Wired UK: Humanoid robots to gain advanced social skills

Source: wired.co.uk

A pan-European team of robotics researchers began a project this year that could see humanoid bots interact with groups of people in a realistic, anthropomorphic way, for the first time.

The “Humanoids with auditory and visual abilities in populated spaces” (HUMAVIPS) project has the ambitious goal of making humanoid bots just that bit more human by building algorithms that will enable bots to mimic what psychologists call the “cocktail party effect” -– the human ability to focus attention on just one person in the midst of other people, voices and background noise.

If successful, HUMAVIPS will give future humanoid bots something that existing bots don’t possess -– the simple social skills necessary to deal with small groups of people, including the basic intelligence to pick out a group of humans and determine which ones want to interact with it. It could also endow bots with the ability to infer meaning from incoming sense data, which would be a rudimentary step towards truly anthropomorphic robot intelligence.

Led by Radu Horaud, Director of Research at INRIA, the three-year project, which has attracted 2.6m euros in European Commission funding, builds on the POP project (see Wired’s December report), which provided proof-of-concept for the idea that combining auditory and visual information improves a bot’s ability to pick identify human speakers in the midst of background noise.
Read more about HUMAVIPS here.

Wired UK: AMARSi project could see robots learn from co-workers

Source: wired.co.uk

Another recent story for Wired:

Robots of the future will be capable of learning more complex behaviours than ever before if a new, pan-European research project succeeds in its goal of developing the world’s first architecture for advanced robotic motor skills.

If successful, the four-year AMARSi (Adaptive Modular Architecture for Rich Motor Skills) project (which started this month) could see a manufacturing world filled with autonomous, intelligent humanoid worker bots that can learn new skills by interacting with their co-workers. It could also see a society with personal carer bots capable of quickly adapting to complex environments and changing human needs.

If the researchers are successful, the 7 million euro, EU-funded project will enable humanoid (and quadruped) bots to autonomously learn and develop motor skills in open-ended environments in the same way humans do — by learning from the data provided by movement and essentially rewiring their circuits to process and store the new knowledge they’ve acquired.

It’s all a far cry from the limited learning and motor skills capabilities of existing bots and it will rely on a suitably advanced range of technologies to make it happen: dynamic neural networks built on reservoir computing principles, new robotics hardware designs, and sophisticated software algorithms are all involved.

AMARSi relies on a “more-or-less unusual,” biologically inspired view of motor skills that goes beyond traditional robotic designs and is better suited to truly autonomous robots, says Project Coordinator, Jochen Steil, Director of The Cognitive Robotics and Learning Laboratory (CoR-Lab), at Bielefield University, in Germany.

Read more about the AMARSi project here.

Scientist Clarifies Giant Stingray Story

Ian Welch poses with a 771lb giant stingray, he caught on the Maeklong River in Thailand while helping to tag the endangered creatures. Photo: BNPS.CO.UK

A University of Nevada scientist has sought to clarify the ‘giant stingray’ story that’s been doing the rounds recently –and has revealed that the fish was caught again two weeks after the initial catch, but still has not been weighed.

“While the photo is genuine and there’s no denying that this is a huge stingray, the stingray in the photo was never weighed,” says University of Nevada, Reno conservation biologist Zeb Hogan.

Hogan is lead researcher for the “Megafishes Project,” a joint venture with the National Geographic Society which aims to find, study, and protect the world’s largest freshwater fish.

News of the catch spread quickly. However, contrary to initial media reports, it is unknown if this fish, which was tagged and released in central Thailand on January 28, 2009 as part of the National Geographic expedition, is truly the world’s largest freshwater fish, he said. The fish, caught by volunteer angler Ian Welch from a small boat using a rod and reel, will be featured in an upcoming documentary airing on the National Geographic Channel.

“Surprisingly, we caught the stingray again four weeks later on Feb. 28,” Hogan said. “It’s still hasn’t been weighed so it still isn’t known if it’s a record breaker. We estimated the weight based on previous catches and simple ‘back-of-the-envelope’ calculations.”

Hogan, along with his team of researchers and anglers on site at the time of capture, approximate the fish’s weight to be between 550-770 pounds. An even slightly larger fish than the one tagged would almost certainly be a world record freshwater fish, he said.

“In terms of disk width, this is the second largest stingray I’ve seen, the largest was in Cambodia in 2003,” Hogan said. “This recent fish was very thick, so it may have weighed more.”

The big winged fish was caught the second time about four kilometers from the original site by local anglers who work with his team. Researchers immediately released it. The find could mean that the ray population is smaller, or less migratory, than originally believed.

The tagging, tracking and sometime recapturing are how biologists estimate abundance of fish populations, Hogan said. Biologists continue to track the big fish’s movements using an array of underwater listening devices designed to detect tagged fish.

Hogan and his team have tagged 18 of this species of stingrays (Himantura chaophraya) as part of the recently established research project on the stingray in central Thailand for the University of Nevada, Reno, the Thai Department of Fisheries, the sport-fishing company Fishsiam and the National Geographic Society sponsored Megafishes Project. This species is listed as vulnerable to extinction by the International Union for Conservation of Nature (IUCN).

If he can get more funding for the project, Hogan hopes to eventually tag 40-50 stingrays for the research study, the first ever ecological study of the giant freshwater stingray which was discovered only 20 years ago. Freshwater giant stingrays are among the largest of the approximately 200 species of rays. They can be found in a handful of rivers in Southeast Asia and northern Australia.

“We aim to determine its conservation status, its abundance, its maximum size, whether or not it’s a true freshwater species, whether or not regional populations interact and its migratory patterns and critical habitat,” he said.

“It’s clear that this species of giant freshwater stingray has the potential to be the largest freshwater fish in the world,” Hogan said. The current record holder for world’s largest freshwater fish is a 646-pound Mekong giant catfish caught by fishermen in northern Thailand in 2005.

The Megafishes Project is a 5-year initiative to find, study, and protect the world’s largest freshwater fish.  A megafish is defined as any freshwater fish species that grows over 6 feet long or weighs more than 200 pounds.  Approximately two dozen fish meet this criteria, including catfish, carp, trout, sturgeon, sawfish, paddlefish, gar and the giant freshwater stingray.

Who Owns The Fastest Muscles On Earth?

It must be cheetahs, right? Or peregrine falcons?
How about the Pronghorn Antelope or the threadsnake?

Nope.

According to a team of scientists at the University of Utah, the fastest muscles on earth actually belong to