Home India News Indian-American programmes robots to follow the leader better

Indian-American programmes robots to follow the leader better

By IANS,

Washington : An Indian-American professor of engineering has programmed a robot that can sense your head turning left a fraction of a second before your body makes that left turn. That turn of the head is the cue it will pick up to keep following.

While negotiating a highway or sauntering down the street, people pick up cues about what other people are going to do and act accordingly.

Now University of California (Davis) researchers led by associate professor of mechanical and aeronautical engineering Sanjay Joshi have been able to programme robots to pick up cues about their leaders and follow them accordingly.

“Robots that are better at following could be easier for people to work with. A hospital robot could follow a doctor around the wards,” Joshi wrote in the August issue of IEEE Transactions on Industrial Electronics.

Behavioural studies show that people unconsciously turn their heads a fraction of a second before making a left or right turn. Joshi and his team developed a programme that could take such behavioural cues into account in making decisions about which way to move.

Joshi, graduate student Michael Chueh and undergraduates William Au Yeung and Calvin Lei tested the system using a small commercially available robot, the Evolution Robotics Scorpion.

The robot’s camera could identify a target on the lead robot, and the robot’s onboard computer could combine the target information with behavioural cue information.

Rather than have the lead robot signal the follower directly, the research team sent “behavioural cues” to the follower via wireless link. Effectively, the cues told the robot, “the leader might be about to turn right” or “might be about to turn left”.

To develop a decision on how to move, the follower robot was programmed to take into account the lead robot’s behavioural cues and the follower’s prediction of the lead robot’s movement, based on the leader’s current speed and direction.

Robots that incorporated behavioural information into their decisions performed much better at following the leader around corners than others, the researchers found.