This work addresses the task of robot depalletizing by means of a mobile manipulator, taking into account the problem of localizing the boxes to be removed from the pallet and a manipulation strategy that allows to pull the boxes without lifting them with the robot arm. The depalletizing task is of particular interest in the industrial scenario in order to increase efficiency, flexibility and economic affordability of automatic warehouses.The proposed solution makes use of a multi-sensor vision system and a force-controlled collaborative robot in order to detect the boxes on the pallet and to control the robot interaction with the boxes to be removed. The vision system comprises a fixed 3D Time-of-flight camera and an eye-in-hand 2D camera. Preliminary experimental results performed on a laboratory setup with a fixed-based robotic manipulator are reported to show the effectiveness of the perception and control system.
In specific virtual reality applications that require high accuracy it may be advisable to replace the built-in tracking system of the HMD with a third party solution. The purpose of this research work is to evaluate the accuracy of the built-in tracking system of the Oculus Rift S Head Mounted Display (HMD) in room scale environments against a motion capture system. In particular, an experimental evaluation of the Oculus Rift S inside-out tracking technology was carried out, compared to the performance of an outside-in tracking method based on the OptiTrack motion capture system. In order to track the pose of the HMD using the motion capture system the Oculus Rift S was instrumented with passive retro-reflective markers and calibrated. Experiments have been performed on a dataset of multiple paths including simple motions as well as more complex paths. Each recorded path contained simultaneous changes in both position and orientation of the HMD. Our results indicate that in room-scale environments the average translation error for the Oculus Rift S tracking system is about $$1.83$$
1.83
cm, and the average rotation error is about $$0.77^\circ$$
0
.
77
∘
, which is 2 orders of magnitude higher than the performance that can be achieved using a motion capture system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.