Delivery drones have been attracting attention as one of the promising technologies to deliver packages. Several research studies on routing problems specifically for drone delivery scenarios have extended Vehicle Routing Problems (VRPs). Most existing VRPs are based on Traveling Salesman Problems (TSPs) for minimizing the overall distance. On the other hand, VRPs for drone delivery have been aware of energy consumption due to the consideration of battery capacity. Despite hovering motions with loading packages accounting for a large portion of energy consumption since delivery drones need to hover with several packages, little research has been conducted on drone routing problems that aim at the minimization of overall flight times. In addition, flight time is strongly influenced by windy conditions such as headwinds and tailwinds. In this paper, we propose a VRP for drone delivery in which flight time is dependent on the weight of packages in a windy environment, called Flight Speed-aware Vehicle Routing Problem with Load and Wind (FSVRPLW). In this paper, flight speed changes depending on the load and wind. Specifically, a heavier package slows down flight speeds and a lighter package speeds up flight speeds. In addition, a headwind slows down flight speeds and a tailwind speed up flight speeds. We mathematically derived the problem and developed a dynamic programming algorithm to solve the problem. In the experiments, we investigate how much impact both the weight of packages and the wind have on the flight time. The experimental results indicate that taking loads and wind into account is very effective in reducing flight times. Moreover, the results of comparing the effects of load and wind indicate that flight time largely depends on the weight of packages.

In this work, we propose a method for estimating depth for an image of a monocular camera in order to avoid a collision for the autonomous flight of a drone. The highest flight speed of a drone is generally approximate 22.2 m/s, and long-distant depth information is crucial for autonomous flights since if the long-distance information is not available, the drone flying at high speeds is prone to collisions. However, long-range, measurable depth cameras are too heavy to be equipped on a drone. This work applies Pix2Pix, which is a kind of Conditional Generative Adversarial Nets (CGAN). Pix2Pix generates depth images from a monocular camera. Additionally, this work applies optical flow to enhance the accuracy of depth estimation. In this work, we propose a highly accurate depth estimation method that effectively embeds an optical flow map into a monocular image. The models are trained with taking advantage of AirSim, which is one of the flight simulators. AirSim can take both monocular and depth images over a hundred meter in the virtual environment, and our model generates a depth image that provides the long-distance information than images captured by a common depth camera. We evaluate accuracy and error of our proposed method using test images in AirSim. In addition, the proposed method is utilized for flight simulation to evaluate the effectiveness to collision avoidance. As a result, our proposed method is higher accuracy and lower error than a state of work. Moreover, our proposed method is lower collision than a state of work.

Delivery drones have been attracting attention as a means of solving recent logistics issues, and many companies are focusing on their practical applications. Many research studies on delivery drones have been active for several decades. Among them, extended routing problems for drones have been proposed based on the Traveling Salesman Problem (TSP), which is used, for example, in truck vehicle routing problems. In parcel delivery by drones, additional constraints such as battery capacity, payload, and weather conditions need to be considered. This study addresses the routing problem for delivery drones. Most existing studies assume that the drone’s flight speed is constant regardless of the load. On the other hand, some studies assume that the flight speed varies with the load. This routing problem is called the Flight Speed-Aware Traveling Salesman Problem (FSTSP). The complexity of the drone flight speed function in this problem makes it difficult to solve the routing problem using general-purpose mathematical optimization solvers. In this study, the routing problem is reduced to an integer programming problem by using linear and quadratic approximations of the flight speed function. This enables us to solve the problem using general-purpose mathematical optimization solvers. In experiments, we compared the existing and proposed methods in terms of solving time and total flight time. The experimental results show that the proposed method with multiple threads has a shorter solving time than the state-of-the-art method when the number of customers is 17 or more. In terms of total flight time, the proposed methods deteriorate by an average of 0.4% for integer quadratic programming and an average of 1.9% for integer cubic programming compared to state-of-the-art methods. These experimental results show that the quadratic and cubic approximations of the problem have almost no degradation of the solution.

Digital microfluidic biochips (DMFBs), which are used in various fields like DNA analysis, clinical diagnosis, and PCR testing, have made biochemical experiments more compact, efficient, and user-friendly than the previous methods. However, their reliability is often compromised by their inability to adapt to all kinds of errors. Errors in biochips can be categorized into two types: known errors, and unknown errors. Known errors are detectable before the start of the routing process using sensors or cameras. Unknown errors, in contrast, only become apparent during the routing process and remain undetected by sensors or cameras, which can unexpectedly stop the routing process and diminish the reliability of biochips. This paper introduces a deep reinforcement learning-based routing algorithm, designed to manage not only known errors but also unknown errors. Our experiments demonstrated that our algorithm outperformed the previous ones in terms of the success rate of the routing, in the scenarios including both known errors and unknown errors. Additionally, our algorithm contributed to detecting unknown errors during the routing process, identifying the most efficient routing path with a high probability.

Recent years, autonomous drones have attracted attention in many fields due to their convenience. Autonomous drones require precise depth information so as to avoid collision to fly fast and both of RGB image and LiDAR point cloud are often employed in applications based on Convolutional Neural Networks (CNNs) to estimate the distance to obstacles. Such applications are implemented onboard embedded systems. In order to precisely estimate the depth, such CNN models are in general so complex to extract many features that the computational complexity increases, requiring long inference time. In order to solve the issue, we employ optical flow to aid in-depth estimation. In addition, we propose a new attention structure that makes maximum use of optical flow without complicating the network. Furthermore, we achieve improved performance without modifying the depth estimator by adding a perceptual discriminator in training. The proposed model is evaluated through accuracy, error, and inference time on the KITTI dataset. In the experiments, we have demonstrated the proposed method achieves better performance by up to 34% accuracy, 55% error reduction and 66% faster inference time on Jetson nano compared to previous methods. The proposed method is also evaluated through a collision avoidance in simulated drone flight and achieves the lowest collision rate of all estimation methods. These experimental results show the potential of proposed method to be used in real-world autonomous drone flight applications.

Urine sediment analysis plays a vital role in the evaluation of kidney health. Traditional machine learning techniques approach the task of urine sediment particle detection as an image classification problem, wherein the particles are segmented based on features like edges or thresholds. However, the segmentation process for sediment particles in urine images is complex due to the inherent limitations of low contrast and weak edge characteristics. To mitigate the background noise on detection, that is, to focus more on the important part (i.e., cells), there have appeared several works that employ attention-based urinary sediment detector; however, their works did not consider the best location attention modules. This paper YOLOv7-based urinary sediment detection with attention modules. YOLOv7 is one of state-of-the-art models, and we additionally implement attention modules in the backbone of YOLOv7 so that they empower its network to enhance the feature extraction with mitigating the background noises. In experiments, we perform the proposed models on urinary sediment dataset and the results demonstrate that our proposed models outperform original YOLOv7 and a state-of-the-art urinary sediment detector in terms of recall score by 12.4% and 4.3% as well as mAP score by 7.4% and 1.6%. Our source is provided in the following link: https://github.com/Info-Sys-OU/Multi-class-Urinary-Sediment-Particles-Detection-based-on-YOLOv7-with-Attention-Modules.