The Age-of-Information (AoI) metric has been widely studied in the theoretical communication networks and queuing systems literature. However, experimental evaluation of its applicability to complex real-world time-sensitive systems is largely lacking. In this work, we develop, implement, and evaluate an AoI-based application layer middleware that enables the customization of WiFi networks to the needs of time-sensitive applications. By controlling the storage and flow of information in the underlying WiFi network, our middleware can: (i) prevent packet collisions; (ii) discard stale packets that are no longer useful; and (iii) dynamically prioritize the transmission of the most relevant information. To demonstrate the benefits of our middleware, we implement a mobility tracking application using a swarm of UAVs communicating with a central controller via WiFi. Our experimental results show that, when compared to WiFi-UDP/WiFi-TCP, the middleware can improve information freshness by a factor of 109x/48x and tracking accuracy by a factor of 4x/6x, respectively. Most importantly, our results also show that the performance gains of our approach increase as the system scales and/or the traffic load increases.

In recent years, unmanned aerial vehicle (UAV) related technology has expanded knowledge in the area, bringing to light new problems and challenges that require solutions. Furthermore, because the technology allows processes usually carried out by people to be automated, it is in great demand in industrial sectors. The automation of these vehicles has been addressed in the literature, applying different machine learning strategies. Reinforcement learning (RL) is an automation framework that is frequently used to train autonomous agents. RL is a machine learning paradigm wherein an agent interacts with an environment to solve a given task. However, learning autonomously can be time consuming, computationally expensive, and may not be practical in highly-complex scenarios. Interactive reinforcement learning allows an external trainer to provide advice to an agent while it is learning a task. In this study, we set out to teach an RL agent to control a drone using reward-shaping and policy-shaping techniques simultaneously. Two simulated scenarios were proposed for the training; one without obstacles and one with obstacles. We also studied the influence of each technique. The results show that an agent trained simultaneously with both techniques obtains a lower reward than an agent trained using only a policy-based approach. Nevertheless, the agent achieves lower execution times and less dispersion during training.

Ukraine accused Russia of destroying homes in the southeast and knocking out power in many areas with a new volley of missiles on Monday, while Moscow said Ukrainian drones had attacked two air bases deep inside Russia hundreds of kilometres from the front lines. A new missile barrage had been anticipated in Ukraine for days, and it took place just as emergency blackouts were due to end, with previous damage repaired. The strikes plunged parts of Ukraine back into freezing darkness with temperatures now firmly below zero Celsius (32 Fahrenheit). At least four people were killed in the Russian attacks, Ukrainian President Volodymyr Zelenskyy said, adding that most of some 70 missiles were shot down. Energy workers had already begun work on restoring power supplies, he said.

Warnings that Russia was planning a fresh wave of attacks have been circulating for several days. They eventually arrived just hours after a series of explosions at two airbases deep inside Russia, which Moscow blamed on Ukrainian drones intercepted by Russian air-defences.

Japan on Monday lifted its ban on urban drone flights outside visible range over residential areas to allow aerial parcel deliveries and help address the country's labor shortages amid the greying of the population across the country, particularly in rural areas. Unattended drone flights were previously only allowed over uninhabited areas, such as mountains, rivers and farmlands in so-called level-three operations under the four-tier classification system. Level-four automated drone operations over residential areas will likely begin once operators seeking to provide such services complete government procedures necessary for conducting the flight around March. This could be due to a conflict with your ad-blocking or security software. Please add japantimes.co.jp and piano.io to your list of allowed sites.

Weapon systems that select and engage targets without meaningful human control are unacceptable and need to be prevented. All countries have a duty to protect humanity from this dangerous development by banning fully autonomous weapons. Retaining meaningful human control over the use of force is an ethical imperative, a legal necessity, and a moral obligation. In the period since Human Rights Watch and other nongovernmental organizations launched the Campaign to Stop Killer Robots in 2013, the question of how to respond to concerns over fully autonomous weapons has steadily climbed the international agenda. The challenge of killer robots, like climate change, is widely regarded as a grave threat to humanity that deserves urgent multilateral action.

Delivery robots have been spotted forming an orderly queue to use a pedestrian crossing - with one asking a passer-by to press the button for them. Pictures showed The Starship Technologies food delivery robots patiently waiting to cross the road as part of its new trial in Cambridge this month. Cyclist Naomi Davies spotted the group of robots on the pavement and said they waited for three light changes before one crossed the road. While waiting in line, one of the robots asked a woman to press the button for them. Starship said the robots were not'shy' so were happy to ask strangers for help when they needed it.

This paper addresses the problem of position estimation in UAVs operating in a cluttered environment where GPS information is unavailable. A model learning-based approach is proposed that takes in the rotor RPMs and past state as input and predicts the one-step-ahead position of the UAV using a novel spectral-normalized memory neural network (SN-MNN). The spectral normalization guarantees stable and reliable prediction performance. The predicted position is transformed to global coordinate frame which is then fused along with the odometry of other peripheral sensors like IMU, barometer, compass etc., using the onboard extended Kalman filter to estimate the states of the UAV. The experimental flight data collected from a motion capture facility using a micro-UAV is used to train the SN-MNN. The PX4-ECL library is used to replay the flight data using the proposed algorithm, and the estimated position is compared with actual ground truth data. The proposed algorithm doesn't require any additional onboard sensors, and is computationally light. The performance of the proposed approach is compared with the current state-of-art GPS-denied algorithms, and it can be seen that the proposed algorithm has the least RMSE for position estimates.

Quadcopter trajectory tracking control has been extensively investigated and implemented in the past. Available controls mostly use the Euler angle standards to describe the quadcopters rotational kinematics and dynamics. As a result, the same rotation can be translated into different roll, pitch, and yaw angles because there are multiple Euler angle standards for characterization of rotation in a 3-dimensional motion space. Additionally, it is computationally expensive to convert a quadcopters orientation to the associated roll, pitch, and yaw angles, which may make it difficult to track quick and aggressive trajectories. To address these issues, this paper will develop a flatness-based trajectory tracking control without using Euler angles. We assess and test the proposed controls performance in the Gazebo simulation environment and contrast its functionality with the existing Mellinger controller, which has been widely adopted by the robotics and unmanned aerial system (UAS) communities.

"The future of delivery, today: this is our bold promise," says Lauri Vain (VP of Engineering at Starship), adding, "With a combination of mobile technology, our global fleet of autonomous robots, and partnerships with stores and restaurants, we are helping to make the local delivery industry faster, cleaner, smarter and more cost-efficient, and we are very excited about our partnership with ESPROS and its unique chip technology." Starship Technologies is based in San Francisco with its main engineering office in Estonia. Starship's sidewalk delivery robots travel up to 4 mph (6.4 kph) and weighs around 80 lbs (176 kg). They can carry around 20 lbs (44 kg) at a time. The robots uses a mixture of computer vision and GPS to know its location.