Didactic material for the course of Robotic Perception and Action – 2019/20
Introduction
Mobile Robotics
(note in the italian versione there are some notes of the teacher)
Point to Point Path Planning in chained form
Exercises in Maple:
- General slides
- Polynomial inputs maple pdf and maple file
- Piecewise constant inputs maple pdf and maple file
- Double steering driving wheels maple pdf
- Optmization methods for chained form A
- Optmization methods for chained form B
Global methods for Path Planning
- Path Planning and Control with Potential Fields
- Path Planning with A* and Elastic Bands
- + Matlab file to try with A* and Elastic Bands
Simultaneous Location And Mapping – SLAM
Sensors and Sensor Fusion
Sensors
- Introduction
- Incremental sensors
- Environment Referred Sensors
- Depth sensors – Kinect
- Intro to Sensor Fusion
Sensor Fusion
- Sensor Fusion in Frequency: Complementary Filtering
- Statistical Sensor Fusion
- Machine learning
- Exercise on sensor Fusion
- Work in Class (presentation);
- Data and Functions – Vectorial Sensor Fusion simulating eye tracker’s data fusion
- Second set of data + Transformation Matrixes between the different acquisitions (not wrt the ground). A sequence of 14 ToF images and 3D points while approaching toward the laboratory door
Additional material
The following are lessons not given in 2018 but useful to understand in deep the SVD and PCA tools:
- Tutorial on PCA and SVD
- Lesson 1 – SVD
- Lesson 2 – SVD applications
- Lesson 3 – PCA on Data Vector Matrix
- Lesson 4 – SVD and PCA
- Lesson 5 – SVD for Rigid Motion Estimation
Mixed Reality
Software
General material on Unity and C#
State Machine
Unity Projects
- First Project: Introduction on c#
- Roll a Ball Game
- Wall Game
- State Machine – First part
- State Machine – Second part
- State Machine – Final
- Simplified State Machine
Blender