Object Tracking For Robotic Assembly Dataset Creation And Tracking Evaluation

While many current object tracking approaches focus on tracking humans or traffic situations, and not include robotic models, in this work we specifically focus on the task of object tracking in a robotic assembly environment. For this, we outline the specific challenges and chances of object tracking for the assembly purpose and then create a dataset in a PyBullet simulation environment, where a robot arm picks, moves and places a block in the scene. We then evaluate the tracking performance of the AR tracking library VisionLib and conclude that it is not suitable for tracking objects in robotic assembly. Finally, we outline further research topics which are important for creating a good object tracker in robotic assembly.