Predator Evasion by a Robocrab

Abstract

We describe the first robot designed to emulate the specific perceptual and motor capabilities of the fiddler crab. An omnidirectional robot platform uses onboard computation to process images from a 360 degrees camera view, filtering them through a biological model of the crab’s ommatidia layout, extracting potential ‘predator’ cues, and executing an evasion response that also depends on contextual information. We show that, as for real crabs, multiple cues are needed for effective escape in different predator-prey scenarios.

Date
Jul 27, 2017 10:00 AM — 10:20 AM
Location
Stanford University, CA, United States
Evripidis Gkanias
Evripidis Gkanias
Research Associate in Computational & Neuromorphic Modelling

Post-doctoral research associate at the University of Edinburgh, School of Informatics.