PhD project title and outline, including interdisciplinary dimension:
Motion Planning and Representation Learning under Uncertainty for Motor Primitives and Robotics

Autonomous robots have recently come to the fore as having a major role to play in supporting sustainable and competitive industrial manufacturing in UK and Europe, as well as solving challenging societal problems such as health care provision. Recently, there have been rapid developments in both computing power and robotic technologies. We now have faster robot brains and more precise, robust and compliant robotic sensor, actuators and devices. On the other hand, with the very significant advancements in artificial intelligence and machine learning, we also have more powerful algorithms for processing and learning from big data. Modern robots are now able to perform more challenging tasks and to master complex and dexterous skills more quickly. However there are still major barriers to robots living and working seamlessly with humans in human-friendly unstructured environments that are geometrically complex and uncertain. In particular, it is necessary to come up with a new motion planning and learning paradigm that enables robots to i) learn to represent the environment and update the learnt model by interaction under uncertainty with the environment more efficiently; ii) optimize their motion and behaviour based on the learnt model.
We focus on robotic applications because robots are becoming more capable with regard to autonomously solving complex daily tasks. These tasks often require the robots to select actions over a long time horizon, e.g. over hours or days, under uncertainty about i) noisy or imperfect perception, ii) properties and locations of objects, iii) partial information in human-robot interaction and iv) pervasive delayed dependencies. The problem state might represent symbolic relations of objects, the degree-of-freedoms of environment, and kinematics of the possible motion of all objects.

Primary supervisor: Dr Wasif Naeem (EEECS)
Secondary supervisor: Dr Vien Ngo (EEECS)
Third supervisor: Professor Seán McLoone (EEECS)
External Partner/Organisation: Bosch