Main Content


Navigation Toolbox 入門


Navigation Toolbox™ は、運動の計画、位置推定とマッピングの同時実行 (SLAM)、慣性ナビゲーションのためのアルゴリズムと解析ツールを提供します。このツールボックスには、カスタマイズ可能な探索とサンプリングベースのパスプランナー、およびパスの検証と比較に使用するメトリクスが含まれています。SLAM マップ ビルダー アプリにより、2 次元および 3 次元マップ表現を作成し、SLAM アルゴリズムを使用してマップを生成し、マップの生成を対話的に可視化してデバッグすることができます。このツールボックスには位置推定用のセンサー モデルとアルゴリズムが含まれています。IMU、GPS、およびホイール エンコーダーのセンサー データのシミュレーションと可視化を行い、マルチセンサー姿勢推定用のフュージョン フィルターを調整することができます。

自動運転、ロボット工学、家電製品のアプリケーション向けの参考例が提供されています。ナビゲーション アルゴリズムをハードウェアに直接展開して (MATLAB® Coder™ または Simulink® Coder を使用)、このアルゴリズムをテストできます。


  • Rotations, Orientation, and Quaternions

    This example reviews concepts in three-dimensional rotations and how quaternions are used to describe orientation and rotations. Quaternions are a skew field of hypercomplex numbers. They have found applications in aerospace, computer graphics, and virtual reality. In MATLAB®, quaternion mathematics can be represented by manipulating the quaternion class.

  • Introduction to Simulating IMU Measurements

    This example shows how to simulate inertial measurement unit (IMU) measurements using the imuSensor (Sensor Fusion and Tracking Toolbox) System object. An IMU can include a combination of individual sensors, including a gyroscope, an accelerometer, and a magnetometer. You can specify properties of the individual sensors using gyroparams (Sensor Fusion and Tracking Toolbox), accelparams (Sensor Fusion and Tracking Toolbox), and magparams (Sensor Fusion and Tracking Toolbox), respectively.

  • Estimate Position and Orientation of a Ground Vehicle

    This example shows how to estimate the position and orientation of ground vehicles by fusing data from an inertial measurement unit (IMU) and a global positioning system (GPS) receiver.

  • Estimate Robot Pose with Scan Matching

    This example demonstrates how to match two laser scans using the Normal Distributions Transform (NDT) algorithm [1]. The goal of scan matching is to find the relative pose (or transform) between the two robot positions where the scans were taken. The scans can be aligned based on the shapes of their overlapping features.

  • Plan Mobile Robot Paths Using RRT

    This example shows how to use the rapidly exploring random tree (RRT) algorithm to plan a path for a vehicle through a known map. Special vehicle constraints are also applied with a custom state space. You can tune your own planner with custom state space and path validation objects for any navigation application.

  • Implement Simultaneous Localization And Mapping (SLAM) with Lidar Scans

    This example demonstrates how to implement the Simultaneous Localization And Mapping (SLAM) algorithm on a collected series of lidar scans using pose graph optimization. The goal of this example is to build a map of the environment using the lidar scans and retrieve the trajectory of the robot.

  • Perform SLAM Using 3-D Lidar Point Clouds

    This example demonstrates how to implement the simultaneous localization and mapping (SLAM) algorithm on collected 3-D lidar sensor data using point cloud processing algorithms and pose graph optimization. The goal of this example is to estimate the trajectory of the robot and create a 3-D occupancy map of the environment from the 3-D lidar point clouds and estimated trajectory.


Navigation Toolbox の概要
Navigation Toolbox でサポートされている各種の機能について学ぶ