When Hurricane Helene and Milton hit the Southeast US, they left a trail of devastation in their wake. Roads, homes, and chunks of towns were swept away by torrential floods. Thousands of residents were left without homes and forced to take refuge in community centers which were cut off from access to critical supplies and resources. One of those shelters, a senior center in Marion, North Carolina, has received a lifeline from an unlikely source. For a little over a week, a white, buzzing autonomous drone operated by Wing has been collecting prescription drugs, baby formula, and other critical resources from a nearby Walmart supercenter and airdropping them to the senior center.

Hamas on Friday is admitting to suffering "very painful and distressing" losses following the killing of its leader Yahya Sinwar as the Israeli military has released new drone video capturing the final moments of the terrorist's life. Footage taken of a wounded Sinwar shows him throwing a wooden board at a drone that was surveying damage inside of a building that the Israel Defense Forces targeted in Rafah, according to IDF Spokesperson Rear Adm. Daniel Hagari. Sinwar was later found dead with a gun and nearly 11,000 in his possession, he added. "Yes it's very painful and distressing to lose beloved people, especially extraordinary leaders like ours, but what we are sure of is that we are eventually victorious; this is the outcome for all people who fought for their liberty," senior Hamas official Basem Naim said Friday. "It seems that Israel believes that killing our leaders means the end of our movement and the struggle of the Palestinian people. They can believe what they want, and this is not the first time they said that," he continued.

Ukrainian troops are locked in a bitter battle for the town of Toretsk in the eastern region of Donetsk, which Russian troops entered last Friday. A spokesperson for Luhansk Technical University said Russian troops were demolishing the town as they advanced. "They erase the city with artillery. We have already seen it in other towns of Donbas. They are trying to find weak points in our defence with such small strikes," Anastasia Bobovnikova said.

The Israeli military released a video on Thursday showing a drone flying into a building in Rafah, where a man the video identifies as Yahya Sinwar is sitting on a chair. The Israeli military described the video as showing Mr. Sinwar "moments before his elimination." While the video has been edited, it is clear that the man, who is covered in dust, watches the drone for at least 20 seconds before throwing an object, possibly a stick, at the drone. The Times could not independently verify the identity of the man. The room seen in the drone video matches the location of earlier photographs obtained by The New York Times showing the corpse of a man closely resembling Mr. Sinwar.

Multi-agent systems are trained to maximize shared cost objectives, which typically reflect system-level efficiency. However, in the resource-constrained environments of mobility and transportation systems, efficiency may be achieved at the expense of fairness -- certain agents may incur significantly greater costs or lower rewards compared to others. Tasks could be distributed inequitably, leading to some agents receiving an unfair advantage while others incur disproportionately high costs. It is important to consider the tradeoffs between efficiency and fairness. We consider the problem of fair multi-agent navigation for a group of decentralized agents using multi-agent reinforcement learning (MARL). We consider the reciprocal of the coefficient of variation of the distances traveled by different agents as a measure of fairness and investigate whether agents can learn to be fair without significantly sacrificing efficiency (i.e., increasing the total distance traveled). We find that by training agents using min-max fair distance goal assignments along with a reward term that incentivizes fairness as they move towards their goals, the agents (1) learn a fair assignment of goals and (2) achieve almost perfect goal coverage in navigation scenarios using only local observations. For goal coverage scenarios, we find that, on average, our model yields a 14% improvement in efficiency and a 5% improvement in fairness over a baseline trained using random assignments. Furthermore, an average of 21% improvement in fairness can be achieved compared to a model trained on optimally efficient assignments; this increase in fairness comes at the expense of only a 7% decrease in efficiency. Finally, we extend our method to environments in which agents must complete coverage tasks in prescribed formations and show that it is possible to do so without tailoring the models to specific formation shapes.

This paper focuses on developing a bearings-only measurement-based three-dimensional window traversal guidance method for quadrotor Uninhabitated Aerial Vehicles (UAVs). The desired flight path and heading angles of the quadrotor are proposed as functions of the bearing angle information of the four vertices of the window. These angular guidance inputs employ a bearing angle bisector term and an elliptic shaping angle term, which directs the quadrotor towards the centroid of the window. Detailed stability analysis of the resulting kinematics demonstrates that all quadrotor trajectories lead to the centroid of the window along a direction which is normal to the window plane. A qualitative comparison with existing traversal methodologies showcases the superiority of the proposed guidance approach with regard to the nature of information, computations for generating the guidance commands, and flexibility of replanning the traversal path. Realistic simulations considering six degree-of-freedom quadrotor model and Monte Carlo studies validate the effectiveness, accuracy, and robustness of the proposed guidance solution. Representative flight validation trials are carried out using an indoor motion capture system.

This paper proposes an integrated framework for coordinating multiple unmanned aerial vehicles (UAVs) in a distributed fashion to persistently enclose and track a moving target without external localization systems. It is assumed that the UAV can obtain self-displacement and the target's relative position using vision-based methods within its local frame. Additionally, UAVs can measure relative distances and communicate with each other, e.g. by ultrawideband (UWB) sensors. Due to the absence of a global coordinate system, measurements from neighbors cannot be directly utilized for collaborative estimation of the target state. To address this, a recursive least squares estimator (RLSE) for estimating the relative positions between UAVs is integrated into a distributed Kalman filter (DKF), enabling a persistent estimation of the target state. When the UAV loses direct measurements of the target due to environmental occlusion, measurements from neighbors will be aligned into the UAV's local frame to provide indirect measurements. Furthermore, simultaneously ensuring the convergence of the estimators and maintaining effective target tracking is a significant challenge. To tackle this problem, a consensus-based formation controller with bounded inputs is developed by integrating a coupled oscillator-based circular formation design. Theoretical analysis shows that the proposed framework ensures asymptotic tracking of a target with constant velocity. For a target with varying velocity, the tracking error converges to a bounded region related to the target's maximum acceleration. Simulations and experiments validate the effectiveness of the proposed algorithm.

Deep Reinforcement learning (DRL) is used to enable autonomous navigation in unknown environments. Most research assume perfect sensor data, but real-world environments may contain natural and artificial sensor noise and denial. Here, we present a benchmark of both well-used and emerging DRL algorithms in a navigation task with configurable sensor denial effects. In particular, we are interested in comparing how different DRL methods (e.g. model-free PPO vs. model-based DreamerV3) are affected by sensor denial. We show that DreamerV3 outperforms other methods in the visual end-to-end navigation task with a dynamic goal - and other methods are not able to learn this. Furthermore, DreamerV3 generally outperforms other methods in sensor-denied environments. In order to improve robustness, we use adversarial training and demonstrate an improved performance in denied environments, although this generally comes with a performance cost on the vanilla environments. We anticipate this benchmark of different DRL methods and the usage of adversarial training to be a starting point for the development of more elaborate navigation strategies that are capable of dealing with uncertain and denied sensor readings.

With the rapid advancements in wireless communication fields, including low-altitude economies, 6G, and Wi-Fi, the scale of wireless networks continues to expand, accompanied by increasing service quality demands. Traditional deep reinforcement learning (DRL)-based optimization models can improve network performance by solving non-convex optimization problems intelligently. However, they heavily rely on online deployment and often require extensive initial training. Online DRL optimization models typically make accurate decisions based on current channel state distributions. When these distributions change, their generalization capability diminishes, which hinders the responsiveness essential for real-time and high-reliability wireless communication networks. Furthermore, different users have varying quality of service (QoS) requirements across diverse scenarios, and conventional online DRL methods struggle to accommodate this variability. Consequently, exploring flexible and customized AI strategies is critical. We propose a wireless network intent (WNI)-guided trajectory generation model based on a generative diffusion model (GDM). This model can be generated and fine-tuned in real time to achieve the objective and meet the constraints of target intent networks, significantly reducing state information exposure during wireless communication. Moreover, The WNI-guided optimization trajectory generation can be customized to address differentiated QoS requirements, enhancing the overall quality of communication in future intelligent networks. Extensive simulation results demonstrate that our approach achieves greater stability in spectral efficiency variations and outperforms traditional DRL optimization models in dynamic communication systems.

Aerial robots are a well-established solution for exploration, monitoring, and inspection, thanks to their superior maneuverability and agility. However, in many environments of interest, they risk crashing and sustaining damage following collisions. Traditional methods focus on avoiding obstacles entirely to prevent damage, but these approaches can be limiting, particularly in complex environments where collisions may be unavoidable, or on weight and compute-constrained platforms. This paper presents a novel approach to enhance the robustness and autonomy of drones in such scenarios by developing a path recovery and adjustment method for a high-speed collision-resistant drone equipped with binary contact sensors. The proposed system employs an estimator that explicitly models collisions, using pre-collision velocities and rates to predict post-collision dynamics, thereby improving the drone's state estimation accuracy. Additionally, we introduce a vector-field-based path representation which guarantees convergence to the path. Post-collision, the contact point is incorporated into the vector field as a repulsive potential, enabling the drone to avoid obstacles while naturally converging to the original path. The effectiveness of this method is validated through Monte Carlo simulations and demonstrated on a physical prototype, showing successful path following and adjustment through collisions as well as recovery from collisions at speeds up to 3.7 m / s.