The project aims to introduce students to the development of autonomous agents using different paradigms of artificial intelligence. It was a key evaluation point of the Artificial Intelligence for Autonomous Systems course in the CSE undergraduate program of ISEL.
The project is divided into three main parts, each focusing on a different type of agent: reactive, deliberative using state space search, and deliberative using Markov Decision Processes. The environment is a 2D grid with fixed dimensions that can be configured to add or retract complexity. The agent moves in four directions (up, down, left, right) and can detect obstacles and objects in its vicinity. Agents are evaluated based on their performance in avoiding obstacles and targeting objects.
 |
|---|
| Environment Example |
Important
This overview is a brief summary of the project. For a more detailed explanation, please refer to the Project Report, which contains a comprehensive analysis of the project's development, technical documentation, and results. Be aware that the report is written in Portuguese.
Each following agent has a short embedded demonstration video showcasing its behavior in the environment in a specific configuration.
reactive.mp4
delib-pee.mp4
delib-pdm.mp4
- Clone the repository:
- Install:
- Python 3.11 or higher (check with
python --version) - Pygame (install with
pip install pygame)
- Python 3.11 or higher (check with
- Activate the type of agent you want to run by commenting/uncommenting the corresponding line in the
iasa49428/iasa_agente/src/teste.pyfile. - Navigate to the project's
iasa_agentedirectory. - Run the following command to start the simulation:
set PYTHONPATH=src;src\lib python src/teste.py
Instituto Superior de Engenharia de Lisboa
BSc in Computer Science and Engineering
Artificial Intelligence for Autonomous Systems
Summer Semester of 2023/2024