Researchers at UC Davis have developed a control system that allows a robot to pick up on behavioural cues enabling it to accurately follow another robot in front of it.
Robots that are better at following could be easier for people to work with. A hospital robot, for example, could follow a doctor around wards.
Humans use signals and subconscious cues to build a model that predicts where other people are going. Sanjay Joshi, associate professor of mechanical and aeronautical engineering and his team of researchers at UC Davis built upon this idea by developing a control system for robots that could take such behavioural cues into account when making decisions about which way they should move.
They then tested the system using a small commercially available robot called the Evolution Robotics Scorpion. The robot’s camera could identify a target on the lead robot and its onboard computer could combine that information with behavioural cue information.
Rather than have the lead robot signal the follower directly, the research team sent behavioural cues based on its speed and direction to the robot following it via a wireless link. The follower robot was programmed to take into account these cues and then predict the lead robot’s movement.
The researchers found that the robots that incorporated behavioural information into their decisions performed much better at following the leader around corners than others.
‘We think that if we can embed these cues in control systems, we can make following more reliable,’ said Prof Joshi.
A paper describing the work was published in the August 2008 issue of IEEE Transactions on Industrial Electronics.