위치추정 알고리즘

입자 필터, 스캔 매칭, 몬테카를로 위치추정, 자세 그래프, 오도메트리

몬테카를로 위치추정과 같은 위치추정 알고리즘과 스캔 매칭은 거리 센서 또는 라이다 측정값을 사용하여 알려진 맵에서 자세를 추정합니다. 자세 그래프는 추정된 자세를 추적하며 모서리 제약 조건과 루프 폐쇄를 기반으로 최적화될 수 있습니다. 동시적 위치추정 및 지도작성에 대한 내용은 SLAM 항목을 참조하십시오.

함수

모두 확장

입자 필터 상태 추정

`stateEstimatorPF`	Create particle filter state estimator
`getStateEstimate`	Extract best state estimate and covariance from particles
`predict`	Predict state of robot in next time step
`correct`	Adjust state estimate based on sensor measurement

스캔 매칭

`matchScans`	Estimate pose between two laser scans
`matchScansGrid`	Estimate pose between two lidar scans using grid-based search
`matchScansLine`	Estimate pose between two laser scans using line features
`transformScan`	Transform laser scan based on relative pose
`lidarScan`	Create object for storing 2-D lidar scan

몬테카를로 위치추정

`monteCarloLocalization`	Localize robot using range sensor data and map
`lidarScan`	Create object for storing 2-D lidar scan
`getParticles`	Get particles from localization algorithm
`odometryMotionModel`	Create an odometry motion model
`likelihoodFieldSensorModel`	Create a likelihood field range sensor model
`resamplingPolicyPF`	Create resampling policy object with resampling settings

자세 그래프

`poseGraph`	2차원 자세 그래프 만들기
`poseGraph3D`	Create 3-D pose graph
`poseplot`	3-D pose plot
`addPointLandmark`	Add landmark point node to pose graph
`addRelativePose`	Add relative pose to pose graph
`edgeNodePairs`	Edge node pairs in pose graph
`edgeConstraints`	Edge constraints in pose graph
`edgeResidualErrors`	Compute pose graph edge residual errors
`findEdgeID`	Find edge ID of edge
`nodeEstimates`	Poses of nodes in pose graph
`optimizePoseGraph`	Optimize nodes in pose graph
`removeEdges`	Remove loop closure edges from graph
`show`	Plot pose graph
`trimLoopClosures`	Optimize pose graph and remove bad loop closures

인자 그래프

`factorGraph`	Bipartite graph of factors and nodes
`factorGraphSolverOptions`	Solver options for factor graph
`importFactorGraph`	Import factor graph from g2o log file
`factorIMU`	Convert IMU readings to factor
`factorGPS`	Factor for GPS measurement
`factorTwoPoseSE2`	Factor relating two SE(2) poses
`factorTwoPoseSE3`	Factor relating two SE(3) poses
`factorPoseSE2AndPointXY`	Factor relating SE(2) position and 2-D point
`factorPoseSE3AndPointXYZ`	Factor relating SE(3) position and 3-D point
`factorIMUBiasPrior`	Prior factor for IMU bias
`factorVelocity3Prior`	Prior factor for 3-D velocity
`factorPoseSE3Prior`	Full-state prior factor for SE(3) pose

휠 인코더 오도메트리

`wheelEncoderOdometryAckermann`	Compute Ackermann vehicle odometry using wheel encoder ticks and steering angle
`wheelEncoderOdometryBicycle`	Compute bicycle odometry using wheel encoder ticks and steering angle
`wheelEncoderOdometryDifferentialDrive`	Compute differential-drive vehicle odometry using wheel encoder ticks
`wheelEncoderOdometryUnicycle`	Compute unicycle odometry using wheel encoder ticks and angular velocity

도움말 항목

Compose a Series of Laser Scans with Pose Changes
Use the matchScans function to compute the pose difference between a series of laser scans.
Minimize Search Range in Grid-based Lidar Scan Matching Using IMU
This example shows how to use an inertial measurement unit (IMU) to minimize the search range of the rotation angle for scan matching algorithms.
Monte Carlo Localization Algorithm
The Monte Carlo Localization (MCL) algorithm is used to estimate the position and orientation of a robot.
Particle Filter Workflow
A particle filter is a recursive, Bayesian state estimator that uses discrete particles to approximate the posterior distribution of the estimated state.
Particle Filter Parameters
To use the stateEstimatorPF (Robotics System Toolbox) particle filter, you must specify parameters such as the number of particles, the initial particle location, and the state estimation method.

추천 예제

Factor Graph-Based Pedestrian Localization with IMU and GPS Sensors

Estimate the position of a pedestrian using logged sensor data from an inertial measurement unit (IMU) and Global Positioning System (GPS) receiver and a factor graph.

라이브 스크립트 열기

Landmark SLAM Using AprilTag Markers

Combine robot odometry data and observed fiducial markers called AprilTags to better estimate the robot trajectory and the landmark positions in the environment. The example uses a pose graph approach and a factor graph approach, and compares the two graphs.

라이브 스크립트 열기

Localize TurtleBot Using Monte Carlo Localization Algorithm

Apply the Monte Carlo Localization algorithm on a TurtleBot® robot in a simulated Gazebo® environment.

라이브 스크립트 열기

Reduce Drift in 3-D Visual Odometry Trajectory Using Pose Graphs

Reduce the drift in the estimated trajectory (location and orientation) of a monocular camera using 3-D pose graph optimization. Visual odometry estimates the current global pose of the camera (current frame). Because of poor matching or errors in 3-D point triangulation, robot trajectories often tends to drift from the ground truth. Loop closure detection and pose graph optimization reduce this drift and correct for errors.

라이브 스크립트 열기