Abstract
Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.
Original language | English |
---|---|
Title of host publication | Proceedings - IEEE International Conference on Robotics and Automation |
Pages | 3531-3536 |
Number of pages | 6 |
Volume | 4 |
Publication status | Published - 2000 |
Event | ICRA 2000: IEEE International Conference on Robotics and Automation - San Francisco, CA, USA Duration: Apr 24 2000 → Apr 28 2000 |
Other
Other | ICRA 2000: IEEE International Conference on Robotics and Automation |
---|---|
City | San Francisco, CA, USA |
Period | 4/24/00 → 4/28/00 |
Fingerprint
ASJC Scopus subject areas
- Software
- Control and Systems Engineering
Cite this
Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control. / Tar, J.; Rudas, I.; Bito, J. F.; Kozlowski, K.
Proceedings - IEEE International Conference on Robotics and Automation. Vol. 4 2000. p. 3531-3536.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control
AU - Tar, J.
AU - Rudas, I.
AU - Bito, J. F.
AU - Kozlowski, K.
PY - 2000
Y1 - 2000
N2 - Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.
AB - Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.
UR - http://www.scopus.com/inward/record.url?scp=0033718126&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033718126&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0033718126
VL - 4
SP - 3531
EP - 3536
BT - Proceedings - IEEE International Conference on Robotics and Automation
ER -