A Unified Model For Developmental Robotics



A Unified Model For Developmental Robotics

Williams Paquier, Nicolas Do Huu, Raja Chatila

LAAS/CNRS, 7 avenue du Colonel Roche, F-31077 Toulouse Cedex 04, France
[email protected], [email protected], [email protected]

Abstract

We present the architecture and distributed
algorithms of an implemented system called
NeuSter, that unifies learning, perception and ac-
tion for autonomous robot control. NeuSter com-
prises several sub-systems that provide online
learning for networks of million neurons on ma-
chine clusters. It extracts information from sen-
sors, builds its own representations of the envi-
ronment in order to learn non-predefined goals.

1. A need for a common framework

Several approaches and models propose developmen-
tal robot properties (Tijsseling and Berthouze, 2001,
MacDorman et al., 2001). From a robotics point of view,
all these properties should be implemented in a single
system and the question of system integration must be ad-
dressed. We propose a multi-scale and distributed model
which permits to address online perception, representa-
tion, goal learning, and skill acquisition. With this sys-
tem, the robot acquires new capabilities by building new
representations, starting from a very elementary prede-
fined set, and by synthezising new actions (or skills) also
using a very limited elementary set as a starting vocabu-
lary. Learning and adaptation rely on an exploration pro-
cess that enables to build and reinforce the representa-
tions and actions. These actions are the more rewarding
in achieving the system’s goals, which are also incremen-
tally learned. No predefined structures are given to the
system - except its general neural architecture. The clas-
sical symbol grounding problem (Harnad, 1990) is thus
addressed.

System architecture is described in the next section,
and an example of operation in section 3.

2. System Architecture

The global system has two main properties : a) the first is
extraction of representations from the environment, and
b) the second is action chaining to obtain the representa-
tions which produce the best global effect. The system is
composed of seven functional subsystems as depicted in
Figure 1 (Paquier and Chatila, 2002).

The system is structured in slices of connected
Pulsed Neural Networks (PNN) based on a discrete in-
tegrate and fire model. PNN provide a level of de-
scription that allows to develop the learning process
(Gerstner and Kistler, 2002), categorization and associ-
ation, while avoiding combinatorial explosion. Within
each slice’s thickness, six neurons are connected to form
a column which is the basic element of the system. The
first three neurons of a column are responsible for infor-
mation extraction and competition in the input stream, the
fourth neuron is responsible for the persistence of detec-
tion and is the input to the next slices. The last two neu-
rons are responsible for the scoring process and its diffu-
sion in the global system.

,'У\

Figure 1: Global system and sensory-motor loops. Plain ar-
rows are hard-coded pathways and dotted arrows correspond to
learned pathways.

The functions of the seven subsystems are as follows:

Sensing (SEN) is the input of the global system
and is the frontier between the environment and the neu-
ral space. It is composed of maps of converter neu-
rons between physical value and computable information
wherein the potential values are static and dynamic “im-
ages” of the stimuli.

Initial Representations (IR) is a neuronal structure
which is the initial set of representation goals. Each neu-
ron in IR can be activated by SEN, and the result of this
activation has a predefined effect on the criteria satisfac-
tion (see GE next). IR can be considered as the initial
position in the
representation/score space. The system
behaviour will grow from this point.

Context Decomposition (CD) can be defined as the
categorization engine. It extracts all the high-level fea-
tures that could be used to describe the environment. It is

    1   2  


More intriguing information

1. The effect of classroom diversity on tolerance and participation in England, Sweden and Germany
2. Estimating the Economic Value of Specific Characteristics Associated with Angus Bulls Sold at Auction
3. BEN CHOI & YANBING CHEN
4. Road pricing and (re)location decisions households
5. The Impact of Financial Openness on Economic Integration: Evidence from the Europe and the Cis
6. The name is absent
7. Can we design a market for competitive health insurance? CHERE Discussion Paper No 53
8. Linkages between research, scholarship and teaching in universities in China
9. Examining the Regional Aspect of Foreign Direct Investment to Developing Countries
10. Credit Markets and the Propagation of Monetary Policy Shocks
11. On the Real Exchange Rate Effects of Higher Electricity Prices in South Africa
12. TOWARDS THE ZERO ACCIDENT GOAL: ASSISTING THE FIRST OFFICER MONITOR AND CHALLENGE CAPTAIN ERRORS
13. The name is absent
14. Segmentación en la era de la globalización: ¿Cómo encontrar un segmento nuevo de mercado?
15. Regional specialisation in a transition country - Hungary
16. The Formation of Wenzhou Footwear Clusters: How Were the Entry Barriers Overcome?
17. The name is absent
18. Who’s afraid of critical race theory in education? a reply to Mike Cole’s ‘The color-line and the class struggle’
19. Fiscal Reform and Monetary Union in West Africa
20. Surveying the welfare state: challenges, policy development and causes of resilience