Postdoctoral Research Assistant in Learning Perceptive Contact-Rich LocoManipulation

We are seeking a full-time Postdoctoral Research Assistant to join the Machine Learning & Articulated Robots Group (ARG) of the Oxford Robotics Institute and the Department of Engineering Science in central Oxford. The post is funded by the EPSRC's Centre to Centre (C2C) Grant, "Mobile Robotic Inspector: Learning to Explore and Manipulate in the Real World" and is fixed-term for 24 months.

The project will develop leaning-based approaches to contact rich mobile manipulation (LocoManipulation) with a focus on legged robots -mainly humanoids- in challenging scenarios. This C2C project is in collaboration with ETH Zurich's "RobotX - Center for Robotics" and is build around a rich schedule of visits to and from ETH. The goal is to further develop our mobile manipulation capabilities, able of physically demanding and dexterous mobile manipulation tasks in a range of dynamic domains (industrial, service, domestic). This position will focus on using and developing learning-based perceptive approaches.

You will develop a control framework integrating multi-modal perception and tactile feedback, for locomotion and manipulation. You will be responsible for the design, development, implementation and evaluation of learning-based loco-manipulation methods suitable for legged systems in physically-realistic simulated environments and on real robots.

Informal enquiries may be addressed to Prof. Ioannis Havoutis.

For more information about working at the Department, see

www.eng.ox.ac.uk/about/work-with-us/

Keywords: Humanoids, Machine Learning, Manipulation, Locomotion, Reinforcement Learning