Postdoctoral Fellowship, Engineering and Applied Science
Engineering & Applied Science
Location: Aston University Main Campus
Grade: Grade 08
Contract Type: Fixed Term (12 Months)
Basis: Full Time
Closing Date: 23.59 hours BST on Friday 05 April 2019
Interview Date: To be confirmed
Deep Reinforcement Learning and Knowledge Transfer for Robot Dexterous In-Hand Manipulation
Applications are invited for a Postdoctoral Fellowship at the School of Engineering and Applied Science to be undertaken within the Computer Science Research Group at Aston University, Birmingham, UK. The successful applicant will join an established experimental group working on artificial perception and machine learning towards robot dexterous manipulation. This position is available to start as soon as possible (from March 2019).
The postdoctoral fellow will work within the EU CHIST-ERA InDex project (Robot In-hand Dexterous manipulation by extracting data from human manipulation of objects to improve robotic autonomy and dexterity) that will kick-off in March 2019. It is expected the fellow will collaborate with our partners (Sorbonne University, Technische Universität Wien, University of Genoa, and University of Tartu) during the course of the project.
This post is initially one-year contract, with the possibility of renewing it until the duration of the project (3 years).
Background of the Project
It is expected that the postdoctoral fellow will design and develop an approach based on deep reinforcement and transfer learning to endow a robot to autonomously learn and adapt its strategy to interact with objects during in-hand manipulation tasks, and also being able to transfer this knowledge to other contexts. Beyond of learning from human demonstrations, learning from a synthetic environment (simulations) can be an alternative, where transfer learning will play an important role to use the knowledge acquired from that environment to be applied to a real-world context.
The fellowship is based on Aston University Grade 8 spine point 32, which is currently a salary of £35,211 per annum.
The successful applicant must have a Ph.D. degree in Computer Science or Electrical Engineering or other related degrees. Preferred skill requirements include experience with robot perception, grasping and dexterous manipulation and/or knowledge in machine learning. We would particularly like to encourage application from women seeking to progress their academic careers.