Human Robot Collaborative Assembly - Multi Instance Multi Object Tracking

In a goal oriented Human Robot Collaborative (HRC) scenario, where the goal is to complete an assembly process, a robust object tracker might not necessarily fulfill its functional role due to the dynamic nature of HRC. Moreover, for an efficient HRC, the functional role of object tacker should not only be limited to localizing and tracking object for robotic manipulation. It should also a) determine the current state of the assembly process and b) verify if the chosen action has been successfully performed. Thus enabling an uninterrupted completion of an HRC assembly process. We present a Context Enhanced Framework for Multi Object Tracking, that i) allows uninterrupted completion of assembly process ii) improves the overall functional accuracy of the object tracker from 49 percent to 96 percent iii) enables the object tracker to handle multiple instance of multiple objects in a HRC setting. [Reference] Sharath Chandra Akkaladevi, Matthias Plasch, Christian Eitzinger, Andreas Pichler and Bernhard Rinner, Towards a Context Enhanced Framework for Multi Object Tracking in Human Robot Collaboration, in Proc. IEEE International Conference on Intelligent Robots (IROS) 2018