Modular neural control for a reactive behavior of walking machines

Poramate Manoonpong; Frank Pasemann; Joern Fischer

Modular neural control for a reactive behavior of walking machines

Poramate Manoonpong^*, Frank Pasemann, Joern Fischer

^*Corresponding author for this work

SDU Biorobotics

Fraunhofer IAIS

Research output: Contribution to conference without publisher/journal › Paper › Research › peer-review

Abstract

A small modular neural network is presented which is able to control the sensor-driven behavior of walking machines with many degrees of freedom. The controller is composed of a so called minimal recurrent controller (MRC) for sensory signal processing, a SO(2)-network as neural oscillator to generate the rhythmic leg movements, and a velocity regulating network (VRN) which expands the steering capabilities of the walking machine. This recurrent neurocontroller enables the machine to explore an in-door environment by avoiding obstacles. It was developed and tested using a physical simulation environment, and was then successfully transferred to the physical four-legged walking machine, called AMOS-WD02.

Original language	English
Publication date	12. Dec 2005
Number of pages	6
Publication status	Published - 12. Dec 2005
Event	2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005 - Espoo, Finland Duration: 27. Jun 2005 → 30. Jun 2005

Conference

Conference	2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005
Country/Territory	Finland
City	Espoo
Period	27/06/2005 → 30/06/2005
Sponsor	IEEE Robotics and Automation Society

SDU Link

Check access to the material in SDU Library's search engine

Cite this

@conference{8d51d5a747c84a388e7b2253b09f66af,

title = "Modular neural control for a reactive behavior of walking machines",

abstract = "A small modular neural network is presented which is able to control the sensor-driven behavior of walking machines with many degrees of freedom. The controller is composed of a so called minimal recurrent controller (MRC) for sensory signal processing, a SO(2)-network as neural oscillator to generate the rhythmic leg movements, and a velocity regulating network (VRN) which expands the steering capabilities of the walking machine. This recurrent neurocontroller enables the machine to explore an in-door environment by avoiding obstacles. It was developed and tested using a physical simulation environment, and was then successfully transferred to the physical four-legged walking machine, called AMOS-WD02.",

author = "Poramate Manoonpong and Frank Pasemann and Joern Fischer",

year = "2005",

month = dec,

day = "12",

language = "English",

pages = "403--408",

note = "2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005 ; Conference date: 27-06-2005 Through 30-06-2005",

}

Modular neural control for a reactive behavior of walking machines. / Manoonpong, Poramate; Pasemann, Frank; Fischer, Joern.
2005. 403-408 Paper presented at 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005, Espoo, Finland.

Research output: Contribution to conference without publisher/journal › Paper › Research › peer-review

TY - CONF

T1 - Modular neural control for a reactive behavior of walking machines

AU - Manoonpong, Poramate

AU - Pasemann, Frank

AU - Fischer, Joern

PY - 2005/12/12

Y1 - 2005/12/12

N2 - A small modular neural network is presented which is able to control the sensor-driven behavior of walking machines with many degrees of freedom. The controller is composed of a so called minimal recurrent controller (MRC) for sensory signal processing, a SO(2)-network as neural oscillator to generate the rhythmic leg movements, and a velocity regulating network (VRN) which expands the steering capabilities of the walking machine. This recurrent neurocontroller enables the machine to explore an in-door environment by avoiding obstacles. It was developed and tested using a physical simulation environment, and was then successfully transferred to the physical four-legged walking machine, called AMOS-WD02.

AB - A small modular neural network is presented which is able to control the sensor-driven behavior of walking machines with many degrees of freedom. The controller is composed of a so called minimal recurrent controller (MRC) for sensory signal processing, a SO(2)-network as neural oscillator to generate the rhythmic leg movements, and a velocity regulating network (VRN) which expands the steering capabilities of the walking machine. This recurrent neurocontroller enables the machine to explore an in-door environment by avoiding obstacles. It was developed and tested using a physical simulation environment, and was then successfully transferred to the physical four-legged walking machine, called AMOS-WD02.

UR - http://www.scopus.com/inward/record.url?scp=28444491776&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:28444491776

SP - 403

EP - 408

T2 - 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005

Y2 - 27 June 2005 through 30 June 2005

ER -

Modular neural control for a reactive behavior of walking machines

Abstract

Conference

SDU Link

Other files and links

Fingerprint

Cite this