— This paper presents the development of a contact interaction-based navigation strategy for a biped humanoid robot with the aim of supporting current visual-based navigation. The robot arms are equipped with force sensors to detect physical contact with objects. We proposed a motion algorithm consisting of searching tasks, self-localization, correction of locomotion direction and obstacle avoidance. Priority is given to right-side direction to navigate the robot locomotion in conjunction with a strategy to avoid obstacles. The proposed algorithm is evaluated in an experiment with a humanoid robot operating in a room with walls and obstacles. The experimental results reveal good performance of the robot when recognizing objects by touching and grasping, continuously generating suitable trajectory to correct locomotion direction and avoiding collisions.
Hanafiah B. Yussof, Mitsuhiro Yamano, Masahiro Ohk