Scientist develops 'brain' for robots

An Indian-origin scientist in the United States has developed a new feedback system that allows robots to operate with minimal supervision and could eventually lead to autonomous machines.

The system may lead to robots which think for themselves, learn, adapt and use active critique to work unsupervised.

Developed by Jagannathan Sarangapani, from Missouri University of Science and Technology, the system makes use of current formation moving robots and introduces a fault-tolerant control design to improve the probability of completing a set task.

The new feedback system will allow a “follower” robot to take over as the “leader” robot if the original leader has a system or mechanical failure.

In a leader/follower formation, the lead robot is controlled through a nonholonomic system, meaning that the trajectory is set in advance, and the followers are tracing the same pattern that the leader takes by using Sonar.

When a problem occurs and roles need to be changed to continue, the fault tolerant control system comes into use.

It uses reinforcement learning and active critique, both inspired by behaviourial psychology.