recovery in robotics;
-conduct experiments with the robots (hexapod robot, mobile manipulator, iCub humanoid robot);
-write scientific papers that will be sent to peer-reviewed journals and conferences.
Skills and profiles
Prospective candidates should hold a master degree in computer science, machine learning, or robotics. A good knowledge of C++ will be useful, as well as a will to work with real robots.
STARTING DATE : 1st of October 2015
DURATION : 3 years
MONTHLY SALARY : 1 580 € net (medical insurance included) for the first two years, 1 661 € net the third year
-Possibility of French courses
-Help for housing
-Contribution in part to the costs of transport (French public transport company)
-Possibility of lunch time for 2,72 € per day
-Complementary health insurance with competitive price
FOR FURTHER INFORMATION :
Please contact : firstname.lastname@example.org
For your application please send
– A resume
– A motivation letter
– A scan of your Bachelor’s degree transcript and Master’s degree transcript (if you are still a Master student at the time of application, please provide the list of classes that you have taken and the grades you have obtained)
– Reference letters
Security and defence procedure :
In the interests of protecting its scientific and technological assets, Inria is a restricted-access establishment. Consequently, it follows special regulations for welcoming any person who whishes to work with the institute. The final acceptance of each candidate thus depends on applying this security and defence procedure.
1541 lượt xem, 1 xem hôm nay