A reinforcement learning approach to obstacle avoidance of mobile robots (CROSBI ID 484869)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Maček, Kristijan ; Petrović, Ivan ; Perić, Nedjeljko
engleski
A reinforcement learning approach to obstacle avoidance of mobile robots
One of the basic issues in navigation of autonomous mobile robots is the obstacle avoidance task that is commonly achieved using reactive control paradigm where a local mapping from perceived states to actions is acquired. A control strategy with learning capabilities in an unknown environment can be obtained using reinforcement learning where the learning agent is given only sparse reward information. This credit assignment problem includes both temporal and structural aspects. While the temporal credit assignment problem is solved using core elements of reinforcement learning agent, solution of the structural credit assignment problem requires an appropriate internal state space representation of the environment. In this paper a discrete coding of the input space using a neural network structure is presented as opposed to the commonly used continuous internal representation. This enables a faster and more efficient convergence of the reinforcement learning process.
reinforcement learning; mobile robots; obstacle avoidance
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
462-466-x.
2002.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of the 7th IEEE International Workshop on Advanced Motion Control
Jezernik, Karel ; Ohnishi, Kouhei
Maribor: Tiskarna tehniških fakultet Maribor ; IEEE
Podaci o skupu
The 7th IEEE International Workshop on Advanced Motion Control,
predavanje
03.07.2002-05.07.2002
Maribor, Slovenija