Drone operators from the private sector who volunteered to fly unmanned vehicles to the disaster-hit Noto Peninsula in Ishikawa Prefecture following January's magnitude 7.6 earthquake returned to the region last week after record-breaking rainfall caused severe floods and cut off access to remote communities. The Japan UAS Industrial Development Association (JUIDA), an industry body of drone companies, was commissioned by the Self-Defense Forces to carry out multiple missions to transport bread, vegetable juice, milk, and cooked and dry-packed rice to people in areas that had been cut off. Other operators that took part in the effort included KDDI SmartDrone, which was directly commissioned by the prefecture to fly drones over wrecked roads to snap images that would help assess the damage caused by landslides.

Navigating complex environments requires Unmanned Aerial Vehicles (UAVs) and autonomous systems to perform trajectory tracking and obstacle avoidance in real-time. While many control strategies have effectively utilized linear approximations, addressing the non-linear dynamics of UAV, especially in obstacle-dense environments, remains a key challenge that requires further research. This paper introduces a Non-linear Model Predictive Control (NMPC) framework for the DJI Matrice 100, addressing these challenges by using a dynamic model and B-spline interpolation for smooth reference trajectories, ensuring minimal deviation while respecting safety constraints. The framework supports various trajectory types and employs a penalty-based cost function for control accuracy in tight maneuvers. The framework utilizes CasADi for efficient real-time optimization, enabling the UAV to maintain robust operation even under tight computational constraints. Simulation and real-world indoor and outdoor experiments demonstrated the NMPC ability to adapt to disturbances, resulting in smooth, collision-free navigation.

In this paper, we present our proposed approach for active tracking to increase the autonomy of Unmanned Aerial Vehicles (UAVs) using event cameras, low-energy imaging sensors that offer significant advantages in speed and dynamic range. The proposed tracking controller is designed to respond to visual feedback from the mounted event sensor, adjusting the drone movements to follow the target. To leverage the full motion capabilities of a quadrotor and the unique properties of event sensors, we propose an end-to-end deep-reinforcement learning (DRL) framework that maps raw sensor data from event streams directly to control actions for the UAV. To learn an optimal policy under highly variable and challenging conditions, we opt for a simulation environment with domain randomization for effective transfer to real-world environments. We demonstrate the effectiveness of our approach through experiments in challenging scenarios, including fast-moving targets and changing lighting conditions, which result in improved generalization capabilities.

As both sides of the ongoing Russia-Ukraine war attempt to claim technological supremacy, drone versus drone combat has become routine – and thanks to the ubiquity of cameras, this new kind of warfare is being documented in real time across air, land and sea. Russia's invasion of Ukraine has already been dubbed the "first drone war", with some sources suggesting that small drones are inflicting as much as 80 per cent of the damage to military hardware and personnel.

A new joint venture between Serve Robotics sidewalk delivery robots and Alphabet's Wing flying drone service will do a dual test run. Both tech companies hope that flying and sidewalk drones can cover areas its counterpart can't and speed up delivery times. TechCrunch reported that Serve Robotics and Wing will start making deliveries in Dallas sometime in the coming months. The test will include a select number of customer orders being delivered by a combination of sidewalk robots and flying drones. One of the biggest challenges for drone delivery is coverage.

A new joint venture between Uber's Serve Robotics sidewalk delivery drones and Alphabet's Wing flying drone service will do a dual test run. Both tech companies hope that flying and sidewalk drones can cover areas its counterpart can't and speed up delivery times. TechCrunch reported that Serve Robotics and Wing will start making deliveries in Dallas, Texas sometime in the coming months. The test will include a select number of customer orders being delivered by a combination of sidewalk and flying drones. One of the biggest challenges for drone delivery is coverage.

Bats are amongst the animal kingdom's most unorthodox fliers. Unlike birds, the furry, flying mammals can dynamically reshape and morph their wings to achieve maximum force and hover in place. The soft membrane of their wings, which more closely resembles a human arm than a bird's wing, is also extremely flexible, which means bats can contour themselves to squeeze into tiny corridors. Now, researchers from Northeastern University are leaning on those unique elements and applying them to a fully autonomous flying drone called "Aerobat." Eventually, they believe this bat-inspired robot could be used to navigate sewer tunnels, caves, and other tight corridors largely off-limits to current flying robots.

The Pentagon has said the mass production and deployment of systems to detect, track and neutralize small drones will be the next focus of its Replicator initiative as it seeks to better protect the "most critical" U.S. installations and forces around the globe. "My expectation is that Replicator 2 will deliver meaningfully improved C-sUAS (counter-small unmanned aerial system) protection to critical assets within 24 months of Congress approving funding," Defense Secretary Lloyd Austin wrote in a memorandum published Monday in which he also charged his deputy, Kathleen Hicks, with spearheading the new effort. "I am confident the Replicator Initiative will complement and advance the significant C-sUAS work already underway in the DoD (Department of Defense)," Austin said in the memo.

We perform uncertainty propagation on an event manifold for Guidance & Control Networks (G&CNETs), aiming to enhance the certification tools for neural networks in this field. This work utilizes three previously solved optimal control problems with varying levels of dynamics nonlinearity and event manifold complexity. The G&CNETs are trained to represent the optimal control policies of a time-optimal interplanetary transfer, a mass-optimal landing on an asteroid and energy-optimal drone racing, respectively. For each of these problems, we describe analytically the terminal conditions on an event manifold with respect to initial state uncertainties. Crucially, this expansion does not depend on time but solely on the initial conditions of the system, thereby making it possible to study the robustness of the G&CNET at any specific stage of a mission defined by the event manifold. Once this analytical expression is found, we provide confidence bounds by applying the Cauchy-Hadamard theorem and perform uncertainty propagation using moment generating functions. While Monte Carlo-based (MC) methods can yield the results we present, this work is driven by the recognition that MC simulations alone may be insufficient for future certification of neural networks in guidance and control applications.

The next ubiquitous computing platform, following personal computers and smartphones, is poised to be inherently autonomous, encompassing technologies like drones, robots, and self-driving cars. Ensuring reliability for these autonomous machines is critical. However, current resiliency solutions make fundamental trade-offs between reliability and cost, resulting in significant overhead in performance, energy consumption, and chip area. This is due to the "one-size-fits-all" approach commonly used, where the same protection scheme is applied throughout the entire software computing stack. This paper presents the key insight that to achieve high protection coverage with minimal cost, we must leverage the inherent variations in robustness across different layers of the autonomous machine software stack. Specifically, we demonstrate that various nodes in this complex stack exhibit different levels of robustness against hardware faults. Our findings reveal that the front-end of an autonomous machine's software stack tends to be more robust, whereas the back-end is generally more vulnerable. Building on these inherent robustness differences, we propose a Vulnerability-Adaptive Protection (VAP) design paradigm. In this paradigm, the allocation of protection resources - whether spatially (e.g., through modular redundancy) or temporally (e.g., via re-execution) - is made inversely proportional to the inherent robustness of tasks or algorithms within the autonomous machine system. Experimental results show that VAP provides high protection coverage while maintaining low overhead in both autonomous vehicle and drone systems.