Self-Balancing Two-Wheeled Robot Featuring Intelligent End-to-End Deep Visual-Steering

This article proposes a self-balancing wheeled robot named J4.alpha equipped with intelligent modules for automatic navigation. A mechanism involving dynamic mass was designed to control the linear motion of the robot. RGB-D camera was adopted to monitor the front environment; a deep convolutional neural network was adopted to realize a certain level of socially compliant navigation. In combination with the topological localization scheme, J4.alpha can navigate between nodal locations without environment modification. To facilitate the work of the manipulator on-board, an auto-balancing module was designed to maintain force equilibrium. To further secure spatial reliability, motorized parking stands are also introduced. Prototypes were made and tests were carried out to examine the system dynamics. The experimental result confirmed the effectiveness of the intelligent navigation modules.