Robotics is one of the most emerging technologies today, and are used in a variety of applications, ranging from complex rocket technology to monitoring of crops in agriculture. Robots can be exceptionally useful in a smart hospital environment provided that they are equipped with improved vision capabilities for detection and avoidance of obstacles present in their path, thus allowing robots to perform their tasks without any disturbance. In the particular case of Autonomous Nursing Robots, major essential issues are effective robot path planning for the delivery of medicines to patients, measuring the patient body parameters through sensors, interacting with and informing the patient, by means of voice-based modules, about the doctors visiting schedule, his/her body parameter details, etc. This paper presents an approach of a complete Autonomous Nursing Robot which supports all the aforementioned tasks. In this paper, we present a new Autonomous Nursing Robot system capable of operating in a smart hospital environment area. The objective of the system is to identify the patient room, perform robot path planning for the delivery of medicines to a patient, and measure the patient body parameters, through a wireless BLE (Bluetooth Low Energy) beacon receiver and the BLE beacon transmitter at the respective patient rooms. Assuming that a wireless beacon is kept at the patient room, the robot follows the beacon’s signal, identifies the respective room and delivers the needed medicine to the patient. A new fuzzy controller system which consists of three ultrasonic sensors and one camera is developed to detect the optimal robot path and to avoid the robot collision with stable and moving obstacles. The fuzzy controller effectively detects obstacles in the robot’s vicinity and makes proper decisions for avoiding them. The navigation of the robot is implemented on a BLE tag module by using the AOA (Angle of Arrival) method. The robot uses sensors to measure the patient body parameters and updates these data to the hospital patient database system in a private cloud mode. It also makes uses of a Google assistant to interact with the patients. The robotic system was implemented on the Raspberry Pi using Matlab 2018b. The system performance was evaluated on a PC with an Intel Core i5 processor, while the solar power was used to power the system. Several sensors, namely HC-SR04 ultrasonic sensor, Logitech HD 720p image sensor, a temperature sensor and a heart rate sensor are used together with a camera to generate datasets for testing the proposed system. In particular, the system was tested on operations taking place in the context of a private hospital in Tirunelveli, Tamilnadu, India. A detailed comparison is performed, through some performance metrics, such as Correlation, Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), against the related works of Deepu et al., Huh and Seo, Chinmayi et al., Alli et al., Xu, Ran et al., and Lee et al. The experimental system validation showed that the fuzzy controller achieves very high accuracy in obstacle detection and avoidance, with a very low computational time for taking directional decisions. Moreover, the experimental results demonstrated that the robotic system achieves superior accuracy in detecting/avoiding obstacles compared to other systems of similar purposes presented in the related works.

机器人技术是当今最新兴的技术之一，并被用于各种应用，从复杂的火箭技术到农业作物监测。机器人在智能医院环境中非常有用，前提是它们配备了改进的视觉能力，可以检测和避开路径中存在的障碍物，从而使机器人能够在不受任何干扰的情况下执行任务。在自主护理机器人的特殊情况下，主要的基本问题是有效的机器人路径规划，用于向患者输送药物，通过传感器测量患者身体参数，通过基于语音的模块与患者交互并通知患者医生就诊时间表，他/她的身体参数详细信息等。本文提出了一种支持上述所有任务的完整自主护理机器人的方法。在本文中，我们提出了一种能够在智能医院环境区域中运行的新型自主护理机器人系统。该系统的目标是通过无线 BLE（低功耗蓝牙）信标接收器和位于各自的病房。假设病房里有一个无线信标，机器人会跟随信标的信号，识别相应的房间并将所需的药物输送给患者。开发了一种由三个超声波传感器和一个摄像头组成的新型模糊控制器系统，用于检测机器人的最佳路径，避免机器人与稳定和移动的障碍物发生碰撞。模糊控制器有效地检测机器人附近的障碍物并做出适当的决策以避开它们。机器人的导航是通过使用 AOA（到达角）方法在 BLE 标签模块上实现的。机器人使用传感器测量患者身体参数，并以私有云模式将这些数据更新到医院患者数据库系统。它还利用谷歌助手与患者互动。该机器人系统是使用 Matlab 2018b 在 Raspberry Pi 上实现的。系统性能在配备 Intel Core i5 处理器的 PC 上进行评估，而太阳能则用于为系统供电。多个传感器，即 HC-SR04 超声波传感器、Logitech HD 720p 图像传感器、温度传感器和心率传感器与摄像头一起使用，以生成用于测试所提出系统的数据集。特别是，该系统在印度泰米尔纳德邦 Tirunelveli 的一家私立医院的运营中进行了测试。通过一些性能指标，例如相关性、均方根误差 (RMSE) 和平均绝对百分比误差 (MAPE)，与 Deepu 等人、Huh 和 Seo、Chinmayi 等人的相关工作进行了详细的比较。 、Alli 等人、Xu、Ran 等人和 Lee 等人。实验系统验证表明，模糊控制器在障碍物检测和避让方面实现了非常高的精度，并且做出方向决策的计算时间非常短。而且，