Unmanned Aerial Vehicles (UAVs) are utilized for a wide range of tasks, such as search, traffic monitoring, package delivery, military combat engagements and rescue operations. In each of these situations, the UAV is used to independently navigate the environment without human involvement, perform out particular tasks while avoiding obstacles, and collect data. To avoid the traffic for delivery service, some of them using the Unmanned Aerial Vehicle (UAV) to deliver the products. In collaborative control systems for unmanned aerial vehicles (UAVs), path planning is an important study field. UAV path planning is the process of looking for a route which will enable a UAV to follow a better flight path from its beginning point and eventually return at its destination point within the context of a particular mission. This flight path must fit the UAV's limitations while avoiding obstacles and aggressive threats. Thus, effective path planning is necessary to achieve traffic free delivery of services. Planning a practical three-dimensional (3-D) flight plan for unmanned aerial vehicles (UAVs) is a significant problem for following management and decision making. Hence in this work, Multi-Doped Pattern Learning (MDPL) Based Real Time 3D Path Planning of Unmanned Aerial Vehicles Using Integrated Probabilistic Pattern Modelling (IPPM) is presented. This approach will optimally find the correlation between the vertices from different sensor data and map with the pattern modelling to form 3D visual effect which helps to drive the UAV and prevent from accident by obstacles.