Teaching

1. Mobile Robots (2022-now)

This is an undergraduate level course with 2 credits and 32 hours study. This introductory course covers essential elements and algorithms necessary to build and control a mobile robot. It includes both lecture and lab components. The core content of this course covers: 

• key components and kinematics of mobile robots

• path planning and trajectory following

• sensing

• localization, mapping & SLAM

• modeling and control of mobile robots with CoppeliaSim and ROS (Lab)

• building environmental map with Gmapping (Lab)

• navigation with ROS move_base using Dijkstra and DWA (Lab)

2. Fundamentals of Control Engineering (2020-now)

This is an undergraduate level course with 3 credits and 48 hours study. This course contains theoretical part with 42 hours study, and lab part with 6 hours study. This theoretical part is also divided into two parts: Complex variable functions and integral transformations (10 study hours, Crash course) & Control theory (32 study hours). The main content of the course covers:

• complex variable functions and their integration

• series and residues

• Fourier transform and Laplace transform

• mathematical model of control system

• time domain analysis of LTI system

• frequency domain analysis of LTI system (Nyquist & Bode plots)

• stability analysis of LTI system (Routh, Nyquist & Bode criteria)

• correction of LTI system (PID etc.)

Course materials (in Chinese, including slides and homeworks) are shared on Baidu NetDisk at:

link: https://pan.baidu.com/s/1IKtepQ85CZfTRPraAoqFkA , code: b9ee

3. Robot Programming (Introduction to ROS) (2023-now)

This is a graduate level course for course-based Master students with 2 credits and 32 hours study. This is a practical course in which students learn how to use various components offered by Robot Operating System (ROS) to control their robots. The core content of this course covers: 

• robot modeling and simulation (gazebo and coppeliasim)

• ROS common communications (topic, client & server, action)

• coordinate transform and ROS TF

• localization, mapping and navigation (ROS navigation stack) 

• Visualization in ROS (RViz & rqts)

• control of robot manipulator (MoveIt)

• case studies (navigation of mobile robot, autonomous pesticide spray robot, autonomous feeder robot etc.)

4. Agricultural Robots (2023-now)

This is a graduate level course for research-based Master and PhD students with 2 credits and 32 hours study. This course focuses on the common sensing, localization, mapping, and navigation methods adopted by most of agricultural robots. The core content of this course covers: 

• deep learning methods for visual perception (detection, semantic and instance segmentation)

• deep learning methods for 3D point cloud (segmentation, aligning and completion)

• deep learning methods for speech recognition and production (wav2vec, tacotron2)

• localization and mapping (extended Kalman filter, particle filter and graph based SLAM etc.)

• autonomous navigation (path and trajectory planning)

• case studies (autonomous pesticide spray robot, autonomous feeder robot etc.)