University of Hertfordshire

By the same authors

A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies

Research output: Contribution to conferencePaperpeer-review

Standard

A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies. / Maye, Alexander; Trendafilov, Dari; Polani, D.; Engel, Andreas.

2015. Paper presented at IROS 2015 Workshop on Sensorimotor Contingencies For Robotics, Hamburg, Germany.

Research output: Contribution to conferencePaperpeer-review

Harvard

Maye, A, Trendafilov, D, Polani, D & Engel, A 2015, 'A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies', Paper presented at IROS 2015 Workshop on Sensorimotor Contingencies For Robotics, Hamburg, Germany, 2/10/15.

APA

Maye, A., Trendafilov, D., Polani, D., & Engel, A. (2015). A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies. Paper presented at IROS 2015 Workshop on Sensorimotor Contingencies For Robotics, Hamburg, Germany.

Vancouver

Maye A, Trendafilov D, Polani D, Engel A. A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies. 2015. Paper presented at IROS 2015 Workshop on Sensorimotor Contingencies For Robotics, Hamburg, Germany.

Author

Maye, Alexander ; Trendafilov, Dari ; Polani, D. ; Engel, Andreas. / A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies. Paper presented at IROS 2015 Workshop on Sensorimotor Contingencies For Robotics, Hamburg, Germany.

Bibtex

@conference{df2690032ac04f48b8873bb39a5e7987,
title = "A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies",
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.",
author = "Alexander Maye and Dari Trendafilov and D. Polani and Andreas Engel",
note = "Alexander Maye, Dari Trendafilov, Daniel Polani, Andreas Engel, {\textquoteleft}A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies{\textquoteright}, paper presented at the International Conference on Intelligent Robots and Systems (IROS) 2015 Workshop on Sensorimotor Contingencies for Robotics, Hamburg, Germany, 2 October, 2015. ; IROS 2015 Workshop on Sensorimotor Contingencies For Robotics ; Conference date: 02-10-2015",
year = "2015",
month = oct,
day = "2",
language = "English",

}

RIS

TY - CONF

T1 - A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies

AU - Maye, Alexander

AU - Trendafilov, Dari

AU - Polani, D.

AU - Engel, Andreas

N1 - Alexander Maye, Dari Trendafilov, Daniel Polani, Andreas Engel, ‘A visual attention mechanism for autonomous robots controlled by sensorimotor contingencies’, paper presented at the International Conference on Intelligent Robots and Systems (IROS) 2015 Workshop on Sensorimotor Contingencies for Robotics, Hamburg, Germany, 2 October, 2015.

PY - 2015/10/2

Y1 - 2015/10/2

N2 - 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.

AB - 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.

M3 - Paper

T2 - IROS 2015 Workshop on Sensorimotor Contingencies For Robotics

Y2 - 2 October 2015

ER -