Robot Localization and Mapping Based on Humans
Scientists at the University of Southern California have come up with a unique means of SLAM (Simultaneous Localization and Mapping) for a robotic vehicle. They’ve tried to emulate the way that humans supposedly do this, by creating a "fingerprint" of where the robot is based on raw data. The fingerprint lists unique features surrounding the robot. The combination of these features differentiates each location.
The benefit to such a system is that it takes relatively few computational cycles to record the raw data from the sensors into a "fingerprint." Later on, pattern matching algorithms can compare data to see if the robot has visited the location before.
Tests on the robotic vehicle — an adapted Daimler-Chrysler Smart Car equipped with a laser range finder and omnidirectional camera as sensors — have shown that it can successfully explore and navigate more than one and a half kilometers of urban terrain without getting lost.
The benefit to such a system is that it takes relatively few computational cycles to record the raw data from the sensors into a "fingerprint." Later on, pattern matching algorithms can compare data to see if the robot has visited the location before.
Read Similar Posts:
TrackBack URL
