Unmanned Aerial Vehicles (UAVs) are pivotal in applications such as search and rescue and environmental monitoring, excelling in intelligent perception tasks. However, their limited battery capacity hinders long-duration and long-distance missions. Charging UAVs (CUAVs) offers a potential solution by recharging mission UAVs (MUAVs), but existing methods rely on impractical pre-planned routes, failing to enable organic cooperation and limiting mission efficiency. We introduce a novel multi-agent deep reinforcement learning model named \textbf{H}eterogeneous \textbf{G}raph \textbf{A}ttention \textbf{M}ulti-agent Deep Deterministic Policy Gradient (HGAM), designed to dynamically coordinate MUAVs and CUAVs. This approach maximizes data collection, geographical fairness, and energy efficiency by allowing UAVs to adapt their routes in real-time to current task demands and environmental conditions without pre-planning. Our model uses heterogeneous graph attention networks (GATs) to present heterogeneous agents and facilitate efficient information exchange. It operates within an actor-critic framework. Simulation results show that our model significantly improves cooperation among heterogeneous UAVs, outperforming existing methods in several metrics, including data collection rate and charging efficiency.

Autonomous drone racing has risen as a challenging robotic benchmark for testing the limits of learning, perception, planning, and control. Expert human pilots are able to agilely fly a drone through a race track by mapping the real-time feed from a single onboard camera directly to control commands. Recent works in autonomous drone racing attempting direct pixel-to-commands control policies (without explicit state estimation) have relied on either intermediate representations that simplify the observation space or performed extensive bootstrapping using Imitation Learning (IL). This paper introduces an approach that learns policies from scratch, allowing a quadrotor to autonomously navigate a race track by directly mapping raw onboard camera pixels to control commands, just as human pilots do. By leveraging model-based reinforcement learning~(RL) - specifically DreamerV3 - we train visuomotor policies capable of agile flight through a race track using only raw pixel observations. While model-free RL methods such as PPO struggle to learn under these conditions, DreamerV3 efficiently acquires complex visuomotor behaviors. Moreover, because our policies learn directly from pixel inputs, the perception-aware reward term employed in previous RL approaches to guide the training process is no longer needed. Our experiments demonstrate in both simulation and real-world flight how the proposed approach can be deployed on agile quadrotors. This approach advances the frontier of vision-based autonomous flight and shows that model-based RL is a promising direction for real-world robotics.

Age-of-information (AoI) and transmission power are crucial performance metrics in low energy wireless networks, where information freshness is of paramount importance. This study examines a power-limited internet of things (IoT) network supported by a flying unmanned aerial vehicle(UAV) that collects data. Our aim is to optimize the UAV flight trajectory and scheduling policy to minimize a varying AoI and transmission power combination. To tackle this variation, this paper proposes a meta-deep reinforcement learning (RL) approach that integrates deep Q-networks (DQNs) with model-agnostic meta-learning (MAML). DQNs determine optimal UAV decisions, while MAML enables scalability across varying objective functions. Numerical results indicate that the proposed algorithm converges faster and adapts to new objectives more effectively than traditional deep RL methods, achieving minimal AoI and transmission power overall.

The Ukrainian Air Force said Russia launched four missiles and 131 drones towards Ukraine overnight. The Air Force also said that 72 of the drones were destroyed while 59 disappeared without reaching their targets. Moscow's Ministry of Defence said its troops intercepted and destroyed 55 Ukrainian drones in six Russian regions overnight. Six drones were downed in Voronezh where, according to the region's Governor Aleksandr Gusev, falling debris started a blaze just six days after remnants of another intercepted drone triggered an earlier fire. Kyiv's military claimed responsibility for attacking an aviation manufacturing plant in Russia's Smolensk region where "combat aircraft[s] are being modernised and manufactured", as well as an attack on Voronezh which resulted in a fuel depot fire.

This paper addresses the challenges of selecting relay nodes and coordinating among them in UAV-assisted Internet-of-Vehicles (IoV). The selection of UAV relay nodes in IoV employs mechanisms executed either at centralized servers or decentralized nodes, which have two main limitations: 1) the traceability of the selection mechanism execution and 2) the coordination among the selected UAVs, which is currently offered in a centralized manner and is not coupled with the relay selection. Existing UAV coordination methods often rely on optimization methods, which are not adaptable to different environment complexities, or on centralized deep reinforcement learning, which lacks scalability in multi-UAV settings. Overall, there is a need for a comprehensive framework where relay selection and coordination are coupled and executed in a transparent and trusted manner. This work proposes a framework empowered by reinforcement learning and Blockchain for UAV-assisted IoV networks. It consists of three main components: a two-sided UAV relay selection mechanism for UAV-assisted IoV, a decentralized Multi-Agent Deep Reinforcement Learning (MDRL) model for autonomous UAV coordination, and a Blockchain implementation for transparency and traceability in the interactions between vehicles and UAVs. The relay selection considers the two-sided preferences of vehicles and UAVs based on the Quality-of-UAV (QoU) and the Quality-of-Vehicle (QoV). Upon selection of relay UAVs, the decentralized coordination between them is enabled through an MDRL model trained to control their mobility and maintain the network coverage and connectivity using Proximal Policy Optimization (PPO). The evaluation results demonstrate that the proposed selection and coordination mechanisms improve the stability of the selected relays and maximize the coverage and connectivity achieved by the UAVs.

This paper introduces an innovative drone carrier concept that is applied in maritime port security or offshore rescue. This system works with a heterogeneous system consisting of multiple Unmanned Aerial Vehicles (UAVs) and Unmanned Surface Vehicles (USVs) to perform inspection and intervention tasks in GNSS-denied or interrupted environments. The carrier, an electric catamaran measuring 4m by 7m, features a 4m by 6m deck supporting automated takeoff and landing for four DJI M300 drones, along with a 10kg-payload manipulator operable in up to level 3 sea conditions. Utilizing an offshore gimbal camera for navigation, the carrier can autonomously navigate, approach and dock with non-cooperative vessels, guided by an onboard camera, LiDAR, and Doppler Velocity Log (DVL) over a 3 km$^2$ area. UAVs equipped with onboard Ultra-Wideband (UWB) technology execute mapping, detection, and manipulation tasks using a versatile gripper designed for wet, saline conditions. Additionally, two UAVs can coordinate to transport large objects to the manipulator or interact directly with them. These procedures are fully automated and were successfully demonstrated at the Mohammed Bin Zayed International Robotic Competition (MBZIRC2024), where the drone carrier equipped with four UAVS and one manipulator, automatically accomplished the intervention tasks in sea-level-3 (wave height 1.25m) based on the rough target information.

An interactive map of UFO sightings has revealed shockingly new reports of drones in New Jersey and other states, suggesting this bizarre mystery is still unfolding. The map, created by the UAP (Unidentified Aerial Phenomena) tracking website Enigma Labs, shows hundreds of sightings logged as recently as January 7 in multiple Northeastern states. The mysterious drones along the East Coast appeared in November, with 22 people issuing reports to Enigma starting on the 20th. But that number dramatically increased to 347 by December 31. A drone ban was issued from December 18 to January 17, during which Enigma labs said the average number of reported sightings dropped by 43 percent.

The world needs whistleblowers, perhaps now more than ever. But whistleblowing has never been more dangerous. Jennifer Gibson has seen this problem develop up close. As a whistleblower lawyer based in the U.K., she has represented concerned insiders in the national security and tech worlds for more than a decade. She's represented family members of civilians killed by Pentagon drone strikes, and executives from top tech companies who've turned against their billionaire bosses.

Since the ceasefire has gone into force, the skies in Gaza have changed. There is an unusual stillness. We do not hear Israeli fighter jets or helicopters any more. The quadcopters are also gone, but the drones – the "zanana" – remain. The buzzing of Israeli drones is unmistakable.

Russia and Ukraine have continued to exchange barrages of air attacks, despite Donald Trump having said he would end the war within 24 hours of becoming US president. While Trump was inaugurated on Monday afternoon, neither Kyiv nor Moscow have shown signs of de-escalating the drone and missile strikes they have been launching against one another in recent months. Both launched barrages overnight on Tuesday. Russia said it downed 55 Ukrainian drones, more than half of which were intercepted over regions on the border. Kyiv said it struck an oil depot near the town of Liski in the Voronezh region, sparking a blaze at the facility for the second time in less than a week.