
Machine learning guarantees robots' performance in unknown territory
Research News Release
EurekAlert! provides eligible reporters with free access to embargoed and breaking news releases.
Eligibility GuidelinesEurekAlert! offers eligible public information officers paid access to a reliable news release distribution service.
Eligibility Guidelines
EurekAlert! is a service of the American Association for the Advancement of Science.

As engineers increasingly turn to machine learning methods to develop adaptable robots, new work by Princeton University researchers makes progress on safety and performance guarantees for robots operating in novel environments with diverse types of obstacles and constraints.
Urban planners may soon have a new way to measure traffic congestion. By capturing the different routes by which vehicles can travel between locations, researchers have developed a new computer algorithm that helps quantify regions of congestion in urban areas and suggests ways around them.

If you've ever seen a seagull snatch a pasty or felt their beady eyes on your sandwich in the park, you'd be right to suspect they know exactly when to strike to increase their chances of getting a human snack. A new study by the University of Bristol is the most in-depth look to date at the foraging behaviours of urban gulls and how they've adapted to patterns of human activity in a city.

A research team at Toyohashi University of Technology developed a method for reducing aerodynamic noise via plasma. Cavity flow, such as the flow around car gaps of high-speed trains, often radiates aerodynamic noise. A plasma actuator inducing flow was applied to suppress this noise. By periodically switching off the power of the plasma actuator, a higher reduction in sound pressure level was observed when compared with continuous operation under the same power consumption.

Squids use a form of jet propulsion that is not well understood, especially when it comes to their hydrodynamics under turbulent flow conditions. Discovering their secrets can help create new designs for bioinspired underwater robots, so researchers are exploring the fundamental mechanism. They describe their numerical study in Physics of Fluids; among their discoveries, they found that thrust production and efficiency are underestimated within laminar, or nonturbulent, flows.

'The AmphiSTAR uses a sprawling mechanism inspired by cockroaches, and it is designed to run on water at high speeds like the basilisk lizard,' says Ben-Gurion University Prof. Zarrouk. 'We envision that AmphiSTAR can be used for agricultural, search and rescue and excavation applications, where both crawling and swimming are required.'
A research team from North Carolina A&T State University has, for the first time, designed a cloud-based autonomous system framework utilizing the standard messaging protocol for the internet-of-things (IoT). This framework is robust to network-denied environments by utilizing each vehicle, along with a clustering algorithm, to maximize the network coverage area.

Rice University researchers continue to advance the science of single-molecule machines with a new lineup of nanocars, in anticipation of the next international Nanocar Race in 2022.
POSTECH Professor Byoungwoo Kang's research team uncovers a new Li-ion battery electrode material that can achieve high-energy density and high power capability per volume without reducing particle size.

Scientists from the University of Bristol and the Royal Veterinary College have discovered how birds are able to fly in gusty conditions - findings that could inform the development of bio-inspired small-scale aircraft.