The need for civilian use of Unmanned Aerial Vehicles (UAVs) has drastically increased in recent years. Their potential applications for civilian use include door-to-door package delivery, law enforcement, first aid, and emergency services in urban areas, which put the UAVs into obstacle collision risk. Therefore, UAVs are required to be equipped with sensors so as to acquire Artificial Intelligence (AI) to avoid potential risks during mission execution. The AI comes with intensive training of an on-board machine that is responsible to autonomously navigate the UAV. The training enables the UAV to develop humanoid perception of the environment it is to be navigating in. During the mission, this perception detects and localizes objects in the environment. It is based on this AI that this work proposes a real-time three-dimensional (3D) path planner that maneuvers the UAV towards destination through obstacle-free path. The proposed path planner has a heuristic sense of ☆A☆ algorithm, but requires no frontier nodes to be stored in a memory unlike ☆A☆. The planner relies on relative locations of detected objects (obstacles) and determines collision-free paths. This path planner is light-weight and hence a fast guidance method for real-time purposes. Its performance efficiency is proved through rigorous Software-In-The-Loop (SITL) simulations in constrained-environment and preliminary real flight tests.
Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.