|
Matthew Howard
Matthew Howard is a postdoctoral researcher involved in the European STIFF Project. He recieved his PhD in July 2009 from Edinburgh University under the supervision of Dr.Sethu Vijayakumar where, in a collaborative project with Honda Research Institute Europe (HRI-EU), he investigated the role of motion constraints in the control and learning of behaviours in anthropomorphic and humanoid robotics. He received his in MSc in Artificial Intelligence from the School of Informatics (University of Edinburgh) in 2005, and, prior to that, an MSci in Physics from Imperial College, London in 2004. His primary research interest is the application of machine learning techniques to robot control. |
|
STIFF Research in this project focusses on the role of impedance control in humans and robots, and brings together a number of partners in the fields of human modelling, novel hardware development and control. At SLMC we are concerned with the machine learning and optimal control aspects of the problem, looking at how impedance control strategies can emerge from first principles of optimality and how these strategies can be applied to variable impedance actuation. See the STIFF project homepage for more details. |
|
Learning from Constrained Motion Data Research in this project focusses on methods for learning control policies from motion data where the demonstrator has been subjected to dynamic, variable constraints on motion. Here we aim to abstract the task from the specifics of the motion induced by the constraints, in order to predict behaviour in novel contexts with novel constraints. |