The Ride-Sharing Assignment Problem (AAAI 2018) is a fundamental problem in intelligent transportation systems, urban mobility, and algorithmic decision-making. Given a set of m vehicles with initial locations and n requests (n≤mk), each with a specified origin and destination, the goal is to assign at most k requests to each vehicle and compute corresponding routes that minimize the total travel distance. The algorithmic approach depends on whether n=mk or n

As Unmanned Aerial Vehicle (UAV) technology has developed, UAVs have gradually been used in a variety of fields such as rescue, mapping and aerial photography. At the same time, target detection and tracking algorithms have also been applied to UAVs. Considering the domain of UAV flight, the objective of this paper is to enhance the target detection algorithm utilizing YOLOv5 as its foundation. Initially, the Attentional Scale Sequence Fusion network is adopted. It is used to improve the model's feature learning and small target detection capabilities. Next, to enhance the model's spatial perception for small targets, the ordinary convolution in the feature fusion network is replaced by coordinate convolution. Ultimately, the SIoU loss function is employed with the objective of boosting the accuracy of the prediction box and accelerating the convergence speed of the model training. The enhanced target detection algorithm has led to an improvement in the mAP of 1.2%, an increase in accuracy of 1.7% and a rise in recall of 0.3%.