COVID-19 Pandemic Response Robot

摘要

Due to an arising COVID-19 positive confirmed case in Taiwan, the screening of body temperature, mask wearing and quarantined violation is enhanced. A mobile robot that conducts this task is demanded to reduce the human labor. However, conventional robots suffer from several limitations, perceptual aliasing (e.g., different places/objects can appear identical), occlusion (e.g., place/object appearance changes between visits), different viewpoints, the scale of objects, low mobility, less functionality, and some environmental limitations. As for the thermal imager, it displays the current heat spectrum colors, and needs manual monitoring. This paper proposes applying Simultaneous Localization and Mapping in an unknown environment and using deep learning for detection of temperature, mask wearing, and human face on the Raspberry Pi to overcome these problems. It also uses the A* algorithm to do path planning and obstacle avoidance via 3D Light Detection and Ranging to make the robot move more smoothly. Evaluating and implementing different Simultaneous Localization and Mapping algorithms and deep learning models, then selecting the most suitable method. Root Mean Square Error of three Simultaneous Localization and Mapping algorithms are compared. The predictions of deep learning models are evaluated via the metrics (model speed, accuracy, complexity, precision, recall, precision–recall curve, F1 score). In conclusion, Google Cartographer for building a map, Convolutional Neural Network for mask wearing detection, and only looking once for human face detection achieve the best result among all algorithms.