London, July 15: Experts at the Technical University of Munich have developed a new robot, called B21, which can keep track of the contents of a kitchen, and can learn simple tasks.

The researchers say that their robot may soon gain the ability to prepare dinner while its owners relax.

According to them, the robot exploits the use of radio-frequency identification (RFID) tags on dishes and utensils to avoid some of the object-recognition difficulties that have plagued previous household robots.

"If you want to interpret and understand everyday activities using vision data, it''s very complicated, error-prone, and resource intensive. If you do it with RFID tags, there is very little sensor information, but it''s highly correlated with the activities you are performing," New Scientist magazine quoted lead researcher Michael Beetz as saying.

The researchers say that not only their robot can know where everything is, but it can also learn simple tasks simply by observing the movements of the objects.

"Setting the table is very easily recognised from cups and plates disappearing from the cupboard and appearing on the table, and cleaning up later is characterised by the same objects disappearing from the table and appearing in the dishwasher," Beetz said.

He even said that the research team was trying to connect a number of open-source software packages so as to allow the robot to get instructions from the internet.

Such a system would enable the machine to understand instructions like carrying four plates to th table, instead of making four trips with one plate in each trip.

Connecting robots to the internet may also allow them to share data about specific tasks, recipes, and handy household tips that they have learnt.

"The hard step will be to have the first robot doing it. But then they would share everything," Beetz says.

Stanford University roboticist Andrew Ng said: "It''s very interesting and promising work.

He added: "If you have sensors just on the robot, the range of things the robot can perceive is very limited. If it is able to use sensors embedded in an intelligent environment, it''s as if the robot has many more eyes and sensors and can immediately act much more intelligently in a new environment."

A report describing the new robot has been published in the journal Robotics and Autonomous Systems. (ANI)