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.
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.
A team of European experts is working on a mind-controlled robotic exoskeleton that could enable people currently confined to wheelchairs to walk again and also help astronauts rehabilitate to Earth gravity after prolonged periods in the weightlessness of space.
The MindWalker system, which is being developed as part of a three-year, 2.5 million euro project, consists of a brain-computer interface (BCI), a virtual reality training environment and a robotic exoskeleton attached to the legs.
If perfected, MindWalker will enable people with spinal chord injuries to achieve mobility by sidestepping their spinal chord as a communications pathway to their lower limbs. And, instead of having to rely on wheelchairs or walking frames to get around, they will be supported by an exoskeleton specially designed for everyday use.
Meanwhile, astronauts returning from prolonged space trips — trips that can cause severe bone deterioration and muscle loss — could use the system on their return to Earth to speed up their readjustment to Earth gravity.
If successful, the EU-funded project will bring several advances in different areas of BCI and exoskeleton design.
Read more about MindWalker here.