Fuzzy Footstep Planning for Humanoid Robots Using Locomotion Primitives

보행 프리미티브 기반 휴머노이드 로봇의 퍼지 보행 계획

This paper presents a fuzzy footstep planner for humanoid robots in complex environments. First, we define locomotion primitives for humanoid robots. A global planner finds a global path from a navigation map that is generated based on a combination of 2.5 dimensional maps of the 3D workspace. A local planner searches for an optimal sequence of locomotion primitives along the global path by using fuzzy footstep planning. We verify our approach on a virtual humanoid robot in a simulated environment. Simulation results show a reduction in planning time and the feasibility of the proposed method.