ROBOTICS selection

Nowadays, image processing is ubiquitous in information technology: medicine, biology, agriculture, entertainment, culture, measurement, mechanics, etc.

Image processing involves applying mathematical transformations to images in order to modify their appearance or extract information from them. More generally, image processing aims to manipulate the underlying information contained in an image. While it has long been performed using electronic circuits, image processing is now carried out almost exclusively digitally, i.e., using algorithms generally programmed with an imperative language (C, C++, Java, Python, etc.).

This teaching unit aims to provide a solid foundation in image processing. It covers, among other things, image formation and acquisition, colorimetric transformations, morphological operations, geometric transformations, compression, frequency transformations, recognition and matching techniques, and an introduction to deep learning methods. The courses are supplemented by supporting videos.

The teaching unit consists mainly of 11 lectures covering the basics of the main areas of image processing and three practical sessions, with topics to be chosen from six proposals. Students can choose to carry out the work on images they bring in that are relevant to their field of study.

See the full page

The module will cover the following points:

• Introduction to the Git version control system
• Introduction to ROS middleware for building robotic applications
• Modularization of a robotic application

Practical work: Implementation of a ROS application, testing on a simulator, and verification on a real robot

See the full page

The module will cover the following points:

• Introduction to robotics: history, types of robots, serial and parallel mechanisms, applications
• Components (sensors and actuators)
• Trajectory generation (in joint and operational spaces)
• Direct/inverse geometric models, direct/inverse kinematic model
• Kinematics control and singularities
• Issues and applications in mobile robotics
• Non-holonomic models: unicycle, bicycle, car
• Sensors and odometry
• Location by rangefinder and data fusion (Kalman filter)
• Mapping (homogeneous transformations and ICP)
• Navigation (positioning control, path tracking)

Practical work: applying acquired knowledge to a real robot (either a manipulator arm or a wheeled robot), ROS programming with Git and Python.

See the full page