Reinforcement Learning for Bio-Inspired Target Seeking

James Gillespie, Iñaki Rañó, Nazmul Siddique, José Santos, Mehdi Khamassi

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Because animals are extremely effective at moving in their natural environments they represent an excellent model to implement robust robotic movement and navigation. Braitenberg vehicles are bio-inspired models of animal navigation widely used in robotics. Tuning the parameters of these vehicles to generate appropriate behaviour can be challenging and time consuming. In this paper we present a Reinforcement Learning methodology to learn the sensori-motor connection of Braitenberg vehicle 3a, a biological model of source seeking. We present simulations of different stimuli and reward functions to illustrate the feasibility of this approach.
Original languageEnglish
Title of host publicationTowards Autonomous Robotic Systems : 18th Annual Conference
EditorsYang Gao, Saber Fallah, Yaochu Jin, Constantina Lekakou
PublisherSpringer
Publication date2017
Pages637-650
ISBN (Print)978-3-319-64106-5
ISBN (Electronic)978-3-319-64107-2
DOIs
Publication statusPublished - 2017
Externally publishedYes
SeriesLecture Notes in Computer Science
Volume10454
ISSN0302-9743

Keywords

  • Braitenberg vehicles
  • Reinforcement learning
  • Source seeking

Fingerprint

Dive into the research topics of 'Reinforcement Learning for Bio-Inspired Target Seeking'. Together they form a unique fingerprint.

Cite this