Low-cost indoor mobile robots have gained popularity with the increasing adoption of automation in homes and commercial spaces. However, existing lidar and camera-based solutions have limitations such as poor performance in visually obscured environments, high computational overhead for data processing, and high costs for lidars. In contrast, mmWave radar sensors offer a cost-effective and lightweight alternative, providing accurate ranging regardless of visibility. However, existing radar-based localization suffers from sparse point cloud generation, noise, and false detections. Thus, in this work, we introduce RaGNNarok, a real-time, lightweight, and generalizable graph neural network (GNN)-based framework to enhance radar point clouds, even in complex and dynamic environments. With an inference time of just 7.3 ms on the low-cost Raspberry Pi 5, RaGNNarok runs efficiently even on such resource-constrained devices, requiring no additional computational resources. We evaluate its performance across key tasks, including localization, SLAM, and autonomous navigation, in three different environments. Our results demonstrate strong reliability and generalizability, making RaGNNarok a robust solution for low-cost indoor mobile robots.

-- Recent advances in multi - agent systems manipulation have demonstrated a rising demand for the implementation of multi - UAV systems in urban areas, which are always subjected to the presence of static and dynamic obstacles. Inspired by the collective behavior of tilapia fish and pigeons, the focus of the presented research is on the introduction of a nature - inspired collision - free formation control for a multi - UAV system, considering the obstacle avoidance maneuvers. The developed framework in this study utilizes a semi - distributed control approach, in which, based on a probabilistic Lloyd's algorithm, a centralized guidance algorithm works for optimal positioning of the UAVs, while a distributed control approach has been used for the intervehicle collision and obstacle avoidance. Further, the presented framework has been extended to the 3D space with a novel definition of 3D maneuvers. Collision Avoidance, Centroidal Voronoi Tessellation, Distributed Control, Formation Control, Multi - Agent System, Obstacle Avoidance . From an engineering perspective, swarm intelligence shows how decentralized systems, composed of numerous simple agents, can achieve complex collective behaviors.

A Ukrainian drone attack at an industrial plant in central Russia has killed three people and injured 35 others, a Russian regional governor has said. Alexander Brechalov, head of the Udmurt Republic, said in a post on Telegram on Tuesday that the attack took place at a factory in Izhevsk city. Ten of the wounded were in a serious condition, he noted. There was no immediate official comment from Kyiv. But a Ukrainian security official confirmed the attack, telling the news agency Reuters that the Kupol plant had been hit, with a fire breaking out as a result.

This is second Ukrainian drone attack on the Kupol factory since November - although that strike had not resulted in any casualties. For its part, Moscow continues to carry out attacks in Ukraine. At the weekend Russia launched a record 537 drones and missiles on various locations across the country, including Kyiv and the western city of Lviv. On Monday Ukraine's Volodymyr Zelensky granted the Hero of Ukraine award posthumously to an F-16 pilot, Lieutenant Colonel Maksym Ustymenko, who was killed while trying to repel the aerial attack. On the battlefield, while Russia's advance on the Sumy region seems to have stalled, Moscow appears to be targeting the eastern Dnipropetrovsk region.

Fox News contributor Brett Velicovich demands U.S. defenses'adapt' to modern warfare after Ukraine's drone strikes on'The Story.' As sixth-generation fighter programs ramp up, military insiders are divided over whether future warplanes need pilots at all. The Pentagon is pouring billions into next-generation aircraft, pushing the boundaries of stealth and speed. But as America eyes a future of air dominance, one question looms large: Should Americans still be risking their lives in the cockpit? Autonomous drones backed by AI are progressing faster than many expected, and that has some defense leaders rethinking the role of the pilot.

Autonomous UAV operation necessitates reliable mathematical reasoning for tasks such as trajectory planning and power management. While traditional flight control relies on hardcoded equations, recent Large Language Models (LLMs) offer potential for more flexible problem-solving but struggle with reliably selecting and applying correct mathematical formulations and executing precise multi-step arithmetic. We propose RAG-UAV, a retrieval-augmented generation framework designed to improve the mathematical reasoning of several LLMs (including GPT o1/Turbo, Llama-3.2/3.3, Mistral, and DeepSeek R1) in UAV-specific contexts by providing access to relevant domain literature. To conduct an initial assessment, we introduce the UAV-Math-Bench, a 20-question problem set of UAV-centric mathematical problems across four difficulty levels. Our experiments demonstrate that incorporating retrieval substantially increases exact answer accuracy (achieving up to 75% with o1), reduces instances of incorrect formulation selection (from 25% without RAG to 5\% with RAG), and decreases numerical errors, reducing Mean Squared Error (MSE) by orders of magnitude for the best-performing models. This pilot study indicates that RAG can enable general-purpose LLMs to function as more reliable tools for engineering analysis, although direct real-time flight control requires further investigation and validation on a larger scale. All benchmark data, questions, and answers are publicly available.

Russia launched its biggest aerial attack on Ukraine since the beginning of its full-scale invasion overnight on Sunday, firing a total of 537 aerial weapons, including 477 drones and decoys and 60 missiles, according to the Ukrainian air force. Ukrainian forces intercepted 475 of the weapons, but the military said F-16 pilot Lieutenant Colonel Maksym Ustimenko was killed "while repelling" the "massive enemy air attack". At least four others were also killed in the air raids, in Kherson, Kharkiv, Dnipropetrovsk and Kostiantynivka regions, the Associated Press news agency reported, citing local officials. The aerial attacks were also far-reaching, targeting regions as far away as Lviv, in the far west, where a drone attack caused a large fire at an industrial facility in the city of Drohobych, and cut electricity to parts of the area. Poland said it scrambled aircraft, together with other NATO countries, to ensure the safety of Polish airspace during the attack.

Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physical attacks, such as GPS spoofing, that can corrupt state estimates and lead to unsafe behavior. While reinforcement learning (RL) offers adaptive control capabilities, existing safe RL methods are ineffective against such attacks. We present ARMOR (Adaptive Robust Manipulation-Optimized State Representations), an attack-resilient, model-free RL controller that enables robust UAV operation under adversarial sensor manipulation. Instead of relying on raw sensor observations, ARMOR learns a robust latent representation of the UAV's physical state via a two-stage training framework. In the first stage, a teacher encoder, trained with privileged attack information, generates attack-aware latent states for RL policy training. In the second stage, a student encoder is trained via supervised learning to approximate the teacher's latent states using only historical sensor data, enabling real-world deployment without privileged information. Our experiments show that ARMOR outperforms conventional methods, ensuring UAV safety. Additionally, ARMOR improves generalization to unseen attacks and reduces training cost by eliminating the need for iterative adversarial training.

Ukraine has lost an F-16 aircraft and its pilot while repelling a Russian missile and drone strike, according to the war-torn country's air force. After shooting down seven air targets, the plane was damaged and lost altitude overnight, the Ukrainian military said in a statement published on Telegram on Sunday. "This night, while repelling a massive enemy air attack, a pilot of the 1st class, Lieutenant Colonel Maksym Ustimenko, born in 1993, died on an F-16 aircraft," it said. In a separate statement, the air force said Russia launched 537 projectiles against Ukraine, including Shahed drones, cruise and ballistic missiles. Ukraine claimed to have intercepted 475 of them.

A Russian drone attack killed a teacher and her husband in Ukraine's Odesa, and wounded 14 others, according to Ukrainian officials. Three of the victims, including a child, were in critical condition. At least two others were killed in another Russian attack on the villages of Kostiantynivka and Ivanopillia in the eastern region of Donetsk on Friday, according to Governor Vadym Filashkin. Explosions were heard in the Ukrainian capital, Kyiv, on Saturday night, with Mayor Vitali Klitschko warning residents to take shelter from Russian drones "heading for the city", according to the official Ukrinform news agency. Russia's Ministry of Defence said Russian forces have taken control of the settlement of Chervona Zirka in Donetsk.