Autonomous wheelchair navigation with real time obstacle detection using 3D sensor

Abstract

Autonomous wheelchairs operating in dynamic environments need to sense its surrounding environment and adapt the control signal, in real-time, to avoid collisions and protect the user. In this paper we propose a robust, simple and real-time autonomous navigation module that drives a wheelchair toward a desired target, along with its capability to avoid obstacles in a 3D dynamic environment. To command the mobile robot to the target, we use a Fuzzy Logic Controller (FLC). For obstacle avoidance, we use the Kinect Xbox 360 to provide an actual map of the environment. The generated map is fed to the reactive obstacle avoidance control Deformable Virtual Zone (DVZ). Simulations and real world experiments results are reported to show the feasibility and the performance of the proposed control system.