To better coordinate the movement of robots relative to each other, researchers have developed a system for predicting the direction of their leader based on its behavior.

Researchers in robotics from the University of California at Davis have developed a control system that allows the robots to collect evidence suggesting that their leader is about to turn, predict where it will go and therefore forward. “This is a fundamental problem in robotics,” says Sanjay Joshi, associate professor mechanical and aeronautical engineering at UC Davis. Indeed, whether walking in the street, while driving on the highway or in many other situations, the man collects often deliberate signals and unconscious clues in order to predict what the others and act accordingly. The robots, however, more difficult to coordinate in this way, for example when the leader of a group turns a corner and disappears from the field of vision of its congeners. Studies in behavioral psychology have shown that a person who is unconsciously turn to a brief nod in the direction it will take to ensure that others can follow.

A system inspired by studies of behavioral psychology
Human beings use different signals and to build a predictive model of where their peers are going. It is on this model that Sanjay Joshi and his team have developed an integrated control system allowing robots to take into account such behavioral indices in their decision. The research team tested the system on a small commercial robot called Evolution Robotics Scorpion. The camera of the robot was able to identify the stooge who was in the lead. His system was able to combine this information with behavioral indices. Rather than leading the robot programmed to send signals directly to the saying that we should follow, the research team sent “behavioral indicators” in the second robot via a wireless device.

Teaching robots to follow men
The index said that the leader was running but did not specify in what direction. To decide the direction it should take, the robot has developed its own prediction by combining the index with other parameters such as speed and direction of the leader. The researchers concluded that robots are capable of incorporating behavioral information into their decision-making parameters acted more efficiently by following the leader than the others. “Robots increasingly able to integrate behavior and monitor would be easier to integrate a human work. In a hospital, for example robot could follow a doctor in the hallways.” An article describing this work appeared in the August 2008 issue of IEEE Transactions on Industrial Electronics.