English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In primate brains, tactile and proprioceptive inputs are relayed to thesomatosensory cortex which is known for somatotopic representations, or,"homunculi". Our research centers on understanding the mechanisms of theformation of these and more higher-level body representations (body schema) byusing humanoid robots and neural networks to construct models. We specificallyfocus on how spatial representation of the body may be learned fromsomatosensory information in self-touch configurations. In this work, we targetthe representation of proprioceptive inputs, which we take to be joint anglesin the robot. The inputs collected in different body postures serve as inputsto a Self-Organizing Map (SOM) with a 2D lattice on the output. Withunrestricted, all-to-all connections, the map is not capable of representingthe input space while preserving the topological relationships, because theintrinsic dimensionality of the body posture space is too large. Hence, we usea method we developed previously for tactile inputs (Hoffmann, Straka et al.2018) called MRF-SOM, where the Maximum Receptive Field of output neurons isrestricted so they only learn to represent specific parts of the input space.This is in line with the receptive fields of neurons in somatosensory areasrepresenting proprioception that often respond to combination of few joints(e.g. wrist and elbow).

The homunculus for proprioception: Toward learning the representation of a humanoid robot's joint space using self-organizing maps