The Faculty of Engineering and Sciences at the University of Agder (UiA) has a joint Post-doctoral Research Fellow position available within the fields of Deep Reinforcement Learning, Robotics and Cooperative Control. The position is within the Norwegian Research Council Long-term research project "Collective Efficient Deep Learning and Networked Control for Multiple Collaborative Robot Systems (DEEPCOBOT)". The position is located at Campus Grimstad and will be shared among the Department of Engineering Sciences (50%) and the Department of Information and Communication Technology (50%), for a period of two years. The position is scheduled to start in June 2021, but it is negotiable with the Faculty.
The overall goal of the DEEPCOBOT project is the design of a new generation of decentralized data-driven deep learning-based controllers for multiple coexisting collaborative robots (cobots), which can interact both between themselves and with human operators in order to collectively learn from each other’s experiences and perform cooperatively different complex tasks in a large-scale industrial process environment. The project is motivated by the increasing demand of automation in industry, especially the demand of a safer, more intuitive, more comfortable and more efficient collaboration between multiple cobots and human operators to integrate the best of human abilities (creativity, adaptivity, interaction) and robotic automation (speed, reliability, precision and inexhaustible task execution capability), while being robust across different environments and human operators. This project will lead to several important advances in the areas of machine learning, decentralized control for cobots, graph signal processing, design of cross-layer network protocols for distributed computation and collective intelligence across multiple cobots.
The position will cover theoretical advancements, algorithm design, as well as simulation and experimental evaluation, on two of the following research topics:
1) Deep learning algorithms for the cobots to infer and predict the motion of human operators interacting with them, including also interpretable, active and transfer learning methods to speed up the learning process and the corresponding shared control strategies guiding the interaction between the cobot and human operators.
2) Decentralized local controllers at the cobots using the reinforcement learning framework, where each cobot learns both from its local information and from other information about other cobots’ learning process in the neighborhood.
3) Graph signal processing algorithms, graph neural networks and cross-layer network protocols to provide the required diffusion of information across the cobots so that both the deep learning process is efficient and stable, and the testing running phase is also executed correctly, satisfying the real-time and safety constraints, and minimizing energy consumption.
The project will be integrated in two Centers at UiA, namely, the Center of Mechatronics and the NFR-Toppforsk funded WISENET Center at UiA, where the Post-Doctoral Research Fellow will benefit intellectually from the interaction with internationally recognized researchers, well-equipped environments and will build on and strengthen the established cooperation in AI, Machine Learning, industrial robotics, and autonomous networked cyber-physical systems with industry partners, such as ABB Norway, Mechatronics Innovation Lab (MIL), Omron Electronics Norway, and international partners including University of California San Diego (USA), KTH Royal Institute of Technology (Sweden) and the University of Navarra (Spain). The project will give also the opportunity to pay extended visits to Universities in USA, Sweden and Spain. The robots used in this project are TIAGo robot, UR5 cobot, and ABB Yumi cobot.
To be regarded as an eligible applicant, the candidates must have:
Further provisions relating to the position as Post-Doctoral Research Fellow can be found in the Regulations Concerning Terms and Conditions of Employment for the post of Post-Doctoral Research Fellow, Research Fellow, Research Assistant and Resident.
Additional solid knowledge and experience in some of the following areas will be a plus:
The publication of scientific papers on high impact journals and first-class international conferences related to these topics will be taken into account positively, as well as the previous participation in other national or international projects related to the topics above.
A post-Doctoral research position should function as an intermediate step in the research career following the completion of a PhD degree and preceding a faculty position in a university. For this reason, our Centers are committed to offering the suitable environment and activities that allow the post-doctoral researcher to: (i) consolidate her/his research maturity, (ii) develop her/his teaching and supervision skills by working and co-advising PhD students, and (iii) build up a solid resume that facilitates her/his incorporation to the academia as an assistant or associate professor.
Information about why UiA provides an excellent working environment can be found here.
The position is remunerated according to the State Salary Scale, salary plan 17.510, code 1352 Post-Doctoral Research Fellow, NOK 545 300-566 700 gross salary per year. Higher salary grades may be considered for particularly well-qualified applicants. A compulsory pension contribution to the Norwegian Public Service Pension Fund is deducted from the pay according to current statutory provisions.
UiA is an open and inclusive university. We believe that diversity enriches the workplace and makes us better. We, therefore, encourage qualified candidates to apply for the position independent of gender, age, cultural background, disability or an incomplete CV.
Women are strongly encouraged to apply for the position.
The successful applicant will have rights and obligations in accordance with the current regulations for the position, and organisational changes and changes in the duties and responsibilities of the position must be expected. The engagement is to be made in accordance with the regulations in force concerning the acts relating to Control of the Export of Strategic Goods, Services and Technology. Appointment is made by the University of Agder’s Appointments Committee for Teaching and Research Positions.
Short-listed applicants will be invited for interview. With the applicant’s permission, UiA will also conduct a reference check before appointment. More about the employment process.
In accordance with the Freedom of Information Act § 25 (2), applicants may request that they are not identified in the open list of applicants. The University, however, reserves the right to publish the names of applicants. Applicants will be advised of the University’s intention to exercise this right.
The application and any other necessary information about education and experience (including diplomas and certificates) are to be sent electronically only. Use the link "Apply for this job".
The following documentation shall be submitted as attachments to the online application:
The applicant is fully responsible for submitting complete digital documentation before the closing date. All documentation must be available in a Scandinavian language or English.
Application deadline: 15.03.21
For questions about the position:
For questions about the application process:
|Intitulé||Post-Doctoral Research Fellow in ICT - Collective Deep Learning and Networked Control for Multiple Collaborative Robot Systems|
|Employeur||University of Agder (UiA)|
|Job location||Gimlemoen 25, 4630 Kristiansand S|
|Publié||décembre 24, 2020|
|Date limite d'inscription||mars 15, 2021|
|Types d'emploi||Post doc  |
|Domaines de recherche :||Algorithmes,   Mécatronique,   Ingénierie des communications,   Génie industriel,   Intelligence artificielle,   Communications informatiques (réseaux),   Ingénierie des systèmes de commande,   Ingénierie informatique,   Robotique,    and 6 more. Ingénierie des télécommunications,   Génie électrique,   Génie mécanique,   Apprentissage automatique,   Traitement du signal,   Électronique  |