The rapid growth of the drone industry, particularly in the use of small unmanned aerial systems (sUAS) and unmanned aerial vehicles (UAVs), requires the development of advanced training protocols for remote pilots. Remote pilots must develop a combination of technical and cognitive skills to manage the complexities of modern drone operations. This paper explores the integration of neurotechnology, specifically auricular vagus nerve stimulation (aVNS), as a method to enhance remote pilot training and performance. The scientific literature shows aVNS can safely improve cognitive functions such as attention, learning, and memory. It has also been shown useful to manage stress responses. For safe and efficient sUAS/UAV operation, it is essential for pilots to maintain high levels of vigilance and decision-making under pressure. By modulating sympathetic stress and cortical arousal, aVNS can prime cognitive faculties before training, help maintain focus during training and improve stress recovery post-training. Furthermore, aVNS has demonstrated the potential to enhance multitasking and cognitive control. This may help remote pilots during complex sUAS operations by potentially reducing the risk of impulsive decision-making or cognitive errors. This paper advocates for the inclusion of aVNS in remote pilot training programs by proposing that it can provide significant benefits in improving cognitive readiness, skill and knowledge acquisition, as well as operational safety and efficiency. Future research should focus on optimizing aVNS protocols for drone pilots while assessing long-term benefits to industrial safety and workforce readiness in real-world scenarios.

The problem of reliably detecting and geolocating objects of different classes in soft real-time is essential in many application areas, such as Search and Rescue performed using Unmanned Aerial Vehicles (UAVs). This research addresses the complementary problems of system contextual vision-based detector selection, allocation, and execution, in addition to the fusion of detection results from teams of UAVs for the purpose of accurately and reliably geolocating objects of interest in a timely manner. In an offline step, an application-independent evaluation of vision-based detectors from a system perspective is first performed. Based on this evaluation, the most appropriate algorithms for online object detection for each platform are selected automatically before a mission, taking into account a number of practical system considerations, such as the available communication links, video compression used, and the available computational resources. The detection results are fused using a method for building maps of salient locations which takes advantage of a novel sensor model for vision-based detections for both positive and negative observations. A number of simulated and real flight experiments are also presented, validating the proposed method.

A Ukrainian drone attack has set an oil depot in Russia's southern region of Rostov alight, the authorities said. On Wednesday, regional Governor Vasily Golubev confirmed the overnight strike, saying on the Telegram messaging app that firefighters were extinguishing the blaze at the depot in Rostov's Kamensky district, with no casualties reported. Russia's Ministry of Defence earlier said air defence units destroyed four drones over the region overnight, without mentioning the attack on the oil depot. Three tanks were burning at the oil depot after two drones fell in the area, according to the Baza Telegram channel, which is close to Russian security services. Ukraine's strike marked its latest attack on Russian oil and gas facilities in retaliation for attacks on its energy infrastructure.

Visual Odometry (VO) and SLAM are fundamental components for spatial perception in mobile robots. Despite enormous progress in the field, current VO/SLAM systems are limited by their sensors' capability. Event cameras are novel visual sensors that offer advantages to overcome the limitations of standard cameras, enabling robots to expand their operating range to challenging scenarios, such as high-speed motion and high dynamic range illumination. We propose a novel event-based stereo VO system by combining two ideas: a correspondence-free mapping module that estimates depth by maximizing ray density fusion and a tracking module that estimates camera poses by maximizing edge-map alignment. We evaluate the system comprehensively on five real-world datasets, spanning a variety of camera types (manufacturers and spatial resolutions) and scenarios (driving, flying drone, hand-held, egocentric, etc). The quantitative and qualitative results demonstrate that our method outperforms the state of the art in majority of the test sequences by a margin, e.g., trajectory error reduction of 45% on RPG dataset, 61% on DSEC dataset, and 21% on TUM-VIE dataset. To benefit the community and foster research on event-based perception systems, we release the source code and results: https://github.com/tub-rip/ES-PTAM

Russia has launched a second straight day of missile and drone attacks, targeting several Ukrainian regions and killing at least five people. Two people were killed when a hotel was "wiped out" by a missile in the central city of Kryvyi Rih, regional officials said on Tuesday. Three died in drone attacks on the southeastern city of Zaporizhzhia. Ukrainian President Volodymyr Zelenskyy on Tuesday said Kyiv would retaliate and asked allies to consider joint air defence operations and provide long-range weapons capabilities. Ukraine's air force said it downed five of 10 incoming Russian missiles and 60 of 81 drones in Tuesday's attacks.

Kyiv, Ukraine – Russia's aerial attack on Ukraine was colossal. Moving in waves from several directions and at different speeds and heights, 127 missiles and 109 drones attacked 15 of Ukraine's 24 regions. The attack is being seen in Ukraine as Russian President Vladimir Putin's revenge for Kyiv's daring incursion into the western Russian region of Kursk that began in early August and has resulted in the apparent takeover of more than 1,000sq kilometres (386sq miles). "He is a vindictive person, he got offended," General Lieutenant Ihor Romanenko, ex-deputy head of the General Staff of Ukraine's Armed Forces, told Al Jazeera. The attack began in predawn darkness on Monday as buzzing swarms of explosives-laden heavy drones took off from the Azov Sea town of Yeisk in southwestern Russia.

Russia has launched waves of missile and drone attacks targeting several Ukrainian regions killing at least four people, according to Ukraine's military, a day after it carried out a "massive" attack on Ukraine's power grid. Two people were killed when a hotel was "wiped out" in the central Ukrainian city of Kryvyi Rih, regional officials said on Tuesday. Two more people died in drone attacks on the city of Zaporizhzhia, east of Kryvyi Rih. The Kyiv region's air defence systems were deployed several times overnight to repel missiles and drones targeting Kyiv, the regional military administration said on the Telegram messaging app. Ukrainian air defences shot down about 15 drones and several missiles near the Ukrainian capital during Russia's overnight attack, Serhiy Popko, head of Kyiv's military administration, said on Tuesday morning.

Robotic Autonomous Vehicles (RAVs) rely on their sensors for perception, and follow strict mission specifications (e.g., altitude, speed, and geofence constraints) for safe and timely operations. Physical attacks can corrupt the RAVs' sensors, resulting in mission failures. Recovering RAVs from such attacks demands robust control techniques that maintain compliance with mission specifications even under attacks to ensure the RAV's safety and timely operations. We propose SpecGuard, a technique that complies with mission specifications and performs safe recovery of RAVs. There are two innovations in SpecGuard. First, it introduces an approach to incorporate mission specifications and learn a recovery control policy using Deep Reinforcement Learning (Deep-RL). We design a compliance-based reward structure that reflects the RAV's complex dynamics and enables SpecGuard to satisfy multiple mission specifications simultaneously. Second, SpecGuard incorporates state reconstruction, a technique that minimizes attack induced sensor perturbations. This reconstruction enables effective adversarial training, and optimizing the recovery control policy for robustness under attacks. We evaluate SpecGuard in both virtual and real RAVs, and find that it achieves 92% recovery success rate under attacks on different sensors, without any crashes or stalls. SpecGuard achieves 2X higher recovery success than prior work, and incurs about 15% performance overhead on real RAVs.

Aerospace embodied intelligence aims to empower unmanned aerial vehicles (UAVs) and other aerospace platforms to achieve autonomous perception, cognition, and action, as well as egocentric active interaction with humans and the environment. The aerospace embodied world model serves as an effective means to realize the autonomous intelligence of UAVs and represents a necessary pathway toward aerospace embodied intelligence. However, existing embodied world models primarily focus on ground-level intelligent agents in indoor scenarios, while research on UAV intelligent agents remains unexplored. To address this gap, we construct the first large-scale real-world image-text pre-training dataset, AerialAgent-Ego10k, featuring urban drones from a first-person perspective. We also create a virtual image-text-pose alignment dataset, CyberAgent Ego500k, to facilitate the pre-training of the aerospace embodied world model. For the first time, we clearly define 5 downstream tasks, i.e., aerospace embodied scene awareness, spatial reasoning, navigational exploration, task planning, and motion decision, and construct corresponding instruction datasets, i.e., SkyAgent-Scene3k, SkyAgent-Reason3k, SkyAgent-Nav3k and SkyAgent-Plan3k, and SkyAgent-Act3k, for fine-tuning the aerospace embodiment world model. Simultaneously, we develop SkyAgentEval, the downstream task evaluation metrics based on GPT-4, to comprehensively, flexibly, and objectively assess the results, revealing the potential and limitations of 2D/3D visual language models in UAV-agent tasks. Furthermore, we integrate over 10 2D/3D visual-language models, 2 pre-training datasets, 5 finetuning datasets, more than 10 evaluation metrics, and a simulator into the benchmark suite, i.e., AeroVerse, which will be released to the community to promote exploration and development of aerospace embodied intelligence.

In [11], an APF is applied both is often required for tasks such as inspection and reconnaissance to the VRB and the robots, where the potential acting on [1]. The goal of formation planning algorithms is to the VRB is calculated at a central node and the potentials compute movements of the robots such that a formation is acting on the robots are calculated locally on each robot. In maintained while they perform their respective tasks and avoid [12], convex optimisation is used to find the optimal similarity collisions with obstacles and each other. Formation planning transformation of a configuration that minimises the distance algorithms can be categorised as centralised or distributed. In travelled by the robots, with constraints on the velocities of the centralised methods, all information is gathered at a central robots and environmental constraints on the formation. In [13], location where the plans are computed, while in distributed [14], a method for navigating a formation toward a desired methods all robots participate in the computation of the plans state, by iteratively computing the optimal VRB within the and coordinate via communication, requiring inter-robot coordination largest convex polytope containing the current formation, is mechanisms [1]. Centralised methods can be simpler presented. In [15], the authors demonstrate that finding the to implement since they do not require inter-robot coordination optimal rotation, translation, and assignment of the robots mechanisms, but have the drawback of system dependency in a VRB can be solved separately. In [16], consensus is on a single computer representing a single point of failure.