Prof. Dr. Elmar Rückert - Institut für Robotik und Kognitive Systeme (UzL)
Abstract
-------------
In this talk, I discuss how a probabilisitc model can be used to predict complex
human movements from observing only a few milleseconds of a subset of all
recorded limb trajectories. The model can handle partial observable, missing
data and is robust to sensor noise. In a postural control experiment, I
demonstrate how this model can be used to predict goal directed right arm
motions solely from observing the motion of the trunk or left arm. The model can
be also used for model validation, classification and movement analyses and is
as such interesting for a broad range of research approaches working with
multi-modal motion data.
In the second part of my talk, I discuss how recurrent neural networks can be
used for motion planning and obstacle avoidance. The model is based on the
probabilistic inference framework and can be trained through reinforcement
learning. It can be used to explain neural recordings of mental replays and
pre-plays in rats during navigation tasks and provides a probabilistic theory
for more complex cognitive reasoning tasks.
-------------
Ort: INB Seminarraum (Geb. 64, 1. OG, Raum 17)
