InjectMeAI—Software Module of an Autonomous Injection Humanoid

Autor: Huebner, Kwame Owusu Ampadu, Florian Rokohl, Safdar Mahmood, Marc Reichenbach, Michael
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Sensors; Volume 22; Issue 14; Pages: 5315
ISSN: 1424-8220
DOI: 10.3390/s22145315
Popis: The recent pandemic outbreak proved social distancing effective in helping curb the spread of SARS-CoV-2 variants along with the wearing of masks and hand gloves in hospitals and assisted living environments. Health delivery personnel having undergone training regarding the handling of patients suffering from Corona infection have been stretched. Administering injections involves unavoidable person to person contact. In this circumstance, the spread of bodily fluids and consequently the Coronavirus become eminent, leading to an upsurge of infection rates among nurses and doctors. This makes enforced home office practices and telepresence through humanoid robots a viable alternative. In providing assistance to further reduce contact with patients during vaccinations, a software module has been designed, developed, and implemented on a Pepper robot that estimates the pose of a patient, identifies an injection spot, and raises an arm to deliver the vaccine dose on a bare shoulder. Implementation was done using the QiSDK in an android integrated development environment with a custom Python wrapper. Tests carried out yielded positive results in under 60 s with an 80% success rate, and exposed some ambient lighting discrepancies. These discrepancies can be solved in the near future, paving a new way for humans to get vaccinated.
Databáze: OpenAIRE
Nepřihlášeným uživatelům se plný text nezobrazuje