Allothetic and idiothetic sensor fusion in rat-inspired robot localization

Alfredo Weitzenfeld, Jean-Marc Fellous, Alejandra Barrera, Gonzalo Tejera

Research output: Chapter in Book/Report/Conference proceedingChapter

2 Citations (Scopus)

Abstract

We describe a spatial cognition model based on the rat's brain neurophysiology as a basis for new robotic navigation architectures. The model integrates allothetic (external visual landmarks) and idiothetic (internal kinesthetic information) cues to train either rat or robot to learn a path enabling it to reach a goal from multiple starting positions. It stands in contrast to most robotic architectures based on SLAM, where a map of the environment is built to provide probabilistic localization information computed from robot odometry and landmark perception. Allothetic cues suffer in general from perceptual ambiguity when trying to distinguish between places with equivalent visual patterns, while idiothetic cues suffer from imprecise motions and limited memory recalls. We experiment with both types of cues in different maze configurations by training rats and robots to find the goal starting from a fixed location, and then testing them to reach the same target from new starting locations. We show that the robot, after having pre-explored a maze, can find a goal with improved efficiency, and is able to (1) learn the correct route to reach the goal, (2) recognize places already visited, and (3) exploit allothetic and idiothetic cues to improve on its performance. We finally contrast our biologically-inspired approach to more traditional robotic approaches and discuss current work in progress.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume8407
DOIs
StatePublished - 2012
EventMultisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2012 - Baltimore, MD, United States
Duration: Apr 25 2012Apr 26 2012

Other

OtherMultisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2012
CountryUnited States
CityBaltimore, MD
Period4/25/124/26/12

Fingerprint

Sensor Fusion
multisensor fusion
cues
robots
rats
Rats
Fusion reactions
Robot
Robots
Robotics
robotics
Sensors
Landmarks
landmarks
Spatial Cognition
Neurophysiology
supersonic low altitude missile
neurophysiology
Simultaneous Localization and Mapping
cognition

Keywords

  • Biologically-inspired
  • Localization
  • Navigation
  • Robotics
  • SLAM
  • Spatial cognition

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Weitzenfeld, A., Fellous, J-M., Barrera, A., & Tejera, G. (2012). Allothetic and idiothetic sensor fusion in rat-inspired robot localization. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 8407). [84070E] https://doi.org/10.1117/12.918153

Allothetic and idiothetic sensor fusion in rat-inspired robot localization. / Weitzenfeld, Alfredo; Fellous, Jean-Marc; Barrera, Alejandra; Tejera, Gonzalo.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8407 2012. 84070E.

Research output: Chapter in Book/Report/Conference proceedingChapter

Weitzenfeld, A, Fellous, J-M, Barrera, A & Tejera, G 2012, Allothetic and idiothetic sensor fusion in rat-inspired robot localization. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 8407, 84070E, Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2012, Baltimore, MD, United States, 4/25/12. https://doi.org/10.1117/12.918153
Weitzenfeld A, Fellous J-M, Barrera A, Tejera G. Allothetic and idiothetic sensor fusion in rat-inspired robot localization. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8407. 2012. 84070E https://doi.org/10.1117/12.918153
Weitzenfeld, Alfredo ; Fellous, Jean-Marc ; Barrera, Alejandra ; Tejera, Gonzalo. / Allothetic and idiothetic sensor fusion in rat-inspired robot localization. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 8407 2012.
@inbook{279bb117ddec4466bd1b3061f9feae1b,
title = "Allothetic and idiothetic sensor fusion in rat-inspired robot localization",
abstract = "We describe a spatial cognition model based on the rat's brain neurophysiology as a basis for new robotic navigation architectures. The model integrates allothetic (external visual landmarks) and idiothetic (internal kinesthetic information) cues to train either rat or robot to learn a path enabling it to reach a goal from multiple starting positions. It stands in contrast to most robotic architectures based on SLAM, where a map of the environment is built to provide probabilistic localization information computed from robot odometry and landmark perception. Allothetic cues suffer in general from perceptual ambiguity when trying to distinguish between places with equivalent visual patterns, while idiothetic cues suffer from imprecise motions and limited memory recalls. We experiment with both types of cues in different maze configurations by training rats and robots to find the goal starting from a fixed location, and then testing them to reach the same target from new starting locations. We show that the robot, after having pre-explored a maze, can find a goal with improved efficiency, and is able to (1) learn the correct route to reach the goal, (2) recognize places already visited, and (3) exploit allothetic and idiothetic cues to improve on its performance. We finally contrast our biologically-inspired approach to more traditional robotic approaches and discuss current work in progress.",
keywords = "Biologically-inspired, Localization, Navigation, Robotics, SLAM, Spatial cognition",
author = "Alfredo Weitzenfeld and Jean-Marc Fellous and Alejandra Barrera and Gonzalo Tejera",
year = "2012",
doi = "10.1117/12.918153",
language = "English (US)",
isbn = "9780819490858",
volume = "8407",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - CHAP

T1 - Allothetic and idiothetic sensor fusion in rat-inspired robot localization

AU - Weitzenfeld, Alfredo

AU - Fellous, Jean-Marc

AU - Barrera, Alejandra

AU - Tejera, Gonzalo

PY - 2012

Y1 - 2012

N2 - We describe a spatial cognition model based on the rat's brain neurophysiology as a basis for new robotic navigation architectures. The model integrates allothetic (external visual landmarks) and idiothetic (internal kinesthetic information) cues to train either rat or robot to learn a path enabling it to reach a goal from multiple starting positions. It stands in contrast to most robotic architectures based on SLAM, where a map of the environment is built to provide probabilistic localization information computed from robot odometry and landmark perception. Allothetic cues suffer in general from perceptual ambiguity when trying to distinguish between places with equivalent visual patterns, while idiothetic cues suffer from imprecise motions and limited memory recalls. We experiment with both types of cues in different maze configurations by training rats and robots to find the goal starting from a fixed location, and then testing them to reach the same target from new starting locations. We show that the robot, after having pre-explored a maze, can find a goal with improved efficiency, and is able to (1) learn the correct route to reach the goal, (2) recognize places already visited, and (3) exploit allothetic and idiothetic cues to improve on its performance. We finally contrast our biologically-inspired approach to more traditional robotic approaches and discuss current work in progress.

AB - We describe a spatial cognition model based on the rat's brain neurophysiology as a basis for new robotic navigation architectures. The model integrates allothetic (external visual landmarks) and idiothetic (internal kinesthetic information) cues to train either rat or robot to learn a path enabling it to reach a goal from multiple starting positions. It stands in contrast to most robotic architectures based on SLAM, where a map of the environment is built to provide probabilistic localization information computed from robot odometry and landmark perception. Allothetic cues suffer in general from perceptual ambiguity when trying to distinguish between places with equivalent visual patterns, while idiothetic cues suffer from imprecise motions and limited memory recalls. We experiment with both types of cues in different maze configurations by training rats and robots to find the goal starting from a fixed location, and then testing them to reach the same target from new starting locations. We show that the robot, after having pre-explored a maze, can find a goal with improved efficiency, and is able to (1) learn the correct route to reach the goal, (2) recognize places already visited, and (3) exploit allothetic and idiothetic cues to improve on its performance. We finally contrast our biologically-inspired approach to more traditional robotic approaches and discuss current work in progress.

KW - Biologically-inspired

KW - Localization

KW - Navigation

KW - Robotics

KW - SLAM

KW - Spatial cognition

UR - http://www.scopus.com/inward/record.url?scp=84870184693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870184693&partnerID=8YFLogxK

U2 - 10.1117/12.918153

DO - 10.1117/12.918153

M3 - Chapter

SN - 9780819490858

VL - 8407

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -