The development of a real-world Unmanned Aircraft System (UAS) Traffic Management (UTM) system to ensure the safe integration of Unmanned Aerial Vehicles (UAVs) in low altitude airspace, has recently generated novel research challenges. A key problem is the development of Pre-Flight Conflict Detection and Resolution (CDR) methods that provide collision-free flight paths to all UAVs before their takeoff. Such problem can be represented as a Multi-Agent Path Finding (MAPF) problem. Currently, most MAPF methods assume that the UTM system is a centralized entity in charge of CDR. However, recent discussions on UTM suggest that such centralized control might not be practical or desirable. Therefore, we explore Pre-Flight CDR methods where independent UAS Service Providers (UASSPs) with their own interests, communicate with each other to resolve conflicts among their UAV operations-without centralized UTM directives. We propose a novel MAPF model that supports the decentralized resolution of conflicts, whereby different 'agents', here UASSPs, manage their UAV operations. We present two approaches: (1) a prioritization approach and (2) a simple yet practical pairwise negotiation approach where UASSPs agents determine an agreement to solve conflicts between their UAV operations. We evaluate the performance of our proposed approaches with simulation scenarios based on a consultancy study of predicted UAV traffic for delivery services in Sendai, Japan, 2030. We demonstrate that our negotiation approach improves the "fairness" between UASSPs, i.e. the distribution of costs between UASSPs in terms of total delays and rejected operations due to replanning is more balanced when compared to the prioritization approach.

The increasing demand for services performed by Unmanned Aerial Vehicles (UAVs) requires the simulation of Unmanned Aircraft System Traffic Management (UTM) systems. In particular, Pre-Flight Conflict Detection and Resolution (CDR) methods need to scale to future demand levels and generate conflict-free paths for a potentially large number of UAVs before actual takeoff. However, few studies have examined realistic scenarios and the requirements for the UTM system. In this paper, we focus on the Sendai 2030 model case, a realistic projection of UAV usage for deliveries in one area in Japan. This model case considers up to 21,000 requests for Unmanned Aircraft Systems (UAS) operations over a 13 hour service time, and thus poses a challenge for the Pre-Flight CDR methods. Therefore, we propose an airspace reservation method based on 4DT (3D plus time Trajectories) and map the Pre-Flight CDR problem to a Multi-Agent Path Finding (MAPF) problem. We study first-come first-served (FCFS) and ''batch'' processing of UAS operation requests, and compare the throughput of those methods. We analyze the air traffic topology of deliveries by UAVs, and discuss several metrics to better understand the complexity of air traffic in the Sendai model case. INDEX TERMS Unmanned aircraft system traffic management (UTM), pre-flight conflict detection and resolution (CDR), multi-agent path finding (MAPF), air traffic complexity metrics.

This article describes the artificial intelligence (AI) component of a drone for monitoring and patrolling tasks associated with disaster relief missions in specific restricted disaster scenarios, as specified by the Advanced Robotics Foundation in Japan. The AI component uses deep learning models for environment recognition and object detection. For environment recognition, we use semantic segmentation, or pixel‐wise labeling, based on RGB images. Object detection is key for detecting and locating people in need. Since people are relatively small objects from the drone perspective, we use both RGB and thermal images. To train our models, we created a novel multispectral and publicly available data set of people. We used a geo‐location method to locate people on the ground. The semantic segmentation models were extensively tested using different feature extractors. We created two dedicated data sets, which we have made publicly available. Compared with the baseline model, the best‐performing model could increase the mean intersection over union (IoU) by 1.3%. Furthermore, we compared two types of person detection models. The first one is an ensemble model that combines RGB and thermal information via “late fusion”; the second one is a 4‐channel model that combines these two types of information in an “early fusion” manner. The results suggest that the 4‐channel model had a 40.6% increase of average precision for stricter IoU values (0.75) compared with the ensemble model and a 5.8% increase in the average precision compared with the thermal model. All models were deployed and tested on the NVIDIA AGX Xavier platform. To the best of our knowledge, this study was the first to use both RGB and thermal data from the perspective of a drone for monitoring tasks.

No abstract

No abstract