A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies

Alexander Maye, Dari Trendafilov, D. Polani, Andreas Engel

Research output: Contribution to conferencePaperpeer-review

78 Downloads (Pure)

Abstract

Robot control architectures that are based on learning the dependencies between robot's actions and the resulting change in sensory input face the fundamental problem that for high-dimensional action and/or sensor spaces, the number of these sensorimotor dependencies can become huge. In this article we present a scenario of a robot that learns to avoid collisions with stationary objects from image-based motion flow and a collision detector. Following an information-theoretic approach, we demonstrate that the robot can infer image regions that facilitate the prediction of imminent collisions. This allows restricting the computation to the domain in the input space that is relevant for the given task, which enables learning sensorimotor contingencies in robots with high-dimensional sensor spaces.
Original languageEnglish
Publication statusPublished - 2 Oct 2015
EventIROS 2015 Workshop on Sensorimotor Contingencies For Robotics - Congress Center Hamburg, Hamburg, Germany
Duration: 2 Oct 2015 → …

Workshop

WorkshopIROS 2015 Workshop on Sensorimotor Contingencies For Robotics
Country/TerritoryGermany
CityHamburg
Period2/10/15 → …

Fingerprint

Dive into the research topics of 'A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies'. Together they form a unique fingerprint.

Cite this