Embedded neuromorphic vision for humanoid robots
Authors:
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 129-135
Abstract
We are developing an embedded vision system for the humanoid robot iCub, inspired by the biology of the mammalian visual system, including concepts such as stimulus-driven, asynchronous signal sensing and processing. It comprises stimulus-driven sensors, a dedicated embedded processor and an event-based software infrastructure for processing visual stimuli. These components are integrated with the existing standard machine vision modules currently implemented on the robot, in a configuration that exploits the best features of both: the high resolution, color, frame-based vision and the neuromorphic low redundancy, wide dynamic range and high temporal resolution event-based sensors. This approach seeks to combine various styles of vision hardware with sensorimotor systems to complement and extend the current state-of-the art.Keywords
This publication has 27 references indexed in Scilit:
- Spotting animals in natural scenes: efficiency of humans and monkeys at very low contrastsAnimal Cognition, 2009
- Selective Attention in Multi-Chip Address-Event SystemsSensors, 2009
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008
- Towards long-lived robot genesRobotics and Autonomous Systems, 2007
- Modeling attention to salient proto-objectsNeural Networks, 2006
- Neuromorphic MicrochipsScientific American, 2005
- A 128 x 128 pixel 120-db dynamic-range vision-sensor chip for image contrast and orientation extractionIEEE Journal of Solid-State Circuits, 2003
- Disparity Estimation on Log-Polar Images and Vergence ControlComputer Vision and Image Understanding, 2001
- Analyzing vision at the complexity levelBehavioral and Brain Sciences, 1990
- Neuromorphic electronic systemsProceedings of the IEEE, 1990