Indian-origin scientist develops new type of robotic brain

An Indian-origin scientist in US 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 that think for themselves, learn, adapt and use active critique to work unsupervised.

Developed by Dr 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 change to continue, the fault tolerant control system comes into use.

It uses reinforcement learning and active critique, both inspired by behaviourist psychology to show how machines act in environments to maximise work rate, to help the new, unmanned robot to estimate its new course.

Without this, the follower wouldn't have a path to follow and the task would fail.

"Imagine you have one operator in an office controlling 10 bulldozers remotely," said Sarangapani, the William A Rutledge - Emerson Electric Co Distinguished Professor in Electrical Engineering at S&T.

"In the event that the lead one suffers a mechanical problem, this hardware allows the work to continue," said Sarangapani.

The innovative research can be applied to robotic security surveillance, mining and even aerial manoeuvring.

Sarangapani believes that the research is most important for aerial vehicles. When a helicopter is in flight, faults can now be detected and accommodated.

This means that instead of a catastrophic failure resulting in a potentially fatal crash, the system can allow for a better chance for an emergency landing instead.

The fault tolerance would notice a problem and essentially shut down that malfunctioning part while maintaining slight control of the overall vehicle.

"The end goal is to push robotics to the next level," said Sarangapani.

"I want robots to think for themselves, to learn, adapt and use active critique to work unsupervised. A self-aware robot will eventually be here, it is just a matter of time, he said.