Grounding of Spatial Language
We propose a bio-inspired unsupervised connectionist architecture and apply it to grounding the spatial
phrases. The two-layer architecture combines by concatenation the information from the visual and the
phonological inputs. The system learns to bind proper lexical
and visual features without any prior knowledge. The simulations reveal that separate processing and
representation of the spatial location and the object shape significantly improve the performance of the model... more
(Download a draft
Path integration using multimodal proprioceptive sensory information
In this case study (Reinstein & Hoffmann, 2011), we have exploited the rich multimodal sensory set on the robot to develop a legged odometer. The odometer was used for aiding of an inertial navigation system using an Extended Kalman Filter, giving rise to a dead reckoning (path integration) system for the robot which was tested for different gaits and grounds.
Physical model of mind - Extension of Neural modeling fields theory
We are developing an extension of Neural modeling fields (NMF) theory (Bayesian parametric modeling) for unknown number of models.
This is a physical model of mind which uses as a learning algorithm a fuzzy dynamic logic.
There plays an essential role a knowledge instinct which is an ability to find patterns in information without any external supervisor
(unsupervised cluster analysis). The goal of NMF is to create an architecture similar to brain.
Bioloid toolbox for Matlab
Toolbox for communication between Robotis Bioloid, CM530 and Matlab that allows to fully control all the robot sensors and efectors. The documentation further describes the installation of firmware
and the establishing of bluetooth and cable connection... more
is newly developed open-source SW tool for simulating complex hybrid (neural) systems.
This SW extends the simulator of Artificial Neural Networks (ANNs) called Nengo with the ability to communicate by means of Robotic Operating System (ROS)...