此篇論文貢獻為整合機器人作業系統及深度學習，實現一個具有同步定位及地圖構建、自主導航、人體溫度檢測、口罩辨識及人臉辨識的機器人系統。近年來，人們的健康意識逐漸抬頭，防疫設備也不斷在進步。目前研究人員致力於研究預防傳染疾病及災害應變。然而，傳統的機器人受到一些限制，例如：感知混疊(不同的位置/對象可能看起來相同)、遮擋(偵測物之間的位置/對象外觀變化)、辨識的角度不同、辨識對象的尺寸、機動性低、功能少以及環境限制。至於熱像儀，除了顯示當下的熱光譜影像，還需要手動監控。因此，本文提出一種防疫型機器人，能夠在未知環境中自主移動，利用深度學習來檢測人體體溫、口罩配戴和人臉辨識來克服這些問題，以及透過感測器來進行路徑規劃及避障，使機器人運動更加順暢。

Nowadays, people pay more attention to their health. Currently, researchers contribute to doing epidemic prevention and disaster response. 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 view point, the scale of object, 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 that applying Simultaneous Localization and Mapping (SLAM) 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 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 SLAM algorithms and deep learning models, then selecting the most suitable method. Comparing Root Mean Square Error of three SLAM algorithms. 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 and You Only Look Once achieve the best result among all algorithms.

[1] Y. Abdelrasoul, A. B. S. H. Saman and P. Sebastian, "A quantitative study of tuning ROS gmapping parameters and their effect on performing indoor 2D SLAM," 2016 2nd IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), Ipoh, 2016, pp. 1-6.
[2] N. Yu and B. Zhang, "An Improved Hector SLAM Algorithm based on Information Fusion for Mobile Robot," 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), Nanjing, China, 2018, pp. 279-284.
[3] R. Yagfarov, M. Ivanou and I. Afanasyev, "Map Comparison of Lidar-based 2D SLAM Algorithms Using Precise Ground Truth," 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, 2018, pp. 1979-1983.
[4] K. Wang, Y. Dong, H. Bai, Y. Zhao and K. Hu, "Use fast R-CNN and cascade structure for face detection," 2016 Visual Communications and Image Processing (VCIP), Chengdu, 2016, pp. 1-4.
[5] Y. H. Yeu, M. I. Shapiai, Z. H. Ismail and H. Fauzi, "Investigation on Different Color Spaces on Faster RCNN for Night-Time Human Occupancy Modelling," 2019 IEEE 7th Conference on Systems, Process and Control (ICSPC), Melaka, Malaysia, 2019, pp. 118-121.
[6] K. Xu, Z. Yuan, J. Zhang, Y. Ji, X. He and H. Yang, "SF6 Gas Infrared Thermal Imaging Leakage Detection Based on Faster-RCNN," 2019 International Conference on Smart Grid and Electrical Automation (ICSGEA), Xiangtan, China, 2019, pp. 36-40.
[7] L. Lianqiao, C. Xiai, Z. Huili and W. Ling, "Recognition and Application of Infrared Thermal Image Among Power Facilities Based on YOLO," 2019 Chinese Control and Decision Conference (CCDC), Nanchang, China, 2019, pp. 5939-5943.
[8] M. -F. R. Lee and T. -W. Chien, "Intelligent Robot for Worker Safety Surveillance: Deep Learning Perception and Visual Navigation," 2020 International Conference on Advanced Robotics and Intelligent Systems (ARIS), Taipei, Taiwan, 2020, pp. 1-6.
[9] K. Krinkin, A. Filatov, A. y. Filatov, A. Huletski and D. Kartashov, "Evaluation of Modern Laser Based Indoor SLAM Algorithms," 2018 22nd Conference of Open Innovations Association (FRUCT), Jyvaskyla, 2018, pp. 101-106.
[10] L. Chen, A. Yang, H. Hu and W. Naeem, "RBPF-MSIS: Toward Rao-Blackwellized Particle Filter SLAM for Autonomous Underwater Vehicle with Slow Mechanical Scanning Imaging Sonar," in IEEE Systems Journal, vol. 14, no. 3, pp. 3301-3312.
[11] S. -M. Nasiri, R. Hosseini and H. Moradi, "Novel Parameterization for Gauss–Newton Methods in 3-D Pose Graph Optimization," in IEEE Transactions on Robotics.
[12] Z. Xuexi, L. Guokun, F. Genping, X. Dongliang and L. Shiliu, "SLAM Algorithm Analysis of Mobile Robot Based on Lidar," 2019 Chinese Control Conference (CCC), Guangzhou, China, 2019, pp. 4739-4745.
[13] W. Ye, X. Fan and J. Tang, "Real time UGV positioning based on Reference beacons aided LiDAR scan matching," 2018 Ubiquitous Positioning, Indoor Navigation and Location-Based Services (UPINLBS), Wuhan, 2018, pp. 1-5.
[14] J. Zhu and L. Xu, "Design and Implementation of ROS-Based Autonomous Mobile Robot Positioning and Navigation System," 2019 18th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES), Wuhan, China, 2019, pp. 214-217.
[15] S. Thrun, D. Fox, W. Burgard, and F. Dellaert, "Robust Monte Carlo localization for mobile robots," Artificial Intelligence, vol. 128, no. 1, pp. 99-141, 2001.
[16] S. A. Gunawan, G. N. P. Pratama, A. I. Cahyadi, B. Winduratna, Y. C. H. Yuwono and O. Wahyunggoro, "Smoothed A-star Algorithm for Nonholonomic Mobile Robot Path Planning," 2019 International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, Indonesia, 2019, pp. 654-658.
[17] S. Xu and W. Chou, "An Improved Indoor Localization Method for Mobile Robot Based on WiFi Fingerprint and AMCL," 2017 10th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, 2017, pp. 324-329.
[18] D. Talwar and S. Jung, "Particle Filter-based Localization of a Mobile Robot by Using a Single Lidar Sensor under SLAM in ROS Environment," 2019 19th International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea (South), 2019, pp. 1112-1115.
[19] I. Wasisto, N. Istiqomah, I. K. N. Trisnawan and A. N. Jati, "Implementation of Mobile Sensor Navigation System Based on Adaptive Monte Carlo Localization," 2019 International Conference on Computer, Control, Informatics and its Applications (IC3INA), Tangerang, Indonesia, 2019, pp. 187-192.
[20] S. Jing, C. Hu, C. Wang, G. Zhou and J. Yu, "Vehicle Face Detection Based on Cascaded Convolutional Neural Networks," 2019 Chinese Automation Congress (CAC), Hangzhou, China, 2019, pp. 5149-5152.
[21] Y. Li, J. Zhao, S. Zhang and W. Tan, "Aircraft Detection in Remote Sensing Images Based on Deep Convolutional Neural Network," 2018 IEEE 3rd International Conference on Cloud Computing and Internet of Things (CCIOT), Dalian, China, 2018, pp. 135-138.
[22] J. Shi, Y. Zhou and W. X. Q. Zhang, "Target Detection Based on Improved Mask Rcnn in Service Robot," 2019 Chinese Control Conference (CCC), Guangzhou, China, 2019, pp. 8519-8524.
[23] S. Gu, X. Chen, W. Zeng and X. Wang, "A Deep Learning Tennis Ball Collection Robot and the Implementation on NVIDIA Jetson TX1 Board," 2018 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Auckland, 2018, pp. 170-175.
[24] D. Xiao, F. Shan, Z. Li, B. T. Le, X. Liu and X. Li, "A Target Detection Model Based on Improved Tiny-Yolov3 Under the Environment of Mining Truck," in IEEE Access, vol. 7, pp. 123757-123764, 2019.
[25] J. Won, D. Lee, K. Lee and C. Lin, "An Improved YOLOv3-based Neural Network for De-identification Technology," 2019 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), JeJu, Korea (South), 2019, pp. 1-2.