Gaze control-based navigation architecture using fuzzy integral for humanoid robots

Abstract

When a humanoid robot moves in a dynamic environment, a simple process of planning and following a path may not guarantee competent performance for dynamic obstacle avoidance because the robot acquires limited information from the environment using a local vision sensor. Thus, the distribution of gaze directions is one of the important and difficult issues in navigation for humanoid robots since assigning gaze direction toward surrounding obstacles and map expanding directions have to be considered simultaneously. In particular, the robot needs to distribute its gaze direction to surrounding obstacles including dynamic ones in order to cope with collision issues. In addition, maintaining its gaze direction forward the destination direction has to be also considered. These conflicting objectives generate situations hard to be decided by the robot. In order to cope with this kind of situations, this thesis proposes a fuzzy integral-based gaze control architecture along with the integrated modified-univector field-based navigation for humanoid robots. To determine the gaze direction, four criteria based on local map confidence, waypoint, self-localizat-\\ion and obstacles, are defined along with their corresponding partial evaluation functions. Since all the criteria cannot be independent each other, their integration issues have to be dealt with the consideration of the interconnectivity between them. In order to deal with this issue, fuzzy integral approach has been adopted in this thesis. Using the partial evaluation values and the degree of consideration for criteria, fuzzy integral is applied to each candidate gaze direction for global evaluation. In order to utilize the user preference upon the criteria, Grabish`s graphical interpretation scheme is adopted for the effective user-preference acquisition process. Since the hierarchical structure between criteria is used for the simplification of relationship between criteria, computational effectiveness is...