The Autonomy of Unmanned Aerial Vehicles (UAVs) in indoor environments poses significant challenges due to the lack of reliable GPS signals in enclosed spaces such as warehouses, factories, and indoor facilities. Micro Aerial Vehicles (MAVs) are preferred for navigating in these complex, GPS-denied scenarios because of their agility, low power consumption, and limited computational capabilities. In this paper, we propose a Reinforcement Learning based Deep-Proximal Policy Optimization (D-PPO) algorithm to enhance realtime navigation through improving the computation efficiency. The end-to-end network is trained in 3D realistic meta-environments created using the Unreal Engine. With these trained meta-weights, the MAV system underwent extensive experimental trials in real-world indoor environments. The results indicate that the proposed method reduces computational latency by 91\% during training period without significant degradation in performance. The algorithm was tested on a DJI Tello drone, yielding similar results.

A.2024.0146 1 Rolling Horizon Coverage Control with Collaborative Autonomous Agents Savvas Papaioannou, Panayiotis Kolios, Theocharis Theocharides, Christos G. Panayiotou and Marios M. Polycarpou Abstract This work proposes a coverage controller that enables an aerial team of distributed autonomous agents to collaboratively generate non-myopic coverage plans over a rolling finite horizon, aiming to cover specific points on the surface area of a 3D object of interest. The collaborative coverage problem, formulated, as a distributed model predictive control problem, optimizes the agents' motion and camera control inputs, while considering inter-agent constraints aiming at reducing work redundancy. The proposed coverage controller integrates constraints based on light-path propagation techniques to predict the parts of the object's surface that are visible with regard to the agents' future anticipated states. This work also demonstrates how complex, non-linear visibility assessment constraints can be converted into logical expressions that are embedded as binary constraints into a mixed-integer optimization framework. The proposed approach has been demonstrated through simulations and practical applications for inspecting buildings with unmanned aerial vehicles (UA Vs). I NTRODUCTION The interest in swarm systems such as systems utilizing multiple autonomous unmanned aerial vehicles (UA Vs) has skyrocketed over the last few decades. Rapid advancements in robotics, automation and artificial intelligence coupled with the decreasing costs of electronic components have fuelled a remarkable surge in interest towards the technologies and applications of swarming systems. This work addresses the challenge of coverage planning and control using multiple collaborative intelligent autonomous agents, specifically autonomous UA Vs. Coverage planning [1] is crucial in several application domains including search and rescue operations and critical infrastructure inspections. It is one of the essential functionalities that can notably enhance the autonomy of existing swarming systems enabling them to execute fully automated missions in the aforementioned scenarios. In coverage planning our objective is to design trajectories that allow a team of autonomous mobile agents to comprehensively cover a designated area or points of interest. Concurrently we aim to optimize a specific mission goal such as minimizing the mission's duration and energy consumption of the agents. This work introduces a coverage control framework that optimizes both the kinematic and camera control inputs of multiple UA V agents simultaneously.

Considering the widespread integration of aerial robots in inspection, search and rescue, and monitoring tasks, there is a growing demand to design intuitive human-drone interfaces. These aim to streamline and enhance the user interaction and collaboration process during drone navigation, ultimately expediting mission success and accommodating users' inputs. In this paper, we present a novel human-drone mixed reality interface that aims to (a) increase human-drone spatial awareness by sharing relevant spatial information and representations between the human equipped with a Head Mounted Display (HMD) and the robot and (b) enable safer and intuitive human-drone interactive and collaborative navigation in unknown environments beyond the simple command and control or teleoperation paradigm. We validate our framework through extensive user studies and experiments in a simulated post-disaster scenario, comparing its performance against a traditional First-Person View (FPV) control systems. Furthermore, multiple tests on several users underscore the advantages of the proposed solution, which offers intuitive and natural interaction with the system. This demonstrates the solution's ability to assist humans during a drone navigation mission, ensuring its safe and effective execution.

A drone equipped with an antenna from a male moth can locate the source of a smell more accurately than any electrical sensors. Unfortunately, however, the only smell it can detect is the sex pheromone emitted by female moths. Electrical sensors for odours are commonly used to detect gas leaks, but these are relatively slow to react to smells and even slower to reset between measurements, says Daigo Terutsuki at Shinshu University, Japan. "It's very difficult to apply that to…

The U.S. military will deploy several long-range surveillance drones to Okinawa Prefecture, near Japan's far-flung southwestern islands area near Taiwan, as the allies seek to counter China's ramped-up drone presence in the same area. Defense Minister Gen Nakatani said Tuesday that the U.S. MQ-4C Triton drones will be sent to the U.S. air base in Kadena, on Okinawa's main island, in the coming weeks. "This deployment is expected to enhance the Japan-U.S. alliance's intelligence-gathering capabilities and, by extension, the alliance's deterrence and response capabilities," Nakatani told a news conference.

Kyiv, Ukraine – Thread-thin, glistening in the sun and kilometres long, optical fibres wind through the branches of trees on the frontlines of eastern Ukraine. The cords were – sometimes still are – attached to Russian drones, making them immune to radio-electronic jamming. The drones may have been shot down. Some are still operational, waylaid and replete with danger. "When somebody is passing by, they just fly up and attack," Oleh, a military officer deployed in eastern Ukraine, told Al Jazeera.

Russia's Defence Ministry said its air defence units "intercepted and destroyed" 11 Ukrainian drones over the country's Kursk and Belgorod regions, which border Ukraine, as well as the southern Rostov region overnight. Russia's Defence Ministry said Kyiv carried out seven attacks on Moscow's energy infrastructure facilities between April 5 and 6, despite a moratorium on energy strikes brokered by the United States. According to the ministry, the attacks targeted the Crimean region, which Russia annexed from Ukraine in 2014, as well as Russia's Bryansk, Rostov and Voronezh regions. The ministry also said that Kremlin forces launched an overnight strike using long-range precision weapons and drones against Ukraine's central artillery armament base and defence industry enterprises involved in drone production. According to the ministry, Moscow also gained control over the village of Basivka in Ukraine's Sumy region in a rare cross-border advance.

Visual-inertial odometry (VIO) is widely used for state estimation in autonomous micro aerial vehicles using onboard sensors. Current methods improve VIO by incorporating a model of the translational vehicle dynamics, yet their performance degrades when faced with low-accuracy vehicle models or continuous external disturbances, like wind. Additionally, incorporating rotational dynamics in these models is computationally intractable when they are deployed in online applications, e.g., in a closed-loop control system. We present HDVIO2.0, which models full 6-DoF, translational and rotational, vehicle dynamics and tightly incorporates them into a VIO with minimal impact on the runtime. HDVIO2.0 builds upon the previous work, HDVIO, and addresses these challenges through a hybrid dynamics model combining a point-mass vehicle model with a learning-based component, with access to control commands and IMU history, to capture complex aerodynamic effects. The key idea behind modeling the rotational dynamics is to represent them with continuous-time functions. HDVIO2.0 leverages the divergence between the actual motion and the predicted motion from the hybrid dynamics model to estimate external forces as well as the robot state. Our system surpasses the performance of state-of-the-art methods in experiments using public and new drone dynamics datasets, as well as real-world flights in winds up to 25 km/h. Unlike existing approaches, we also show that accurate vehicle dynamics predictions are achievable without precise knowledge of the full vehicle state.

One person was killed Sunday as Russian air strikes hit the Ukrainian capital, Kyiv, while the death toll from Friday's deadly attack on the central Ukrainian city of Kryvyi Rih continued to rise. The Kyiv victim was found close to the strike's epicenter of the attack in the city's Darnytskyi district, Mayor Vitali Klitschko said. A further three people were injured in the strike, which saw fires break out in several nonresidential areas, damaging cars and buildings. In a statement on social media, Ukrainian President Volodymyr Zelenskyy said the intensifying Russian attacks showed that there is still insufficient international pressure on Moscow. US WILL KNOW IN'MATTER OF WEEKS' IF RUSSIA IS SERIOUS ABOUT PEACE OR USING'DELAY TACTIC': RUBIO He said Russia has launched more than 1,460 guided aerial bombs, nearly 670 attack drones and more than 30 missiles at Ukraine in the past week alone.

At least 14 people, including six children, have been killed in a Russian missile attack on a residential area of the central Ukrainian city of Kryvyi Rih, according to President Volodymyr Zelenskyy, making it one of Moscow's deadliest strikes this year. Friday's attack on Zelenskyy's hometown, which comes as United States President Donald Trump is pushing for a ceasefire in the war, damaged residential blocks and caused fires, Dnipropetrovsk Governor Serhiy Lysak wrote on the Telegram messaging app. The dead and wounded could be seen lying on the pavement, one of them by a playground, in unverified videos circulating on Telegram as grey smoke rose into the sky. At least 50 people were wounded, the emergency services said, adding that the figure was growing. More than 30 people, including a three-month-old baby, were admitted to hospital, Lysak said.