stc
Course 4: Self-driving Car & AI-based Navigation
Workshop Series | Ages: 14+
Total course cost: 50€
14+
120 minutes/Seminar
Nikos Zourtsanos, Dimitris Piperidis
02/02, 09/02, 16/02, 23/02, 09/03 time 15:45 – 17:45
Course 4 falls under the workshop series Self-driving Cars & AI and focuses on the analysis, explanation and synthesis of algorithms for:
- Basic automations in road networks
- Recognition of traffic signs using neural networks and visual data
- Autonomous navigation with obstacle avoidance
- Expert systems for decision-making in road networks
Note: Participation in Cycle 4 does not require completion of the other cycles of the project.
Course 4 consists of the following sessions:
Seminar 1: General Cycle Description and Introduction to Basic Automations
General description of Cycle 4. Brief introduction to the Python programming language. Description of the problem of autonomous navigation in a controlled road network. Explanation and implementation of basic automations in controlled road networks.
Seminar 2: Recognition of Traffic Signs Using Neural Networks
Introduction to the artificial neuron (perceptron) and multilayer neural networks. Methodology for training a neural network using camera data. Implementation of a neural network for recognizing traffic signs and traffic lights using TensorFlow/Keras libraries. Testing the neural network in a simulated environment.
Seminar 3: Algorithms for Autonomous Navigation and Obstacle Avoidance
Introduction to grid-based maps and optimal route-finding. Basics of obstacle detection and avoidance using camera data. Programming and implementation of an intelligent algorithm for safe autonomous navigation.
Seminar 4: Autonomous Navigation in Road Networks
Introduction to expert systems. Design of an expert system for decision-making in road networks. Implementation and experimental testing of the expert system.
Seminar 5: Experimental Operation of the Complete System
Integration of the expert system with the autonomous navigation algorithm. Testing the complete system in a simulated environment. Experimental trials of the complete system.
References - Supplementary Material
- https://www.python.org/
- https://jupyter.org/
- https://www.tensorflow.org/
- https://www.w3schools.com/python/
- https://www.learnpython.org/
- https://www.pythontutorial.net/
- Neural Network
- Graph_Theory
- D3 Grath Theory
- Algorithm Α*
- Python Eperta
- CoppeliaSim Manual
stc