Abstract
The role of mobile robots for cleaning and sanitation purposes is increasing worldwide. Disinfection and hygiene are two integral parts of any safe indoor environment, and these factors become more critical in COVID-19-like pandemic situations. Door handles are highly sensitive contact points that are prone to be contamination. Automation of the door-handle cleaning task is not only important for ensuring safety, but also to improve efficiency. This work proposes an AI-enabled framework for automating cleaning tasks through a Human Support Robot (HSR). The overall cleaning process involves mobile base motion, door-handle detection, and control of the HSR manipulator for the completion of the cleaning tasks. The detection part exploits a deep-learning technique to classify the image space, and provides a set of coordinates for the robot. The cooperative control between the spraying and wiping is developed in the Robotic Operating System. The control module uses the information obtained from the detection module to generate a task/operational space for the robot, along with evaluating the desired position to actuate the manipulators. The complete strategy is validated through numerical simulations, and experiments on a Toyota HSR platform.
Highlights
Cleaning and disinfecting are very important steps in preventing the acquisition and spread of infectious diseases inside closed environments such as apartments, community centers, shopping malls, hospitals, etc
The cleaning of sensitive contact points such as door handles is highly challenging for service robots
This section describes the experimental results of door detection and the cleaning mechanism
Summary
Cleaning and disinfecting are very important steps in preventing the acquisition and spread of infectious diseases inside closed environments such as apartments, community centers, shopping malls, hospitals, etc. The cleaning of sensitive contact points such as door handles is highly challenging for service robots To carry out this task, the service robot needs an optimal vision system to identify the target object and the surrounding environment, and generate a trajectory planning scheme corresponding to arm-manipulation function to safely perform the proper cleaning tasks. Elen et al used computer vision and machine-learning technique to identify the door handle and its types where the author used a 2D sliding-window object-detection algorithm and k-means clustering technique for detecting and localizing a door. The author used a 7 ×7 darknet deep-learning model to recognize the door and k-means color clustering for segmentation of the handle point [29] Another important aspect of the indoor cleaning environment is motion-planning and arm manipulation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
