Expand description
SLAM algorithms for the RustRobotics workspace.
Re-exports§
pub use ekf_slam::EKFSLAMState;pub use icp_matching::ICPResult;pub use icp_matching::ICPTraceFrame;pub use lidar_graph_slam::LidarGraphSlam;pub use lidar_graph_slam::LidarGraphSlamConfig;pub use lidar_graph_slam::LoopClosure;pub use robust_icp::RobustICPResult;pub use robust_icp::RobustIcp2D;pub use robust_icp::Transform2D;pub use scan_to_map::MatchStatus;pub use scan_to_map::ScanToMapConfig;pub use scan_to_map::ScanToMapMatcher;pub use scan_to_map::ScanToMapUpdate;
Modules§
- bundle_
adjustment - Pinhole reprojection factors and dense bundle adjustment.
- carmen
- CARMEN log reader for 2D laser datasets (e.g. the Intel Research Lab and Freiburg logs of the Kümmerle et al. SLAM benchmark).
- correlative_
scan_ matching - Brute-force correlative scan matching.
- dataset
- Loaders for the EuRoC MAV and KITTI odometry dataset layouts.
- dynamic_
filter - Flags LiDAR points on moving objects (people walking by) so they stay out of scan matching and the map.
- ekf_
slam - fastslam1
- fastslam2
- FastSLAM 2.0
- frontier_
exploration - Frontier-based exploration (Yamauchi, 1997) on an
OccupancyGrid. - g2o
- Minimal g2o SE(2)/SE(3) pose-graph text I/O.
- geometric_
icp - Point-to-line and point-to-plane ICP using the shared robust optimizer.
- graph_
based_ slam - icp_
matching - Iterative Closest Point (ICP) SLAM implementation
- imu_
preintegration - Bias-aware IMU preintegration with covariance propagation.
- lidar_
graph_ slam - 2D LiDAR graph SLAM: scan-to-map odometry plus loop closure.
- lidar_
loop_ scenario - Deterministic corridor-loop scenario for
LidarGraphSlam. - lidar_
mcl - Monte Carlo localization of a 2D LiDAR in a known occupancy grid.
- lidar_
occupancy - Log-odds occupancy grid built from LiDAR scans at known poses, e.g. the
node scans of
crate::lidar_graph_slam::LidarGraphSlamat their optimized poses. - pose_
graph_ optimization - 2D pose graph optimization with Gauss-Newton iteration.
- pose_
graph_ optimization_ 3d - SE(3) pose-graph optimization on the shared factor-graph backend.
- robust_
icp - Robust ICP with Gauss-Newton optimization and Huber loss
- scan_
to_ map - Scan-to-map 2D LiDAR odometry with a bounded local submap.
- slam_
benchmark - Relative-pose SLAM metric of Kümmerle et al., “On measuring the accuracy of SLAM algorithms” (Autonomous Robots, 2009).
- vio_
pipeline - Offline visual-inertial pipeline built from the shared estimation modules.
- visual_
frontend - Decoder-independent sparse visual frontend for EuRoC-style sequences.