Like it often does, Google has released into the open-source community an indoor mapping tool called Cartographer that it has used internally.
Cartographer is designed to enable what is known as real-time simultaneous localization and mapping (SLAM)—or the ability to build a 2D or 3D map while at the same time keeping track of an individual or robotic agent’s location within that map.
The algorithms used in SLAM combine data from various sensors such as Light Detection and Ranging (LIDAR) systems and cameras to determine the position of an object within an environment and to map that environment.
SLAM is used widely in technologies such as autonomous vehicles, robotic vacuum machines, automated forklifts and drones, a trio of Google engineers said in a blog post this week.
“Cartographer builds globally consistent maps in real time across a broad range of sensor configurations common in academia and industry,” they said.
At Google, the technology has powered several applications including those for mapping transit hubs and museums and for enabling new visualizations of major buildings, the engineers said.
Google introduced Cartographer two years ago as a backpack equipped with SLAM technology. At the time, the company had described Cartographer as a mapping tool that would let a backpack wearer do things like walk inside a building and generate a floor plan for the structure in real time.
“As fast as you can walk, you can map with Cartographer,” Google has said when it introduced the technology. The company had touted Cartographer as enabling the creation of detailed floor plans for major buildings in a matter of hours. The company likened Cartographer to an indoor version of its Street View technology for creating highly detailed images of an individual’s surroundings inside a building.
Google has since integrated Cartographer with the Robot Operating System (ROS), which is software for building robotics application. The support for ROS has made Cartographer ready for use in robotic platforms ranging from the Toyota Human Support Robot, TurtleBot personal robot kits and the Revo LDS laser scanner, according to the three engineers.
Google’s efforts with Cartographer currently are heavily focused on LIDAR SLAM, they added.
The focus is not surprising considering the fact that LIDAR systems play a critical role in the autonomous vehicle technology that Google has been developing and testing for several years. The LIDAR system installed on the roof of the autonomous vehicles is critical to their ability to detect and avoid obstacles in their path.
Along with Cartographer, Google this week also released some three years’ worth of LIDAR and other sensor-based data sets collected from its backpackers. “Our focus is on advancing and democratizing SLAM as a technology” through collaborative development and community contributors, said the engineers.