Object-Independent Human-to-Robot Handovers using Real Time Robotic Vision

June 02, 2020 · Entered Twilight · 🏛 IEEE Robotics and Automation Letters

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CMakeLists.txt, LICENSE, README.md, _config.yml, cfg, docs, imgs, launch, package.xml, requirements.txt, src

Authors Patrick Rosenberger, Akansel Cosgun, Rhys Newbury, Jun Kwan, Valerio Ortenzi, Peter Corke, Manfred Grafinger arXiv ID 2006.01797 Category cs.RO: Robotics Cross-listed cs.CV, cs.LG Citations 105 Venue IEEE Robotics and Automation Letters Repository https://github.com/patrosat/h2r_handovers ⭐ 36 Last Checked 19 days ago

Abstract

We present an approach for safe and object-independent human-to-robot handovers using real time robotic vision and manipulation. We aim for general applicability with a generic object detector, a fast grasp selection algorithm and by using a single gripper-mounted RGB-D camera, hence not relying on external sensors. The robot is controlled via visual servoing towards the object of interest. Putting a high emphasis on safety, we use two perception modules: human body part segmentation and hand/finger segmentation. Pixels that are deemed to belong to the human are filtered out from candidate grasp poses, hence ensuring that the robot safely picks the object without colliding with the human partner. The grasp selection and perception modules run concurrently in real-time, which allows monitoring of the progress. In experiments with 13 objects, the robot was able to successfully take the object from the human in 81.9% of the trials.