Naslov
Mobile Robot Path Planing Using Gauss Potential Functions and Neural Network : Chapter 30

Autori
Kasać, Josip ; Brezak, Danko ; Majetić, Dubravko ; Novaković, Branko

Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni

Knjiga
DAAAM International Scientific Book 2002

Urednik/ci
Katalinić, Branko

Izdavač
DAAAM International Vienna

Grad
Beč

Godina
2002

Raspon stranica
287-298

ISBN
3-901509-30-5

Ključne riječi
mobile robot, motion planning, potential field, RBF neural network, real-time control

Sažetak
This work deals with the problem of potential field based mobile robot motion planning in unorganised environment. The new approach, using a combination of negative gradient and vortex field based on Gauss potential functions, is proposed. Radial Basis Function Neural Network (RBF Neural Network) learns the dependence between Gauss function parameters and velocity of mobile robot (or relative velocity between robot and obstacle in dynamical environment) ensuring passage between two closely spaced obstacles and smooth path condition. This approach overcomes some standard problems in classical potential field methods like local minima avoidance, problems of no passage between closely spaced obstacles, avoidance of moving obstacles and trajectory oscillations.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Strojarstvo

POVEZANOST RADA