Tehran, Iran – The United States has doubled down on its claim that Iran is planning to sell "hundreds" of drones to Russia to be used in Ukraine, a day after Tehran explicitly rejected the allegation. Jake Sullivan, the US national security adviser, on Saturday reiterated his statement made earlier this week that Iran wants to sell weapons-capable unmanned aerial vehicles (UAVs) to Moscow. He released satellite imagery to the US-based CNN network that purportedly showed that a Russian delegation visited an airfield in central Kashan at least twice in the last month. The Russian delegation is alleged to have been treated to a showcase of the Shahed-191 and Shahed-129 drones, both capable of carrying precision-guided missiles. Sullivan also claimed earlier this week that Iran is training Russian forces in using the drones, and said it is unclear if any drones have already been sold to Moscow.

Autonomous delivery via self-driving cars, on the other hand, is likely further off. Development of the technology has been a slow process, as the machines have continued to plague developers with crashes, sudden stops, and other unforeseen events on the road. These problems, referred to in the industry as "edge cases," are the main deterrent to the wider adoption of self-driving cars, according to Ali Kashani, founder of delivery robotics company Serve, which was spun off from Postmates' autonomous delivery division in 2021.

On the outskirts of Kyiv, troops are in training to be the tip of the spear in Ukraine's drive to modernise its tactical response on the front lines of the war with Russia, through a significant expansion of its drone fleet. Ukraine's military does not have an official drone unit but the use of unmanned aerial vehicles (UAVs) has made it possible for Kyiv to conduct reconnaissance along the 2,470-kilometre (1,535-mile) front line, spotting Russian forces and equipment and remotely directing artillery fire against targets. Drones save Ukrainian lives, but they are expensive and in short supply. "Nowadays, it's very important to have a drone in each battle unit because this is our eyes in the sky," said Lieutenant Anton Galyashinskiy, a Ukrainian army expert in visual data analytics. Galyashinskiy and nine of his fellow soldiers are learning to pilot drones from a moving vehicle.

Amazon has revealed the second city where it plans to start making drone deliveries later this year. The company says it will start contacting customers in College Station, Texas, to gauge their interest in receiving orders via Prime Air. Amazon says it was impressed by many elements of the city, including the research being conducted by Texas A&M University, such as work on drone technology. The US Census Bureau estimates the population of College Station was 120,000 as of last July, so while it isn't the biggest city around, it seems like a decent size for the initially rollout of Prime Air. "Amazon's new facility presents a tremendous opportunity for College Station to be at the forefront of the development of drone delivery technology," Karl Mooney, the mayor of College Station, said.

In an undulating expanse of grassland at the city limits, a pick-up truck kicks up dust as it hurtles downhill, its passengers belting out the theme to 1980s hit comedy "Police Academy". It's a Ukrainian military Mitsubishi L200 on the outskirts of Kyiv and it is chasing after a quadcopter surveillance drone, not bank robbers. The troops inside are in training to be the tip of the spear in Ukraine's drive to modernise its tactical response on the frontlines of its war with Russia, in a massive expanse of its drone fleet. One of Europe's poorest countries even before Moscow's invasion on February 24, Ukraine does not have an official drone unit and is relying on the patriotism and hard cash of its civilians for equipment and training. "Nowadays it's very important to have a drone in each battle unit because this is our eyes in the sky," says Lieutenant Anton Galyashinskiy, 40, an army expert in visual data analytics who is taking part in the exercise.

Each summer, thousands of people flock to the surf beaches of California and Australia, eager to catch one of the Pacific's classic waves. But they likely don't realize that they're sharing the water with growing numbers of great white sharks congregating offshore. The phenomenon has been confirmed using drone technology, which is transforming shark research with its ability to give scientists a bird's-eye view of the animals inhabiting the world's coasts. Drone observations often can reveal more than Earth-bound research methods about shark movements, feeding habits, social relationships, and the animals' reactions to people in their habitat.

A seal has been captured on drone footage using mussel farm lines to try to escape an orca hunt.

To control boll weevil (Anthonomus grandis L.) pest re-infestation in cotton fields, the current practices of volunteer cotton (VC) (Gossypium hirsutum L.) plant detection in fields of rotation crops like corn (Zea mays L.) and sorghum (Sorghum bicolor L.) involve manual field scouting at the edges of fields. This leads to many VC plants growing in the middle of fields remain undetected that continue to grow side by side along with corn and sorghum. When they reach pinhead squaring stage (5-6 leaves), they can serve as hosts for the boll weevil pests. Therefore, it is required to detect, locate and then precisely spot-spray them with chemicals. In this paper, we present the application of YOLOv5m on radiometrically and gamma-corrected low resolution (1.2 Megapixel) multispectral imagery for detecting and locating VC plants growing in the middle of tasseling (VT) growth stage of cornfield. Our results show that VC plants can be detected with a mean average precision (mAP) of 79% and classification accuracy of 78% on images of size 1207 x 923 pixels at an average inference speed of nearly 47 frames per second (FPS) on NVIDIA Tesla P100 GPU-16GB and 0.4 FPS on NVIDIA Jetson TX2 GPU. We also demonstrate the application of a customized unmanned aircraft systems (UAS) for spot-spray applications based on the developed computer vision (CV) algorithm and how it can be used for near real-time detection and mitigation of VC plants growing in corn fields for efficient management of the boll weevil pests.

Ukraine destroyed a series of Russian ordnance depots in the 20th week of the war, demonstrating the efficiency of US-supplied HIMARS (High Mobility Artillery Rocket System) rocket systems and other Western systems, and worrying Russian military observers. These Ukrainian attacks appear to be part of preparations for a summer counteroffensive in the southern Kherson and Zaporizhia districts, which border Crimea. Ukraine said it destroyed a key Russian command post in Kherson district along with a weapons arsenal, killing 12 Russian soldiers on July 10. Its armed forces posted drone footage of a depot in flames. Two days later, Ukraine said it had struck another Russian ammunition depot in Nova Kakhovka, also in Kherson oblast, this time killing 52 soldiers.

The cotton boll weevil, Anthonomus grandis Boheman is a serious pest to the U.S. cotton industry that has cost more than 16 billion USD in damages since it entered the United States from Mexico in the late 1800s. This pest has been nearly eradicated; however, southern part of Texas still faces this issue and is always prone to the pest reinfestation each year due to its sub-tropical climate where cotton plants can grow year-round. Volunteer cotton (VC) plants growing in the fields of inter-seasonal crops, like corn, can serve as hosts to these pests once they reach pin-head square stage (5-6 leaf stage) and therefore need to be detected, located, and destroyed or sprayed . In this paper, we present a study to detect VC plants in a corn field using YOLOv3 on three band aerial images collected by unmanned aircraft system (UAS). The two-fold objectives of this paper were : (i) to determine whether YOLOv3 can be used for VC detection in a corn field using RGB (red, green, and blue) aerial images collected by UAS and (ii) to investigate the behavior of YOLOv3 on images at three different scales (320 x 320, S1; 416 x 416, S2; and 512 x 512, S3 pixels) based on average precision (AP), mean average precision (mAP) and F1-score at 95% confidence level. No significant differences existed for mAP among the three scales, while a significant difference was found for AP between S1 and S3 (p = 0.04) and S2 and S3 (p = 0.02). A significant difference was also found for F1-score between S2 and S3 (p = 0.02). The lack of significant differences of mAP at all the three scales indicated that the trained YOLOv3 model can be used on a computer vision-based remotely piloted aerial application system (RPAAS) for VC detection and spray application in near real-time.