Behaviour-based architecture for abstract learning and control

Pejman Iravani

Behaviour-based architecture for abstract learning and control

Pejman Iravani

Department of Mechanical Engineering

Research output: Contribution to conference › Paper

Abstract

This paper presents a modular behaviour-based architecture for the control and learning of behaviours in mobile robots. The main contribution of this paper is the integration of techniques for generating grounded symbols from raw sensory-motor data and traditional behaviour-based architectures. The resulting architecture reduces the intrinsic dimensionality problems of robotics and allows for abstract control. The architecture is experimentally validated on a simulated robot environment.

Original language	English
Publication status	Published - 2004
Event	Towards Autonomous Robotic Systems (TAROS-04) - Colchester, UK United Kingdom Duration: 1 Sept 2004 → …

Conference

Conference	Towards Autonomous Robotic Systems (TAROS-04)
Country/Territory	UK United Kingdom
City	Colchester
Period	1/09/04 → …

Cite this

@conference{d2b46b1d3e5c4310a2b7daff1a64fd10,

title = "Behaviour-based architecture for abstract learning and control",

abstract = "This paper presents a modular behaviour-based architecture for the control and learning of behaviours in mobile robots. The main contribution of this paper is the integration of techniques for generating grounded symbols from raw sensory-motor data and traditional behaviour-based architectures. The resulting architecture reduces the intrinsic dimensionality problems of robotics and allows for abstract control. The architecture is experimentally validated on a simulated robot environment.",

author = "Pejman Iravani",

year = "2004",

language = "English",

note = "Towards Autonomous Robotic Systems (TAROS-04) ; Conference date: 01-09-2004",

}

TY - CONF

T1 - Behaviour-based architecture for abstract learning and control

AU - Iravani, Pejman

PY - 2004

Y1 - 2004

N2 - This paper presents a modular behaviour-based architecture for the control and learning of behaviours in mobile robots. The main contribution of this paper is the integration of techniques for generating grounded symbols from raw sensory-motor data and traditional behaviour-based architectures. The resulting architecture reduces the intrinsic dimensionality problems of robotics and allows for abstract control. The architecture is experimentally validated on a simulated robot environment.

AB - This paper presents a modular behaviour-based architecture for the control and learning of behaviours in mobile robots. The main contribution of this paper is the integration of techniques for generating grounded symbols from raw sensory-motor data and traditional behaviour-based architectures. The resulting architecture reduces the intrinsic dimensionality problems of robotics and allows for abstract control. The architecture is experimentally validated on a simulated robot environment.

M3 - Paper

T2 - Towards Autonomous Robotic Systems (TAROS-04)

Y2 - 1 September 2004

ER -

Behaviour-based architecture for abstract learning and control

Abstract

Conference

Fingerprint

Cite this