Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations, providing a more practical solution for effective tracking in dynamic environments. However, accurate Drone Visual Active Tracking using reinforcement learning remains challenging due to the absence of a unified benchmark and the complexity of open-world environments with frequent interference. To address these issues, we pioneer a systematic solution. First, we propose DAT, the first open-world drone active air-to-ground tracking benchmark. It encompasses 24 city-scale scenes, featuring targets with human-like behaviors and high-fidelity dynamics simulation.

Drone-based multi-object tracking is essential yet highly challenging due to small targets, severe occlusions, and cluttered backgrounds. Existing RGB-based multiobject tracking algorithms heavily depend on spatial appearance cues such as color and texture, which often degrade in aerial views, compromising tracking reliability. Multispectral imagery, capturing pixel-level spectral reflectance, provides crucial spectral cues that significantly enhance object discriminability under degraded spatial conditions. However, the lack of dedicated multispectral UAV datasets has hindered progress in this domain. To bridge this gap, we introduce MMOT, the first challenging benchmark for drone-based multispectral multi-object tracking dataset. It features three key characteristics: (i) Large Scale -- 125 video sequences with over 488.8K annotations across eight object categories; (ii) Comprehensive Challenges -- covering diverse real-world challenges such as extreme small targets, high-density scenarios, severe occlusions, and complex platform motion; and (iii) Precise Oriented Annotations -- enabling accurate localization and reduced object ambiguity under aerial perspectives.

Latvian intelligence says Russia is preparing military provocations against Baltic states or Poland, including drones and missiles, to pressure NATO to stop supporting Ukraine.

Removing the limit on simultaneous drone use by one person is aimed at optimizing logistics and infrastructure inspections, and at making damage assessment and search operations more effective during disasters. The transport ministry has lifted the upper limit on the number of drones that can be operated by a single pilot at the same time, officials said. Previously, the number was set at five. Removing the limit is aimed at optimizing logistics and infrastructure inspections, and at making damage assessment and search operations more effective during disasters. In March 2025, the ministry set guidelines for using multiple drones at once.

Is the war entering a new phase? Gas sales in Russian-controlled Crimea have halted after Ukrainian drone strikes on the peninsula's supply route. Drivers are now looking for other modes of transport. Colombia's De La Espriella claims victory on preliminary results US and Iran meet for'tense' but'constructive' ceasefire talks What are the end goals of Iran-US negotiations?

Russian troop build-up threatens city seen as key to seizing Ukraine's Donbas Russian troops have infiltrated the strategic city of Kostyantynivka in eastern Ukraine and are now trying to surround it. The entire city is now effectively in a grey zone, no longer controlled by anyone, Ukrainian soldiers have told the BBC. They get into areas behind our backs and in urban conditions it's extremely difficult to push them out, says a Ukrainian drone pilot who operates in that area and prefers to remain anonymous. Kostyantynivka is a gateway to the rest of the Donbas region. If it falls, Russian forces would be able push towards Ukraine's last remaining strongholds in the east, the cities of Kramatorsk and Sloviansk, and move closer to seizing Donbas completely, one of the Kremlin's key objectives in this war.

Is the war entering a new phase? Russian forces have attacked the Ukrainian city of Zaporizhzhia with glide bombs, killing five people, Regional Governor Ivan Fedorov said. In a post on Telegram on Saturday, Fedorov said that Russian air strikes had injured 11 people, and the number was rising after the attack destroyed and damaged residential and non-residential buildings. In recent weeks, Russia and Ukraine have escalated attacks as talks to end the conflict remain at a standstill. On Saturday morning, an aerial attack killed one person and wounded nine others in the city of Kharkiv in eastern Ukraine.

Moscow oil refinery attack brings Russia's war with Ukraine closer to home There are moments when life in Moscow feels completely normal. In the south-east of the city an oil refinery had been hit during a Ukrainian drone attack - even from a distance the sight was surreal. Thick smoke billowing from the direction of the facility had turned the sky dark. Like a giant black shroud, it hung over the Moscow skyline. As extraordinary and eye-catching this was, so was the reaction of people near the refinery.

Unmanned Aerial Vehicles (UAVs) are evolving into language-interactive platforms, enabling more intuitive forms of human-drone interaction. While prior works have primarily focused on high-level planning and long-horizon navigation, we shift attention to language-guided fine-grained trajectory control, where UAVs execute short-range, reactive flight behaviors in response to language instructions. We formalize this problem as the Flying-on-a-Word (Flow) task and introduce UAV imitation learning as an effective approach. In this framework, UAVs learn fine-grained control policies by mimicking eUAxpert pilotVtrajectoriesFlopaired withwatomic Fly around the tree ahead Land on the left side of carlanguage instructions. To support this paradigm, we present UAV-Flow, the firstreal-world benchmark for language-conditioned, fine-grained UAV control.

By sharing information across multiple agents, collaborative perception helps autonomous vehicles mitigate occlusions and improve overall perception accuracy. While most previous work focus on vehicle-to-vehicle and vehicle-to-infrastructure collaboration, with limited attention to aerial perspectives provided by UAVs, which uniquely offer dynamic, top-down views to alleviate occlusions and monitor large-scale interactive environments. A major reason for this is the lack of highquality datasets for aerial-ground collaborative scenarios. To bridge this gap, we present AGC-Drive, the first large-scale real-world dataset for Aerial-Ground Cooperative 3D perception. The data collection platform consists of two vehicles, each equipped with five cameras and one LiDAR sensor, and one UAV carrying a forward-facing camera and a LiDAR sensor, enabling comprehensive multi-view and multi-agent perception.