Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2018/2019

Robot Vision

Login to KOS for course enrollment Display time-table
Code Completion Credits Range Language
B3B33VIR Z,ZK 4 2p+2l Czech
Corequisite:
Safety in Electrical Engineering for a bachelor´s degree (BEZB)
Basic health and occupational safety regulations (BEZZ)
Lecturer:
Karel Zimmermann (guarantor)
Tutor:
Karel Zimmermann (guarantor), Teymur Azayev, Tomáš Petříček
Supervisor:
Department of Cybernetics
Synopsis:

Course learn to apply the machine learning methods and optimization algorithms on known robotics problems such as metrical or semantic mapping from RGB-D data or reactive motion control. The focus of the subject lies in teaching deep learning methods. Students employ the elementary knowledge of optimization and linear algebra such as robust solutions of overdetermined systems of nonlinear equations or gradient minimization methods. Most of the exercises are devoted to the individual solution of the semester work.

Requirements:
Syllabus of lectures:

1 Overview and lecture outline

2 Sensors that can see I (RGB camera and its calibration)

3 Sensors that can see II (depth from stereo, structured light and solid-state lidar)

4 Mapping (correspondence in RGBD data, 3D reconstruction, voxel map creation)

5 Classification

6 Neural networks, backpropagation

7 Convolutional and recurrent neural networks + backpropagation

8 Application of deep neural networks (detection, segmentation, maskRCNN, Yolo, ..)

9 Introduction to TensorFlow I

10 Introduction to TensorFlow II

11 Generative Adversarial Networks, Cascaded Refinement Networks, Style Transfer Networks, GTA,

12 Reinforcement Learning in Robotics (Imitation Learning, GAIL, RL, Actor-Critic, AI-gym, applications)

13 Presentation of semestral work

Syllabus of tutorials:

During labs, students will work on individual semestral works.

Study Objective:
Study materials:

Thrun S., Burgard W., Fox D. Probabilistic robotics, MIT Press, 2006

Šonka M., Hlavác V., Boyle R.: Image processing, analysis, and machine vision, Cengage Learning, Toronto, 2015.

Note:
Further information:
https://cw.fel.cvut.cz/b181/courses/b3b33vir/start
Time-table for winter semester 2018/2019:
06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon
roomKN:E-301
Zimmermann K.
14:30–16:00
(lecture parallel1)
Karlovo nám.
Šrámkova posluchárna K9
roomKN:E-301
Petříček T.
Azayev T.

16:15–17:45
(lecture parallel1
parallel nr.101)

Karlovo nám.
Šrámkova posluchárna K9
Tue
Fri
Thu
Fri
Time-table for summer semester 2018/2019:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2019-03-21
For updated information see http://bilakniha.cvut.cz/en/predmet4675106.html