Robotics Practical 1

Uitgebreide vaknaam	Robotics Practical 1
Leerdoelen	At the end of the course, the student is able to: 1) Design, implement, and experiment a velocity control for a real unicycle mobile robot in a lab environment. 2) Design, implement, and experiment a (linear and non-linear) pose control for a unicycle mobile robot in a lab environment. 3) Design, implement, and experiment an autonomous vision-based navigation control for a unicycle mobile robot to follow a line by using a real RGB camera in a lab environment. 4) Design, implement, and experiment an autonomous vision-based navigation control for a unicycle mobile robot to react to signs by using a deep learning method for the recognition of the signs based on real RGB camera images in a lab environment. 5) Design, implement, and experiment an overall system behavior in which a real unicycle mobile robot follows a line and react to signs in a lab environment.
Omschrijving	The students gain basic knowledge on the low- and high-level control of a unicycle mobile robot (mobile base, RGB camera) in a real lab environment. Students focus on: -A low-level velocity control for the robot. Students learn: 1) Kinematic model of the unicycle robot; 2) Velocity estimation of the robot from wheel’s encoders; 3) PID control for the robot’s velocity; 4) Implementation of the velocity control on the Teensy development board. Tools: ROS, Python, C++ (for Arduino). -A low-level pose control for the robot. Students learn: 1) Basic Lyapunov stability analysis of the unicycle robot; 2) Linear and non-linear control for the robot’s pose; 3) To implement the pose control on the Teensy development board. -A control algorithm for the autonomous navigation of the robot by using the camera in lab experiments. Students learn: 1) To process camera images (collect images with the camera while the robot drives in the environment, design a color-based filter to detect the lines in the environment and to eliminate invalid information); 2) To design/implement a vision-based control so that the robot follows a line; 3) To implement the vision-based control on the NVIDIA® Jetson Nano board. -A deep learning method for the sign recognition by using the camera in lab experiments. Student learn: 1) To process camera images (collect images with the camera while the robot drives in the environment, design a color- and shape-based filter to detect the sign, crop the region-of-interest in the images, create a data-set of the cropped images); 2) To design a convolutional neural network for sign recognition; 3) To implement the network on the NVIDIA® Jetson Nano board. Tools: TensorFlow, Keras, OpenCv. -An overall robot's behavior in lab experiments. Students learn: 1) To build a control architecture for the robot’s behavior (follow a line, react to signs) and organize it in a state machine; 2) To develop well-structured software; 3) To work with a real a real robot. Tool: Git.
Uren per week
Onderwijsvorm	Hoorcollege (LC), Opdracht (ASM), Practisch werk (PRC)
Toetsvorm	Opdracht (AST), Verslag (R) (The final report grade should be above or equal to 5. The final assignment grade should be above or equal to 5. The final weighted grade (30% report + 70% assignment) should be at least 5.5. This course has mandatory presence: At least 75% of the lectures/tutorials/practical work is mandatory, which implies that missing more than 25% results in failure of the course.)
Vaksoort	bachelor
Coördinator	prof. dr. R. Carloni
Docent(en)	prof. dr. R. Carloni
Verplichte literatuur	Titel Auteur ISBN Prijs Introduction to Autonomous Mobile Robots, The MIT Press, 2004 (available online) R. Siegwart and I.R. Nourbakhsh Lecture notes, tutorial instructions.
Entreevoorwaarden	Mandatory: Autonomous Systems. Strongly recommended: Calculus for Artificial Intelligence, Linear Algebra and Multivariable Calculus Recommended: Signals and Systems, Neural Networks, Statistics, Imperative Programming Prior knowledge of Python, Git, C/C++ is useful, but not required. If the mandatory requirements are not met, only the Board of Examiners of the AI BSc may grant an exemption. Exchange students are assumed to have gone through this through their Learning Agreement; pre-master's students through the Board of Admissions - other external students are judged case-by-case.
Opmerkingen	This course unit has a capacity limit. More information about capacity-limit courses can be found here. This course has an intended limit of 78 participants. Artificial Intelligence (BSc) is a Fixed Quota (Numerus Fixus) programme. As a consequence, their courses (course code WBAI) are closed for students that are not registered under the AI BSc programme, unless the course is part of the mandatory curriculum of their programme. If you wish to take this course in your minor – or as part of a so-called ‘unofficial’ pre-master’s – please use the official procedure through the Board of Examiners form.
Opgenomen in	Opleiding Jaar Periode Type BSc Artificial Intelligence 3 semester II a keuzegroep A BSc Artificial Intelligence 2 semester II a keuzegroep A