With the advancements of the Unmanned Aerial Vehicles (UAV) technology for use in different environments, it can be easily substituted for traditional transportation in event of emergencies. In the medical domain, UAV can play a vital role in the fast and efficient delivery of first aid and medical supplies. In the current study, safe and smooth UAV navigation from the initial position to the medical emergency location was achieved with optimal path planning through a proposed algorithm. On the notification of patient about his health condition using GSM band, doctor drone was sent from the nearest hospital facility. To avoid traffic congestion the doctor drone provides medical assistance with minimum computational time and transportation cost. The vehicle routing was carried out through proposed algorithms i.e., capacitated Vehicle Routing Problem (CVRP), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO) and Genetic Algorithm (GA). The comparison between the algorithms was carried out at different vehicle capacities and numbers. The CVRP was found to outperform other algorithms with a runtime of 0.06 sec and cost of 419 at vehicle capacity 10, which is 50% less having the same number of the vehicles but increasing the capacities to 20. The results indicate that the effective path planning method could be applied to provide medical aid in real-time with efficacy.

随着无人驾驶飞机（UAV）技术在不同环境中使用的进步，在紧急情况下，它可以轻松替代传统运输。在医疗领域，无人机可以在快速有效地提供急救和医疗用品方面发挥至关重要的作用。在当前的研究中，通过提出的算法通过最佳路径规划，实现了从初始位置到医疗急救位置的安全，平稳的无人机导航。在使用GSM频段通知患者有关其健康状况的通知后，从最近的医院设施中发送了无人驾驶飞机医生。为避免交通拥堵，医生无人机以最少的计算时间和运输成本为您提供医疗帮助。车辆路线是通过提出的算法进行的，即 车辆容量限制问题（CVRP），粒子群优化（PSO），蚁群优化（ACO）和遗传算法（GA）。算法之间的比较是在不同的车辆容量和数量下进行的。发现在车辆容量为10时，CVRP的运行时间为0.06秒，成本为419，优于其他算法，如果车辆数量相同，但将容量增加到20，则成本降低了50％。结果表明，有效的路径规划该方法可用于实时提供医疗救治。