Humanoid Navigation Strategy Using Fuzzy Motion Planner in a Uneven Smart Home Environment

Abstract

Abstract—This paper presents a fuzzy motion planner for humanoid robots in complex uneven environments. First, we define locomotion primitives for humanoid robots. A high-level planner finds a global path from a global navigation map that is generated based on a combination of 2.5 dimensional maps of the 3D workspace. A mid-level planner creates waypoints that help the robot efficiently cope with various obstacles using only a small set of locomotion primitives that are useful for stable navigation of the robot. A local planner searches for an optimal sequence of locomotion primitives along the global path by using fuzzy motion 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. I.