Visual SLAM and Cartographer

Sensor fusion greatly improves the accuracy and reliability of maps of large spaces.

We develop, contribute to and integrate proprietary and Open Source libraries for Visual SLAM, LiDAR-based SLAM, 2D and 3D based SLAM.

In robotics, SLAM is used to get mobile robot position information in indoor or GNSS denied environments.

Large space mapped with visual slam and LiDAR using cartographer

SLAM Blockers

However, most SLAM implementations get stuck on either (or all) of these three blockers:

Initial map creation

All SLAM implementations use an algorithm to match the current map features with previously seen features. Although many videos on the internet show this in action, many engineers have a hard time to trigger this condition and sometimes have to give up. The amount of parameters and combinations makes it very hard to find a stable configuration without expert knowledge.

Long term map stability

Even if an initial map can be created, a second effect then kicks in which is the aging of the map features, meaning, the features seen a long time ago are no longer present in the environment. So in changing environments, remapping must be done on a regular basis, but this will deteriorate the quality of the initial map if not done properly.

Localisation accuracy

SLAM algorithms have to calculate the current position and orientation by comparing the features detected by the sensors with those in the previously built map. This calculation can not be done with absolute accuracy due to noise in the measurements. This is worsened the more you deviate from a previously mapped path.

How we help

We have vast experience with these conditions in various SLAM frameworks. We use and improve:

  • Our proprietary VSLAM stack capable of sensor fusing IMU, LiDAR, Odometry, 2D and 3D camera images.
  • ORBSLAM-2 and ORBSLAM-3 Monocular, Stereo and RGB-D Slam Library
  • Maplab and the Rovioli frontend
  • Cartographer for LiDAR-based map building and localization
  • NVIDIA cuVSLAM Stereo Visual SLAM based Localization
Get support here!

Learn more from our blog

NVIDIA Isaac ROS In-Depth: cuVSLAM and the DP3.1 Release

NVIDIA's Isaac ROS software stack continues to evolve, with the DP3 .1 release bringing significant improvements to its Visual SLAM (Simultaneous Localization and Mapping) capabilities. Here’s a review of what we found.

Read NVIDIA Isaac ROS In-Depth: cuVSLAM and the DP3.1 Release

NVIDIA Isaac ROS in under 5 minutes

The NVIDIA Isaac Robot Operating System (ROS) is a collection of hardware-accelerated packages that make it easier for ROS developers to build high-performance solutions on NVIDIA hardware.

Read NVIDIA Isaac ROS in under 5 minutes

How to map large indoor spaces with Google Cartographer

In this blog post, we'll be taking a deep dive into how to map large indoor spaces using Google Cartographer. We'll cover why you might want to use Cartographer and how to tune it for your specific needs. By the end of this post, you should have a basic understanding of what Cartographer needs and how to get started using it in your own projects.

Read How to map large indoor spaces with Google Cartographer