Naslov
Methodology of Concept Control Synthesis to Avoid Unmoving and Moving Obstacles

Autori
Kulić, Ranka ; Vukić, Zoran

Izvornik
Journal of Intelligent & Robotic Systems (0921-0296) 37 (2003), 1; 21-41

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Behavioral cloning; cloning success; linear regression; machine learning; obstacle avoidance; robot motion planning

Sažetak
The dynamic path generation problem of robots in environments with other unmoving and moving objects is considered. Generally, the problem is known in the literature as find path or robot motion planning. In this paper, we apply the behavioral cloning approach to design the robot controller. In behavioral cloning, the system learns from control traces of a human operator. The task for the given problem is to find a controller in the form of an explicit mathematical expression. Thus, machine learning programs to induce the operator's trajectories as a set of symbolic constraints are used. Then, mathematical induction to generalize the obtained equations in order to apply them in situ with an infinite number of obstacles is also used. A method to evaluate cloning success is proposed. The typical kind of noise is included.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA