Mobile robot detects social distancing violations to reduce spread of COVID-19

A mobile robot is able to detect people in crowds that are not adhering to social-distancing rules and navigates to them. This encourages them to leave. These findings were published by Adarsh Jagan Sathyamoorthy and coworkers at the University of Maryland, College Park in the journal that is open-access PLOS ONE, December 1 2021.

Previous research has shown that staying at least two meters apart from others can limit the spread of COVID-19. Strategies based on technology–such as strategies that use WiFi and Bluetooth–may assist in identifying and stopping the lapses in social distancing. Robots are a feasible tool to address social distancing in crowds however, a lot of these strategies require the involvement of individuals or infrastructure already in place.

Sathyamoorthy and his colleagues, have created an innovative way to utilize an autonomous mobile robotics robot to accomplish this. The robot is able to detect breaches and navigate to them using its own Red Green Blue-;Depth (RGB-D) camera and 2-D LiDAR (Light Detection and Ranging) sensor, and also tap into an existing CCTV system in the event that it is there is. The robot will display a message on a wall to make it easier for people to leave once it has entered the breach.

The robot employs an unique method to separate those who have violated social distancing laws into groups and then prioritize them based on the degree to which they are stationary, moving, and then steer towards them. The system is based on a machine-learning technique known as Deep Reinforcement Learning and Frozone an algorithm developed by a group of the same researchers to help robots navigate crowds.

The researchers tested their method by having volunteers perform social-distancing breaches while sitting still or walking in a erratic manner. The robot was able to detect and fix the majority of breaches that occurred. CCTV improved its performance.

The robot also comes with thermal cameras that detect potential fevers. This helps in the process of tracing contact. It also includes measures to protect privacy and to de-identify.

Further research is required to verify and improve this method. For instance it is important to investigate how robots affect the behavior of people when they are present in crowds.

The authors add that “a large number of healthcare workers were required to risk their health to serve the public during the COVID-19 outbreak.” Our mission is to provide them with the tools to effectively and safely serve their communities.”

Journal reference:

Sathyamoorthy (A.J.), et. (2021). COVID surveillance robot: Monitoring social distancing restrictions in indoor settings. PLOS ONE.

Content Source:

Gemma Wilson

Gemma is a journalism graduate with keen interest in covering business news – specifically startups. She has as a keen eye for technologies and has predicted quite a few successful startups over the last couple of years.

Related Articles