Evolution of the Sensorimotor Control in an Autonomous Agent

Huber, S; Mallot, HA; Bülthoff, HH

Local TagsRelease HistoryDetailsSummary

Evolution of the Sensorimotor Control in an Autonomous Agent

Huber, S., Mallot, H., & Bülthoff, H.(1996). Evolution of the Sensorimotor Control in an Autonomous Agent (35). Tübingen, Germany: Max Planck Institute for Biological Cybernetics.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-EB5A-5 Version Permalink: https://hdl.handle.net/21.11116/0000-0002-8E7C-4

Genre: Report

Files

show Files

hide Files

:

MPIK-TR-35.pdf (Publisher version), 526KB

View Save

File Permalink:
https://hdl.handle.net/21.11116/0000-0002-8E7D-3

Name:
MPIK-TR-35.pdf

Description:
-

OA-Status:

Visibility:
Public

MIME-Type / Checksum:
application/pdf / [MD5]

Technical Metadata:

View

Copyright Date:
-

Copyright Info:
-

License:
-

Locators

show

Creators

show

hide

Creators:
Huber, S^{1, 2}, Author
Mallot, HA^{1, 2}, Author
Bülthoff, HH^{1, 2}, Author

Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: Visually guided agents are introduced, that evolve their sensor orientations and sensorimotor coupling in a simulated evolution. The work builds on neurobiological results from various aspects of insect navigation and the architecture of the "Vehicles" of Braitenberg (1984). Flies have specialized visuomotor programs for tasks like
compensating for deviations from the course, tracking, and landing, which involve the analysis of visual motion information. We use genetic algorithms to evolve the obstacle avoidance behavior. The sensor orientations and the transmission weights between sensor input and motor output evolve with the sensors and motors acting in a closed
loop of perception and action. The influence of the crossover and mutation probabilities on the outcome of the simulations, specifically the maximum fitness and the convergence of the population are tested.

Details

show

hide

Language(s):

Dates: Date issued: 1996-07

Publication Status: Issued

Pages: 10

Publishing info: Tübingen, Germany : Max Planck Institute for Biological Cybernetics

Table of Contents: -

Rev. Type: -

Identifiers: Report Nr.: 35
BibTex Citekey: 1499

Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show

hide

Title: Technical Report of the Max Planck Institute for Biological Cybernetics

Source Genre: Series

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: 35 Sequence Number: - Start / End Page: - Identifier: -