Open Source Robotics

精選高品質的開源機器人專案、工具與軟體,推動機器人社群向前發展。

Introduction to Mobile Robotics

  • 提供者: University of Freiburg
  • 講師: Prof. Dr. Wolfram Burgard
  • 程度: intermediate
  • 形式: video-lectures
  • 時長: One Semester
  • 類別: mobile-robotics
  • 語言: English
  • 價格: 免費
  • 標籤: mobile-robotics, SLAM, probabilistic-robotics, Kalman-filter, particle-filter, Bayes-filter, localization, mapping

一門全面的大學課程,涵蓋行動機器人的基本概念與技術。主題包括輪式移動、感測器、機率推理、貝氏濾波器、卡爾曼濾波器、粒子濾波器與 SLAM。課程強調以機率論明確表示不確定性,將感知視為狀態估計,將行動視為效用最佳化。由基礎教科書 Probabilistic Robotics 的共同作者 Prof. Wolfram Burgard 講授。完整的講義投影片與練習均可免費取得。

為何值得修讀

Taught by Wolfram Burgard — co-author of 'Probabilistic Robotics,' the definitive textbook in the field — this course provides the theoretical foundations that underpin virtually every mobile robot navigation system in use today. From autonomous cars to warehouse robots to delivery drones, the probabilistic techniques taught here are essential. The complete lecture materials are freely available.

你將學到

  • Probabilistic state estimation using Bayes filters
  • Kalman filters for robot localization with Gaussian uncertainty
  • Particle filters for non-linear, non-Gaussian estimation problems
  • Simultaneous Localization and Mapping (SLAM) fundamentals
  • Sensor models for range finders, cameras, and odometry
  • Motion models for wheeled and differential-drive robots

課程大綱

A full semester course with freely available lecture slides and exercises. Begins with robot motion models and sensor characteristics, then builds the probabilistic framework starting from Bayes filters through Kalman filters and particle filters. Applies these tools to localization, mapping, and SLAM. Covers both theoretical derivations and practical implementation considerations.

核心主題

  • Wheeled locomotion and odometry
  • Sensors for mobile robots: LiDAR, cameras, IMUs
  • Probabilistic reasoning and Bayes rule
  • Bayes filter framework
  • Kalman filter and Extended Kalman Filter (EKF)
  • Particle filters and Monte Carlo Localization
  • Occupancy grid mapping
  • SLAM: EKF-SLAM and Graph-based SLAM
  • Motion planning and path planning

先備知識

  • Linear algebra and matrix operations
  • Basic probability and statistics
  • Calculus (derivatives, integrals)
  • Some programming experience helpful for exercises

適用對象

  • Robotics students focusing on mobile robots and autonomous navigation
  • Engineers building autonomous vehicles, drones, or mobile platforms
  • Researchers needing a solid foundation in probabilistic robotics
  • ROS developers wanting to understand the algorithms behind navigation stacks

連結

  • 網站: http://ais.informatik.uni-freiburg.de/teaching/ss21/robotics/

本網站需要 JavaScript 才能正常運作。請啟用 JavaScript 以瀏覽我們的開源機器人專案。