The New York State UAS Test Site, TruWeather Solutions, the NUAIR Alliance and a company called Windshape have announced that using “industry-leading” micro-weather stimulations, they tested the impact of wind on the air worthiness and performance of various types of UAS. Testing took place at the New York State UAS Test Site at Rome, New York's Griffiss International Airport. “We know that weather impacts small drones in a variety of ways and these tests enabled us to evaluate that impact and each platform’s capacity to reject atmospheric disturbances and maintain safe flight,” explains Major General Marke F. “Hoot” Gibson (ret), chief executive officer, NUAIR Alliance.

With a mind towards reinventing how people care for their lawn, iRobot Corp. has unveiled its new Terra robot mower, which features state-of-the-art mapping and navigation technologies, high-performance, high-quality mowing, and easy installation. Using iRobot’s Imprint Smart Mapping technology, Terra learns its environment, and can mow a lawn like a human does, as it navigates a yard and cuts efficiently in straight, back-and-forth lines. Terra remembers its location in the yard, and where it still needs to cover. If its battery runs low, it will return to its base to recharge, and then pick up where it left off until the yard is complete.

Researchers from MIT and Microsoft have developed a model that identifies instances where autonomous systems have “learned” from training examples that don’t match what’s actually happening in the real world. The researchers say that this model could be used by engineers to improve the safety of artificial intelligence (AI) systems, such as driverless vehicles and autonomous robots. According to the researchers, AI systems that power driverless cars are thoroughly trained in virtual simulations to prepare the vehicle for nearly every event on the road. Sometimes, though, the car makes an unexpected error in the real world because an event occurs that should, but doesn’t, change the car’s behavior.