Microrobotic delivery possesses a promising perspective for precision medicine and has attracted much attention recently. However, its automation remains challenging, especially with complex environmental conditions, such as obstacles and obstructed optical feedback. In this article, we propose an automated control approach for a new type of magnetic microrobot, i.e., the multifunctional magnetic spore (Mag-Spore), which has good potential for targeted delivery. By the surface functionalization of the spore with Fe <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub> O <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sub> nanoparticles and carbon quantum dots (QDs), it can be remotely actuated and tracked by an electromagnetic coil system and the fluorescence microscopy, respectively. Our control approach uses fluorescence imaging for vision feedback, which enhances the recognition and tracking of Mag-Spores, obstacles, and cells. Then, information of the obstacles, targeted cells, and Mag-Spores for planning and control is identified by image processing, and an optimal path planner with obstacle-avoidance capability is designed based on the particle swarm optimization (PSO) algorithm. To make the Mag-Spore follow the planed path accurately, a robust model predictive trajectory-tracking controller is synthesized. Simulations are conducted to validate the proposed control approach and tune the control parameters. Experiments demonstrate the effective targeted delivery of the Mag-Spore by using the proposed automated control method under the guidance of fluorescence imaging. Note to Practitioners-This article was motivated by the recent wide interest of precise targeted delivery using biohybrid magnetic microrobots. Driven by external magnetic fields, microrobots accomplish the targeted delivery tasks. In practical applications, obstacles and obstructed optical feedback often exist that make the delivery task challenging. The Mag-Spore presented here has a hollow structure, so that the cargo-carrying capability is maximized and supported by the proposed automated control techniques, and the delivery precision and efficiency are promised in multiple-obstacle scenarios. In addition, the control method has the robustness to model uncertainties and external disturbances that should be considered and well solved in applications. Fluorescence imaging, a common way for observing biomaterials, is compatible with the proposed control scheme and the developed software so that the recognition and tracking of the Mag-Spore and other biomaterials are improved. Moreover, the self-established plug-and-play (PnP) electromagnetic magnetic coil system has the feature of easy installation and configuration on fluorescence microscopes. Simulations and experiments validate the effectiveness of our method in fluorescence-guided targeted delivery using magnetic microrobots.