There are several open PhD positions at ADVR-IIT for 2012 (deadline for application September 23, 2011).
For “Machine Learning, Robot Control and Human-Robot Interaction”, see Stream 3, Themes 2.7 and 2.8, p.22 on the program for Doctoral Course on Robotics, Cognition and Interaction Technologies in this PDF document.
Additionally, a PhD position opening in learning by imitation is advertised below (same instruction as above):
Theme 2.8b: Learning from demonstrations in a soft robotic arm for assistance in minimally invasive surgery
This PhD position will take place within a new European Project starting in 2012, in which the PhD candidate will collaborate with several universities and institutes in Europe. In minimally invasive surgery, tools go through narrow openings and manipulate soft organs that can move, deform, or change stiffness. There are limitations in current robot-assisted surgical systems due to the rigidity of robot tools. A soft robotic arm will be available within the project to manipulate objects while controlling the stiffness of selected body parts. This PhD proposal will focus on the learning, human-robot interaction and variable compliance manipulation aspects.
The objective is to use multiple demonstrations from the teleoperator to learn force/position control manoeuvres so that the teleoperator could, over time, concentrate on high level decisions while the robot takes care of low level reactive control manoeuvres in a semi-autonomous fashion. The PhD candidate will conduct robotic experiments to answer a number of questions in the areas of learning to control the stiffness of selected parts of the body, moving in a constrained space, and to exert desired forces on soft objects with uncertain impedance parameters.
Probabilistic encoding schemes based on Hidden Markov Models will be used to learn a policy that takes into account variability and correlation information collected during consecutive trials. The aim is to estimate an adequate level of compliance depending on the task requirements to leverage the operator with operations that are not directly relevant for the task. The use of novel control algorithms will be explored to arbitrate the degree of coupling of the flexible arm to best suit the statistics of the task (e.g., by stiffening the arm in task relevant dimensions).