Evolutionary algorithm based neural network controller optimization for autonomous mobile robot navigation

Han, Seong-Joo; Oh, Se‐Young

doi:10.1109/cec.2001.934380

Cited by 5 publications

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

An obstacle avoidance method for mobile robots based on fuzzy decision-making

Kim¹,

Cho²

2006

Robotica

View full text Add to dashboard Cite

SUMMARYIn this paper, an obstacle avoidance method for wheeled mobile robots is proposed, based on selection of the local target points of robot's movement called "via-points" which are defined in a navigation space, generated by taking into consideration a smooth robot motion. The proposed algorithm utilizes a fuzzy multi-attribute decision-making method in which three fuzzy goals are defined to achieve successful robot navigation by deciding the via-point the robot would proceed at each control step. Via-point is defined as the local target point of a robot's movement at each decision instance. Three fuzzy goals to achieve successful robot navigation are defined. At each decision step, a set of the candidates of a next via-point in a 2D navigation space is constructed by combining various heading angles and velocities. Given the fuzzy goals, the fuzzy decision making enables the robot to choose the best via-point among the candidates. An efficient scheme for local minimum recovery from trappedin situation is also provided. A series of simulations has been performed to study the effects of associated navigation parameters on the navigation performances. The method has been implemented on an actual mobile robot and experimented in real environments. Results from a series of simulations and experiments conducted in real environments show the validity and effectiveness of the proposed navigation method.

show abstract