Robot with predictive powers created

Robot with predictive powers created

Robot with predictive powers created

European scientists have created a robot that can predict the intentions of humans, a development that could pave the way to make interactions between human and robot more natural.

The EU-funded JAST project aimed to see whether human and robot could "coordinate their work" and move on with its task without being told what to do next. In effect, the researchers tried to build robots that could be less like workers and more like companions. "In our experiments the robot is not observing to learn a task," explains Wolfram Erlhagen, one of the project consortium's research partners. "The JAST robots already know the task, but they observe behaviour, map it against the task, and quickly learn to anticipate [partner actions] or spot errors when the partner does not follow the correct or expected procedure," stressed Erlhagen, from the University of Minho in Portugal.

The robot, by observing how its human partner grasped a tool or model part, was able to predict how he intended to use it. Clues like these helped the robot to anticipate what its partner might need next, the Science Daily online reported. "Anticipation permits fluid interaction," said Erlhagen. "The robot does not have to see the outcome of the action before it is able to select the next item," he stressed.
Robotic scientists also programmed the machine to deal with suspected errors and seek clarification when their partner's intentions were ambiguous. "Our robot has a neural architecture that mimics the resonance processing that our human studies showed take place during joint actions," said Erlhagen, the leader of the multidisciplinary team.

However, the scientists cautioned that robots would have to learn some manners before they are let loose around humans. Humans know how to behave according to the context they are in. This is subtle and would be difficult for a robot to understand. Nevertheless, robotic scientists were hopeful that by refining this ability to anticipate, it should be possible to produce machine that are proactive in joint tasks and decision-making.