Tracking improves performance of biological collision avoidance models

Vivek Pant, Charles M Higgins

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Abstract Collision avoidance models derived from the study of insect brains do not perform universally well in practical collision scenarios, although the insects themselves may perform well in similar situations. In this article, we present a detailed simulation analysis of two well-known collision avoidance models and illustrate their limitations. In doing so, we present a novel continuous-time implementation of a neuronally based collision avoidance model. We then show that visual tracking can improve performance of thesemodels by allowing an relative computation of the distance between the obstacle and the observer.We compare the results of simulations of the two models with and without tracking to show how tracking improves the ability of the model to detect an imminent collision.We present an implementation of one of thesemodels processing imagery from a camera to showhow it performs in real-world scenarios. These results suggest that insects may track looming objects with their gaze.

Original languageEnglish (US)
Pages (from-to)307-322
Number of pages16
JournalBiological Cybernetics
Volume106
Issue number4-5
DOIs
StatePublished - Jul 2012

Fingerprint

Collision avoidance
Insects
Aptitude
Imagery (Psychotherapy)
Brain
Cameras
Processing

Keywords

  • Collision avoidance
  • Computational modeling
  • Computer vision
  • Insect vision

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science(all)

Cite this

Tracking improves performance of biological collision avoidance models. / Pant, Vivek; Higgins, Charles M.

In: Biological Cybernetics, Vol. 106, No. 4-5, 07.2012, p. 307-322.

Research output: Contribution to journalArticle

@article{e8d7de0cf9ae4b0cad33722f3e68cc1e,
title = "Tracking improves performance of biological collision avoidance models",
abstract = "Abstract Collision avoidance models derived from the study of insect brains do not perform universally well in practical collision scenarios, although the insects themselves may perform well in similar situations. In this article, we present a detailed simulation analysis of two well-known collision avoidance models and illustrate their limitations. In doing so, we present a novel continuous-time implementation of a neuronally based collision avoidance model. We then show that visual tracking can improve performance of thesemodels by allowing an relative computation of the distance between the obstacle and the observer.We compare the results of simulations of the two models with and without tracking to show how tracking improves the ability of the model to detect an imminent collision.We present an implementation of one of thesemodels processing imagery from a camera to showhow it performs in real-world scenarios. These results suggest that insects may track looming objects with their gaze.",
keywords = "Collision avoidance, Computational modeling, Computer vision, Insect vision",
author = "Vivek Pant and Higgins, {Charles M}",
year = "2012",
month = "7",
doi = "10.1007/s00422-012-0499-1",
language = "English (US)",
volume = "106",
pages = "307--322",
journal = "Biological Cybernetics",
issn = "0340-1200",
publisher = "Springer Verlag",
number = "4-5",

}

TY - JOUR

T1 - Tracking improves performance of biological collision avoidance models

AU - Pant, Vivek

AU - Higgins, Charles M

PY - 2012/7

Y1 - 2012/7

N2 - Abstract Collision avoidance models derived from the study of insect brains do not perform universally well in practical collision scenarios, although the insects themselves may perform well in similar situations. In this article, we present a detailed simulation analysis of two well-known collision avoidance models and illustrate their limitations. In doing so, we present a novel continuous-time implementation of a neuronally based collision avoidance model. We then show that visual tracking can improve performance of thesemodels by allowing an relative computation of the distance between the obstacle and the observer.We compare the results of simulations of the two models with and without tracking to show how tracking improves the ability of the model to detect an imminent collision.We present an implementation of one of thesemodels processing imagery from a camera to showhow it performs in real-world scenarios. These results suggest that insects may track looming objects with their gaze.

AB - Abstract Collision avoidance models derived from the study of insect brains do not perform universally well in practical collision scenarios, although the insects themselves may perform well in similar situations. In this article, we present a detailed simulation analysis of two well-known collision avoidance models and illustrate their limitations. In doing so, we present a novel continuous-time implementation of a neuronally based collision avoidance model. We then show that visual tracking can improve performance of thesemodels by allowing an relative computation of the distance between the obstacle and the observer.We compare the results of simulations of the two models with and without tracking to show how tracking improves the ability of the model to detect an imminent collision.We present an implementation of one of thesemodels processing imagery from a camera to showhow it performs in real-world scenarios. These results suggest that insects may track looming objects with their gaze.

KW - Collision avoidance

KW - Computational modeling

KW - Computer vision

KW - Insect vision

UR - http://www.scopus.com/inward/record.url?scp=84864550863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864550863&partnerID=8YFLogxK

U2 - 10.1007/s00422-012-0499-1

DO - 10.1007/s00422-012-0499-1

M3 - Article

C2 - 22744199

AN - SCOPUS:84864550863

VL - 106

SP - 307

EP - 322

JO - Biological Cybernetics

JF - Biological Cybernetics

SN - 0340-1200

IS - 4-5

ER -