Please enable JavaScript to experience the full functionality of GMX.

Robot can be controlled by human mind

Scientists have built a robot that is controlled by the power of the mind.

Researcher's at the Massachusetts Institute of Technology (MIT)'s Computer Science and Artificial Intelligence Laboratory (CSAIL) have designed a new system that monitors human brain activity and muscle activity.

This allows a robot to be controlled by brain signals and small hand gestures.

A demonstration video of the new system shows humanoid robot 'Baxter' moving a power drill to one of three possible targets.

The machine is linked to a human controller whose brainwaves are being monitored by EEG sensors and the muscles in their arm being read using EMG technology.

The system can detect in real-time if the human controller notices an error in its chosen target, and flick of the finger can scroll to the correct option.

CSAIL Director Daniela Rus said: "This work combining EEG and EMG feedback enables natural human-robot interactions for a broader set of applications than we've been able to do before using only EEG feedback. By including muscle feedback, we can use gestures to command the robot spatially, with much more nuance and specificity."

The ground-breaking advancement in the new system meant it could be controlled by a person it had never had contact with before.

Previous systems could generally recognise brain signals when the people using them had been trained to 'think' in specific ways and the system had been trained to recognise those signals.

PhD candidate Joseph DelPreto, who is the lead author of the study, said: "What's great about this approach is that there's no need to train users to think in a prescribed way. The machine adapts to you, and not the other way around."

He added: "By looking at both muscle and brain signals, we can start to pick up on a person's natural gestures along with their snap decisions about whether something is going wrong. This helps make communicating with a robot more like communicating with another person."

Under human supervision, 'Baxter' went from choosing the correct target to drill 70 per cent of the time to more than 97 per cent of the time.

The team hope the research could be used to develop robots to help the elderly or workers with limited mobility.

Rus said: "We'd like to move away from a world where people have to adapt to the constraints of machines. Approaches like this show that it's very much possible to develop robotic systems that are a more natural and intuitive extension of us."

Sponsored Content