• K.R. Ishwarya, Manikandan Ganesan, Ganesh Babu Loganathan
Keywords: Covid-19, Machine learning, Faster-R-CNN, Congestion, GoogLeNet, RPN, AI Robots


The Covid-19 epidemic has changed almost every aspect of human life to an unparalleled degree. At the same time, the pandemic has prompted a tremendous number of studies by scientists across a wide variety of disciplines, trying to examine the phenomenon itself, its epidemiological features, and ways of confronting its implications. Social distancing and isolation are the key steps to limit the spread of this pandemic, where manual activities are usually done by humans are suddenly out of control or dangerous. Undertaking these activities without human-to-human interaction is just where the robotics industry can give real value. Integrating a robot is an effective weapon to fight the spread of this ubiquitous virus. Robots may be used in a monitoring capacity when areas need to be monitored to ensure social distance or lockout protocols are followed. A crowd congestion control robot is proposed in this research to ensure social distance is preserved in public areas, shops, and malls. This AI-powered robot uses computer vision detection and tracking techniques to determine the crowd. Faster R-CNN architecture is used to detect artifacts using a pre-trained CNN model and the abnormality is reported. This proposed congestion control strategy has significant benefits.

How to Cite
Ganesh Babu Loganathan, K. I. M. G. (2021). CROWD CONTROL ROBOT FOR CONGESTION CONTROL. Design Engineering, 3377- 3391. Retrieved from