Course Project: RoboMind

Project Repository on GitHub

All starter code, documentation, and resources are available on GitHub. Clone the repository to get started immediately!

                        git clone https://github.com/aniskoubaa/introduction_to_ai_course.git
                    

Open Repository

⭐ Star the repo • 👁️ Watch for updates

URGENT: 3-Week Deadline!

You have ONLY 3 WEEKS to complete all 4 phases + report + video. This is an intensive timeline that requires immediate action.

Recommended Schedule:
📅 Week 1: Search Algorithms (Phase 1) - 25 points
📅 Week 2: Logic + Probability (Phases 2 & 3) - 40 points
📅 Week 3: Integration + Documentation (Phase 4 + Report + Video) - 35 points
⚠️ NO EXTENSIONS - START TODAY!

Project Overview

What You'll Build

You will implement a rational AI agent that navigates a 2D grid world using Python and Pygame. Your agent will integrate three key AI reasoning techniques learned in this course:

Search Algorithms (BFS, UCS, A*) - to plan optimal paths
Logical Reasoning (Knowledge Base + Inference) - to reason about the world
Probabilistic Reasoning (Bayes' Rule) - to handle uncertainty

🤖

Intelligent Agent

Plans, reasons, and adapts

🎮

Visual Simulation

Pygame grid world

📈

Performance Analysis

Compare algorithms

Learning Outcomes

By completing this project, you will:

Implement and compare classical search algorithms
Apply propositional logic for automated reasoning
Use Bayesian inference to handle sensor uncertainty
Build a complete rational agent integrating all techniques
Analyze and evaluate agent performance systematically

Project Phases

Timeline: 3 WEEKS ONLY - START IMMEDIATELY!

The project is divided into 4 phases to be completed in just 3 weeks. This is a tight deadline - START TODAY! Focus on getting core functionality working first, then refine.

Search Algorithms

Week 1 • 25 points

Implement three search algorithms to find paths from start to goal.

What to Implement:

BFS - Breadth-First Search (shortest path in steps)
UCS - Uniform Cost Search (lowest cost path)
A* - A* with Manhattan & Euclidean heuristics

Files to Modify:

ai_core/search_algorithms.py
agents/search_agent.py

Test Command:

python main.py --test-search

Logic-Based Reasoning

Week 2 • 20 points

Implement a knowledge base with propositional logic and forward chaining inference.

What to Implement:

Knowledge Base - Store facts and rules
Forward Chaining - Automatic inference
Logic Agent - Reason about safe moves

Files to Modify:

ai_core/knowledge_base.py
agents/logic_agent.py

Test Command:

python main.py --test-logic

Probabilistic Reasoning

Week 2-3 • 20 points

Implement Bayesian belief updates to handle sensor uncertainty and noisy readings.

What to Implement:

Bayes' Rule - P(H|E) calculations
Belief Updates - Handle sensor noise
Probabilistic Agent - Navigate under uncertainty

Files to Modify:

ai_core/bayes_reasoning.py
agents/probabilistic_agent.py

Test Command:

python main.py --test-probability

Hybrid Integration

Week 3 • 20 points

Integrate all three reasoning techniques into a single rational agent.

What to Implement:

Integrated Decision-Making - Combine all techniques
Strategy Selection - Choose appropriate method
Rational Behavior - Optimize performance

Files to Modify:

agents/hybrid_agent.py

Test Command:

python main.py --test-hybrid

AI Usage Policy - READ CAREFULLY

Permitted vs. Prohibited AI Use

This project is designed to assess YOUR understanding of AI algorithms. While AI tools can be helpful, they MUST NOT write your code for you.

✓ ALLOWED: Code Autocompletion

You may use IDE features like GitHub Copilot, TabNine, or similar tools for autocompletion and syntax suggestions. These should complete partial lines or suggest next steps.

✓ ALLOWED: LLM for Guidance & Explanation

You may ask ChatGPT, Claude, or similar LLMs to explain concepts, clarify algorithms, or help you understand errors. Example: "Explain how BFS works" or "Why am I getting this Python error?"

✓ ALLOWED: Debugging Assistance

You may use AI to help debug specific errors or understand why your code doesn't work. Always understand the fix before applying it!

✗ FORBIDDEN: Generating Complete Functions

DO NOT ask AI to "write BFS algorithm" or "implement A* search" and copy the result. This defeats the learning purpose and will be detected.

✗ FORBIDDEN: Copy-Pasting Large Code Blocks

DO NOT copy entire functions, classes, or algorithms from AI assistants, Stack Overflow, GitHub, or other sources without understanding and significantly modifying them.

✗ FORBIDDEN: Submitting AI-Written Code

Any substantial portions of code that are clearly AI-generated (detected by our analysis tools) will result in zero points for that phase and potential academic integrity violations.

AI Detection & Enforcement

We will use:

AI-generated code detection tools
Code analysis agents to identify patterns
Manual review of submissions
Oral examinations if needed

Penalties:

Minor violations: Resubmit with deduction
Extensive AI-generated code: Zero on project
Repeated violations: Academic integrity case
Failure to explain code: Zero on project

How to Use AI Responsibly

Learn first, code second: Understand the algorithm before implementing
Start from scratch: Write your own code structure
Use AI for hints: Not complete solutions
Understand every line: Be able to explain your code
Add personal touches: Use your own variable names, comments, style
Cite when appropriate: If you got a key idea from AI, mention it in comments

Grading Rubric (100 Points)

Component	Points	Criteria
Phase 1: Search	25	• BFS correctness & efficiency (8 pts) • UCS correctness & efficiency (8 pts) • A* correctness & optimality (9 pts)
Phase 2: Logic	20	• Knowledge base implementation (10 pts) • Forward chaining inference (10 pts)
Phase 3: Probability	20	• Bayes' rule implementation (10 pts) • Belief map updates (10 pts)
Phase 4: Integration	20	• Hybrid agent integration (15 pts) • Rational behavior demonstration (5 pts)
Documentation & Presentation	10	• 4-page IEEE report (5 pts) • 2-minute YouTube video demo (3 pts) • GitHub repository organization (2 pts)
Code Quality	5	• Well-commented code (2 pts) • Proper structure & naming (2 pts) • Follows Python conventions (1 pt)
TOTAL	100

Submission Requirements

Three Required Deliverables

You must submit ALL three components to receive credit for the project:

1. Private GitHub Repository

Create a private GitHub repository
Upload your complete RoboMind/ project
Include all Python files with implementations
Add a README with setup instructions
Clean code (remove __pycache__)

⚠️ IMPORTANT:
• Repository must be PRIVATE
• Share access ONLY with instructor:
akoubaa@alfaisal.edu
• Do NOT make your repo public

2. Technical Report (IEEE Format)

4 pages maximum (IEEE format)
Download template: IEEE Conference Template
Include performance graphs and tables
Explain approach for each phase
Discuss results, limitations, challenges
Submit as PDF only

Report Structure:
1. Introduction & Approach
2. Phase 1-4 Implementation
3. Results & Analysis
4. Conclusion & Reflection

3. Demo Video (YouTube)

2 minutes maximum
Upload to YouTube (unlisted or public)
Submit YouTube link
Show your agent in action
Demonstrate all 4 phases working
Brief verbal explanation (optional)

Video Content:
• Screen recording of running agents
• Show BFS/UCS/A* paths
• Show logic/probability reasoning
• Show hybrid agent integration
• Keep it concise and focused

How to Submit

Submit through Blackboard/E-learning portal with:
- Private GitHub repository link (shared with instructor)
- 4-page IEEE format report (PDF)
- YouTube video link (2 minutes max)
Include a cover page with: Name, Student ID, Course (SE444), Project Title
All three components must be submitted by the deadline

Important Dates - TIGHT DEADLINE!

Week 1 Target	Phase 1 (Search) - Get BFS, UCS, A* working
Week 2 Target	Phases 2 & 3 (Logic + Probability) - Complete KB and Bayes
Week 3 Target	Phase 4 (Integration) + Report + Video
⚠️ FINAL DEADLINE	END OF WEEK 3 - Code + Report + Video (NO EXTENSIONS!)

Late submissions will NOT be accepted. Plan accordingly and START IMMEDIATELY!

Important: Final Exam Connection

Part of your final exam will be directly related to this project.

Expect exam questions on:

Your implementation choices and design decisions
Algorithm performance comparison and analysis
How search, logic, and probability integrate
Challenges you faced and how you solved them

Why this matters:

Demonstrates deep understanding of AI concepts
Tests your ability to explain and defend your work
Ensures you actually understand the code you wrote
Connects theory (lectures) with practice (project)

Pro Tip: Keep detailed notes about your implementation process, challenges, and decisions. This will help you both in writing your report and preparing for the final exam.

Get Started

Ready to Begin?

Clone the GitHub repository to get the complete starter code package with all documentation

                        $ git clone https://github.com/aniskoubaa/introduction_to_ai_course.git
                        
                    

View on GitHub Download ZIP Read Documentation

Need Help?

Office Hours:

[Schedule TBD]

Discussion Forum:

[Link TBD]

Email:

[Instructor Email]

Academic Integrity

Zero Tolerance Policy

This project is an individual assignment. Academic dishonesty will not be tolerated.

✓ You MAY:

Discuss high-level concepts with classmates
Ask instructors for clarification
Use course materials and textbooks
Search for algorithm explanations

✗ You MAY NOT:

Share code with other students
Copy code from online sources
Use AI to generate complete solutions
Submit work that is not your own

Consequences of Violations

First offense: Zero on project + academic integrity report
Repeated violations: Failure in course + disciplinary action
Note: All cases are reported to the university

Build Something Intelligent!

This project will challenge you, but it's designed to be achievable with consistent effort.
Start early, test often, and ask for help when needed!