Untitled Document
Not a member yet? Register for full benefits!

 Light-based localisation for robotic systems

This story is from the category Artificial Intelligence
Printer Friendly Version
Email to a Friend (currently Down)



Date posted: 11/04/2010

Getting robotic systems to accurately detect both moving and static objects remains an obstacle to building more autonomous robots and more advanced surveillance systems. Innovative technology that uses light beams for localisation and mapping may offer a solution.

The technology advances the current state of the art of Light Detection and Ranging (LIDAR), the optical equivalent of radar in which reflected beams of scattered light are used to determine the location of an object. Whereas most LIDAR systems use a one-step process to detect objects by scanning an area and measuring the time delay between transmission of a pulse and detection of the reflected signal, researchers working in the EU-funded IRPS project added a prior step.

They use LIDAR to first build a 3D map of the area, enabling their system to pinpoint the location of not just static objects but also moving ones - be it a human, an open window or a leaking pipe - to within a few millimetres. The researchers, from four EU countries and Israel and Canada, have called the technology 3D LIMS (3D LIDAR Imaging and Measurement System) and foresee a broad range of applications for it, from navigating autonomous vehicles around airports to monitoring industrial equipment and enhancing security surveillance.

?This two-step LIDAR process, involving first calibration and then real-time navigation, is the key innovation. It allows the system to accurately and rapidly detect changes in the environment,? explains Maurice Heitz, the manager of the IRPS project and a researcher at French technology firm CS Communication & Systčmes.

The technology not only detects objects with greater accuracy, but unlike camera-based robotic vision systems it is not affected by shadows, rain or fog, and provides angular and distance information for each pixel, making it suitable for use in virtually any environment.

See the full Story via external site: www.physorg.com

Most recent stories in this category (Artificial Intelligence):

03/03/2017: Application of Fuzzy Logic Teaches Drones to land on Moving Targets

02/03/2017: Poker-playing AI program first to beat pros at no-limit Texas hold 'em

05/02/2017: Google's driverless cars make progress

04/02/2017: Study Exposes Major Flaw in Turing Test

31/01/2017: Artificial intelligence uncovers new insight into biophysics of cancer

31/01/2017: Hungry penguins help keep smart car code safe

12/01/2017: First ever perched landing performed using machine learning algorithms

12/01/2017: AI takes on humans in marathon poker game