Kimera2: Robust and Accurate Metric-Semantic SLAM in the Real World

Abstract¶

We present improvements to Kimera, an open-source metric-semantic visual-inertial SLAM library. In particular, we enhance Kimera-VIO, the visual-inertial odometry pipeline powering Kimera, to support better feature tracking, more efficient keyframe selection, and various input modalities (eg monocular, stereo, and RGB-D images, as well as wheel odometry). Additionally, Kimera-RPGO and Kimera-PGMO, Kimera's pose-graph optimization backends, are updated to support modern outlier rejection methods - specifically, Graduated-Non-Convexity - for improved robustness to spurious loop closures. These new features are evaluated extensively on a variety of simulated and real robotic platforms, including drones, quadrupeds, wheeled robots, and simulated self-driving cars. We present comparisons against several state-of-the-art visual-inertial SLAM pipelines and discuss strengths and weaknesses of the new release of Kimera. The newly added features have been released open-source at https://github.com/MIT-SPARK/Kimera.

Summary¶

Updates Kimera into a more robust and practical metric-semantic SLAM stack by improving feature tracking, keyframe selection, input modality support, and robust pose-graph and mesh optimization. The paper is useful as both a system paper and a real-world evaluation of Kimera across drones, quadrupeds, wheeled robots, and driving-style settings.

Links¶

Tags¶

Similar Papers¶