Researchers at Duke University and the University of New Mexico (UNM) have developed a system for controlling moving robots capable of autonomously detecting and capturing other moving targets. The system, which is based on the Marco Polo swimming pool game, enables robots to sense and intercept moving targets.
"Games give us a good way of making these highly complex problems easier to visualize," says Duke professor Silvia Ferrari. "Just as in Marco Polo, we needed to create a way that permits mobile robots to detect other moving objects and make predictions about where the targets might go." Ferrari previously led the development of a similar algorithm that divided a space into a series of cells, which a robot could use to move through without colliding with stationary objects.
The most recent research equipped robots with camera sensors, but also used stationary camera sensors to provide coverage of all the cells within the space. "The idea is that multiple sensors are deployed in the space to cooperatively detect moving targets within that space," says UNM professor Rafael Fierro. "The ultimate path taken by the robot sensor is one that maximizes the probability of detection and minimizes the distance needed to capture the target."
From Duke Today
View Full Article