Journal article Open Access
Albini Alessandro;
Giorgio Cannata
{ "files": [ { "links": { "self": "https://zenodo.org/api/files/90ada09c-b5e9-4a3c-bd89-cfdceeb64939/Pressure%20Distribution%20Classification%20and%20Segmentation%20of%20Human%20Hands%20in%20Contact%20with%20the%20Robot%20Body.pdf" }, "checksum": "md5:6f0e43d7291d99e5372d0e9f2b56f1ce", "bucket": "90ada09c-b5e9-4a3c-bd89-cfdceeb64939", "key": "Pressure Distribution Classification and Segmentation of Human Hands in Contact with the Robot Body.pdf", "type": "pdf", "size": 5050158 } ], "owners": [ 94023 ], "doi": "10.1177/0278364920907688", "stats": { "version_unique_downloads": 49.0, "unique_views": 35.0, "views": 39.0, "version_views": 39.0, "unique_downloads": 49.0, "version_unique_views": 35.0, "volume": 282808848.0, "version_downloads": 56.0, "downloads": 56.0, "version_volume": 282808848.0 }, "links": { "doi": "https://doi.org/10.1177/0278364920907688", "latest_html": "https://zenodo.org/record/3706665", "bucket": "https://zenodo.org/api/files/90ada09c-b5e9-4a3c-bd89-cfdceeb64939", "badge": "https://zenodo.org/badge/doi/10.1177/0278364920907688.svg", "html": "https://zenodo.org/record/3706665", "latest": "https://zenodo.org/api/records/3706665" }, "created": "2020-03-11T12:50:44.391035+00:00", "updated": "2020-03-11T20:20:24.557215+00:00", "conceptrecid": "3706664", "revision": 3, "id": 3706665, "metadata": { "access_right_category": "success", "doi": "10.1177/0278364920907688", "description": "<p>This paper deals with the problem of the recognition of human hand touch by a robot equipped with large area tactile<br>\nsensors covering its body. This problem is relevant in the domain of physical human-robot interaction for discriminating<br>\nbetween human and non-human contacts and to trigger and to drive cooperative tasks or robot motions, or to ensure a<br>\nsafe interaction. The underlying assumption, used in this paper, is that voluntary physical interaction tasks involve hand<br>\ntouch over the robot body, and therefore the capability of recognizing hand contacts is a key element to discriminate a<br>\npurposive human touch from other types of interaction.<br>\nThe proposed approach is based on a geometric transformation of the tactile data, formed by pressure measurements<br>\nassociated to a non uniform cloud of 3D points (taxels) spread over a non linear manifold corresponding to the robot<br>\nbody, into tactile images representing the contact pressure distribution in 2D. Tactile images can be processed using<br>\ndeep learning algorithms to recognize human hands and to compute the pressure distribution applied by the various<br>\nhand segments: palm and single fingers.<br>\nExperimental results, performed on a real robot covered with robot skin, show the effectiveness of the proposed<br>\nmethodology. Moreover, to evaluate its robustness, various types of failures have been simulated. A further analysis<br>\nconcerning the transferability of the system has been performed, considering contacts occurring on a different<br>\nsensorized robot part.</p>", "language": "eng", "title": "Pressure Distribution Classification and Segmentation of Human Hands in Contact with the Robot Body", "license": { "id": "CC-BY-4.0" }, "relations": { "version": [ { "count": 1, "index": 0, "parent": { "pid_type": "recid", "pid_value": "3706664" }, "is_last": true, "last_child": { "pid_type": "recid", "pid_value": "3706665" } } ] }, "communities": [ { "id": "collaborate_project" } ], "grants": [ { "code": "820767", "links": { "self": "https://zenodo.org/api/grants/10.13039/501100000780::820767" }, "title": "Co-production CeLL performing Human-Robot Collaborative AssEmbly", "acronym": "CoLLaboratE", "program": "H2020", "funder": { "doi": "10.13039/501100000780", "acronyms": [], "name": "European Commission", "links": { "self": "https://zenodo.org/api/funders/10.13039/501100000780" } } } ], "keywords": [ "tactile sensing, robot skin, human robot interaction" ], "publication_date": "2020-03-10", "creators": [ { "orcid": "0000-0003-1562-7044", "affiliation": "University of Genoa", "name": "Albini Alessandro" }, { "orcid": "0000-0001-7932-5411", "affiliation": "University of Genoa", "name": "Giorgio Cannata" } ], "access_right": "open", "resource_type": { "subtype": "article", "type": "publication", "title": "Journal article" } } }
Views | 39 |
Downloads | 56 |
Data volume | 282.8 MB |
Unique views | 35 |
Unique downloads | 49 |