Choice of ROBOTICS

Nowadays, image processing is omnipresent in information technologies: medicine, biology, agriculture, entertainment, culture, measurement, mechanics...

Image processing consists of applying mathematical transformations to images in order to modify their appearance or to extract information from them. More generally, image processing aims to manipulate the underlying information contained in an image. If it has long been achieved through electronic circuits, image processing is nowadays almost exclusively done digitally, ie via algorithms programmed generally with an imperative language (C, C++, Java, Python, ...).

This course aims to provide a solid foundation in image processing. It covers image formation and acquisition, color transformations, morphological operations, geometric transformations, compression, frequency transformations, recognition and matching techniques, ... and an introduction to deep learning methods. The courses are complemented by support videos.

The teaching unit is mainly composed of 11 didactic courses dealing with the basics in the main fields of image processing and 3 practical work sessions whose subjects are to be chosen among 6 proposals. The students can choose to carry out the work on images that they bring corresponding to their field of training.

See full page

The module will cover the following:

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

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

See full page

The module will cover the following:

• Introduction to robotics: history, types of robots, serial and parallel mechanisms, applications
• Components (sensors and actuators)
• Generation of trajectories (in the articular and operational spaces)
• Geometric models direct/inverse, Kinematic model direct/inverse
• Kinematic control and singularities
• Problems and applications in mobile robotics
• Non-autonomous models: unicycle, bicycle, car
• Sensors and odometry
• Localization by rangefinder and data fusion (Kalman filter)
• Mapping (homogeneous transformations and ICP)
• Navigation (pose control, path following)

Practical work: implementation of the acquired knowledge on a real robot (either a manipulator arm or a robot with wheels), ROS programming with git and python.

See full page