Use localization and pose estimation algorithms to orient your vehicle in your environment. Sensor pose estimation uses filters to improve and combine sensor readings for IMU, GPS, and others. Localization algorithms, like Monte Carlo localization and scan matching, estimate your pose in a known map using range sensor or lidar readings. Pose graphs track your estimated poses and can be optimized based on edge constraints and loop closures. For simultaneous localization and mapping, see SLAM.
|Orientation from accelerometer, gyroscope, and magnetometer readings|
|Height and orientation from MARG and altimeter readings|
|Orientation estimation from a complementary filter|
|Orientation from magnetometer and accelerometer readings|
|Orientation from accelerometer and gyroscope readings|
|Create inertial navigation filter|
|Estimate pose from asynchronous MARG and GPS data|
|Estimate pose from IMU, GPS, and monocular visual odometry (MVO) data|
|Estimate pose from MARG and GPS data|
|Estimate pose with nonholonomic constraints|
|Localize robot using range sensor data and map|
|Create object for storing 2-D lidar scan|
|Get particles from localization algorithm|
|Create an odometry motion model|
|Create a likelihood field range sensor model|
|Create resampling policy object with resampling settings|
This example shows how to use 6-axis and 9-axis fusion algorithms to compute orientation.
This example shows how to align and preprocess logged sensor data.
This example shows how to use spherical linear interpolation (SLERP) to create sequences of quaternions and lowpass filter noisy trajectories.
This example shows how you might fuse sensors at different rates to estimate pose.
matchScans function to compute the pose difference between a series of laser scans.
A particle filter is a recursive, Bayesian state estimator that uses discrete particles to approximate the posterior distribution of the estimated state.
To use the
stateEstimatorPF particle filter, you must specify parameters such as the number of particles, the initial particle location, and the state estimation method.
The Monte Carlo Localization (MCL) algorithm is used to estimate the position and orientation of a robot.
This example shows how to reduce the drift in the estimated trajectory (location and orientation) of a monocular camera using 3-D pose graph optimization.