One of the most critical applications undertaken by coalitions of Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is reaching predefined targets by following the most time-efficient routes while avoiding collisions. Unfortunately, UAVs are hampered by limited battery life, and UGVs face challenges in reachability due to obstacles and elevation variations. Existing literature primarily focuses on one-to-one coalitions, which constrains the efficiency of reaching targets. In this work, we introduce a novel approach for a UAV-UGV coalition with a variable number of vehicles, employing a modified mean-shift clustering algorithm to segment targets into multiple zones. Each vehicle utilizes Multi-agent Deep Deterministic Policy Gradient (MADDPG) and Multi-agent Proximal Policy Optimization (MAPPO), two advanced reinforcement learning algorithms, to form an effective coalition for navigating obstructed environments without collisions. This approach of assigning targets to various circular zones, based on density and range, significantly reduces the time required to reach these targets. Moreover, introducing variability in the number of UAVs and UGVs in a coalition enhances task efficiency by enabling simultaneous multi-target engagement. The results of our experimental evaluation demonstrate that our proposed method substantially surpasses current state-of-the-art techniques, nearly doubling efficiency in terms of target navigation time and task completion rate.

Drones as advanced cyber-physical systems are undergoing a transformative shift with the advent of vision-based learning, a field that is rapidly gaining prominence due to its profound impact on drone autonomy and functionality. Different from existing task-specific surveys, this review offers a comprehensive overview of vision-based learning in drones, emphasizing its pivotal role in enhancing their operational capabilities under various scenarios. We start by elucidating the fundamental principles of vision-based learning, highlighting how it significantly improves drones' visual perception and decision-making processes. We then categorize vision-based control methods into indirect, semi-direct, and end-to-end approaches from the perception-control perspective. We further explore various applications of vision-based drones with learning capabilities, ranging from single-agent systems to more complex multi-agent and heterogeneous system scenarios, and underscore the challenges and innovations characterizing each area. Finally, we explore open questions and potential solutions, paving the way for ongoing research and development in this dynamic and rapidly evolving field. With growing large language models (LLMs) and embodied intelligence, vision-based learning for drones provides a promising but challenging road towards artificial general intelligence (AGI) in 3D physical world.

Abstract-- Global localisation from visual data is a challenging problem applicable to many robotics domains. Prior works have shown that neural networks can be trained to map images of an environment to absolute camera pose within that environment, learning an implicit neural mapping in the process. In this work we evaluate the applicability of such an approach to real-world robotics scenarios, demonstrating that by constraining the problem to 2-dimensions and significantly increasing the quantity of training data, a compact model capable of real-time inference on embedded platforms can be used to achieve localisation accuracy of several centimetres. We deploy our trained model onboard a UGV platform, demonstrating its effectiveness in a waypoint navigation task, wherein it is able to localise with a mean accuracy of 9cm at a rate of 6fps running on the UGV's onboard CPU, 35fps on an embedded GPU, or 220fps on a desktop GPU. Solutions that involve the placement of fixed retrieved images to refine the final estimate [14] [15] [16]; markers or beacons, such as ultra-wideband positioning [1], ultrasonic tracking beacons [2] or visual markers [3] can 5. 2D - 2D Implicit Map Localisation, that we refer to in this facilitate accuracy ranging from centimetres to metres, and work as neural mapping, estimates pose via a neural require specialist hardware be placed within the environment network that has learned an implicit representation of a and in some cases on agents themselves.

Russia says it has targeted Ukrainian military sites in the capital Kyiv and Kharkiv in a new wave of drone and missile attacks in days, in retaliation for a deadly attack a day earlier on the city of Belgorod. The Russian defence ministry said on Sunday it had struck "decision-making centres and military installations" in the northeastern city of Kharkhiv, after Kyiv said that residential buildings, a hotel and cafes had been hit. In the first wave of overnight attacks, at least six missiles hit Kharkiv, Ukraine's National Police said on Sunday, injuring at least 22 people and hitting 12 apartment buildings, 13 residential houses and a kindergarten. Most drones were aimed at Ukraine's first line of defence as well as at civilian, military and infrastructure in the Kharkiv, Kherson, Mykolaiv and Zaporizhia regions, the Ukrainian Air Force said, adding that it destroyed 21 out of 49 attack drones. Earlier, Ukrainian officials said that among those injured in Kharkiv were two boys aged 14 and 16 and a security adviser for a team of German journalists.

North Korea has said it will launch three more military spy satellites, build military drones and boost its nuclear arsenal in 2024, continuing a military modernisation programme that saw a record number of weapons tests this year. Pyongyang put a spy satellite into orbit in November at its third attempt and this month, again launched its most powerful intercontinental ballistic missile (ICBM), which is seen as having the range to deliver a nuclear warhead to anywhere in the United States. "The task of launching three additional reconnaissance satellites in 2024 was declared" as one of the key policy decisions for 2024 at the end of a five-day party meeting chaired by leader Kim Jong Un, the official Korean Central News Agency (KCNA) reported. Kim wrapped up the meeting on Saturday, lashing out at the US, which he blamed for making war inevitable. "Because of reckless moves by the enemies to invade us, it is a fait accompli that a war can break out at any time on the Korean Peninsula," Kim said, according to KCNA.

The limited energy and computing resources of unmanned aerial vehicles (UAVs) hinder the application of aerial artificial intelligence. The utilization of split inference in UAVs garners significant attention due to its effectiveness in mitigating computing and energy requirements. However, achieving energy-efficient split inference in UAVs remains complex considering of various crucial parameters such as energy level and delay constraints, especially involving multiple tasks. In this paper, we present a two-timescale approach for energy minimization in split inference, where discrete and continuous variables are segregated into two timescales to reduce the size of action space and computational complexity. This segregation enables the utilization of tiny reinforcement learning (TRL) for selecting discrete transmission modes for sequential tasks. Moreover, optimization programming (OP) is embedded between TRL's output and reward function to optimize the continuous transmit power. Specifically, we replace the optimization of transmit power with that of transmission time to decrease the computational complexity of OP since we reveal that energy consumption monotonically decreases with increasing transmission time. The replacement significantly reduces the feasible region and enables a fast solution according to the closed-form expression for optimal transmit power. Simulation results show that the proposed algorithm can achieve a higher probability of successful task completion with lower energy consumption.

Simultaneous localization and mapping (SLAM) is a fundamental task for numerous applications such as autonomous navigation and exploration. Despite many SLAM datasets have been released, current SLAM solutions still struggle to have sustained and resilient performance. One major issue is the absence of high-quality datasets including diverse all-weather conditions and a reliable metric for assessing robustness. This limitation significantly restricts the scalability and generalizability of SLAM technologies, impacting their development, validation, and deployment. To address this problem, we present SubT-MRS, an extremely challenging real-world dataset designed to push SLAM towards all-weather environments to pursue the most robust SLAM performance. It contains multi-degraded environments including over 30 diverse scenes such as structureless corridors, varying lighting conditions, and perceptual obscurants like smoke and dust; multimodal sensors such as LiDAR, fisheye camera, IMU, and thermal camera; and multiple locomotions like aerial, legged, and wheeled robots. We develop accuracy and robustness evaluation tracks for SLAM and introduced novel robustness metrics. Comprehensive studies are performed, revealing new observations, challenges, and opportunities for future research.

At least 10 people, including a child, have been killed and 45 injured following a Ukrainian attack on the centre of the Russian provincial capital of Belgorod, the Russian Emergencies Ministry has said. Governor Vyacheslav Gladkov said on Saturday that the attack on Belgorod, about 30km (19 miles) from the border with Ukraine, had hit a residential area. In a Telegram post, he urged all residents to move to air raid shelters as sirens sounded. Belgorod borders Ukraine's Luhansk, Sumy and Kharkiv regions, some of which were hit by Russian air raids on Ukraine on Friday, in what was one of the deadliest attacks since the war began in February 2022. The death toll has risen to 39 from those attacks.

Ukrainian President Volodomyr Zelenskyy gives his outlook on the conflict and offers an update on his countrys counter-offensive on Special Report. Russia's Defense Ministry said Ukraine launched a series of rocket and drone attacks into Russian territories with local officials reporting that two people, including a child, were killed in the attacks. Russia said 13 rockets and 32 drones were shot down over several Russian regions, according to Reuters. A child, born in 2014, was killed in the Bryansk region, while a man in the Belgorod region was also said to have died. Both regions are in western Russia and adjoin Ukraine.

America's Newsroom anchor Bill Hemmer looks back at the top headlines of the past 12 months. The mainstream attention on artificial intelligence (AI) in 2023 allowed militaries to more openly discuss some of the astonishing initiatives they've undertaken as they race toward the future of warfare. AI presented an entirely different challenge and revealed an arms race many did not even know had already gotten well underway: Advanced and automated targeting capabilities, virtual environment weapon testing and AI-controlled vehicles present just the tip of a substantial and rapidly developing iceberg. The allure of AI is so strong that the Pentagon has some 800 AI-related unclassified projects in the works to attain a "force multiplier" integration and gain the upper hand over its rivals. This year gave the general public a better idea of where militaries stand with their astonishing development and where they might head next.