The focus of this work is a generic, intraoperative and image-free planning and execution application for arbitrary orthopedic interventions using a novel handheld robotic device and optical see-through glasses (AR). This medical CAD application enables the surgeon to intraoperatively plan the intervention directly on the patient’s bone. The glasses and all the other instruments are accurately calibrated using new techniques. Several interventions show the effectiveness of this approach.

Extended object tracking deals with estimating the shape and pose of an object based on noisy point measurements. This task is not straightforward, as we may be faced with scarce low-quality measurements, little a priori information, or we may be unable to observe the entire target. This work aims to address these challenges by incorporating ideas from active contours and exploiting information from negative measurements, which tell us where the target cannot be.

In optical belt sorting, accurate predictions of the bulk material particles’ motions are required for high-quality results. By implementing a multitarget tracker tailored to the scenario and deriving novel motion models, the predictions are greatly enhanced. The tracker’s reliability is improved by also considering the particles’ orientations. To this end, new estimators for directional quantities based on orthogonal basis functions are presented and shown to outperform the state of the art.