UK Experts To Make Robots Emotional

 

Machines Will Take Sensory Human Inputs And Adapt Behavior

 

A mere  metal body with “no emotions” and designed to obey human commands at the flip of a remote control button or other equipment, the robot has been subjected to continuous redesigning and enhancement. Now, a 2.3 million euros European project headed by British Scientists aims to make robots interact with humans emotionally.

           According to BBC, the three-year project, Feelix Growing, comprises six countries, and 25 roboticists, developmental psychologists and neuroscientists. Coordinator Lola Canamero said the aim was to build robots that “learn from humans and respond in a socially and emotionally appropriate manner”.

           “The human emotional world is very complex, but we respond to simple cues, things we don’t notice or we don’t pay attention to, such as how some-one moves,” said Canamero, who is bases at the University of Hertfordshire. The project involves building a series of robots that can take sensory input from the humans they are interacting with and then adapt their behavior accordingly. Canamero likens the robots to babies that learn their behavior from the patterns of movement and emotional state of the world around them.

           The most interesting aspect of the project is the software. Canamero said: “We will use very simple robots as the hardware, and for some of the machines we will build expressive heads ourselves. We are most interested in programming and developing behavioral capabilities, particularly in social and emotional interactions with humans.”

           The robots will learn from the feedback they receive from humans. “It’s mostly behavioral and contact feedback. Tactile feedback and emotional feedback through positive re-inforcement, such as kind words, nice behavior or helping the robot do something if it is stuck,” he said.

           “One of the things we are going to use to detect expressions in faces and patterns in motion is a (artificial) neural networks.” Artificial neural networks are being used because they are useful for adapting to changing inputs.