Over the past few years, I’ve been fortunate enough to work on a diverse range of projects that have shaped my journey as a software engineer. From machine learning experiments to autonomous driving simulation, each project has taught me something unique and helped me grow both technically and personally.

🚗 The CARLA Driving Simulator Client

Repository: carla-driving-simulator-client

This is probably my most ambitious project to date. The CARLA Driving Simulator Client is a modular, open-source client for the CARLA simulator that features realistic vehicle control, sensor management, dynamic environments, and a web-based interface for monitoring and control.

What Makes This Project Special

  • Realistic Vehicle Control: Implementing physics-based vehicle control systems
  • Sensor Fusion: Integrating multiple sensor types (LIDAR, cameras, GPS)
  • Web Interface: Real-time monitoring and control through a React-based dashboard
  • Dockerized Deployment: Complete containerization for easy deployment
  • CI/CD Pipeline: Automated testing and deployment workflows

Key Learnings

This project taught me the complexities of autonomous driving simulation and the importance of real-time data processing. Working with sensor fusion, implementing physics-based controls, and building a responsive web interface for monitoring were all challenging but rewarding experiences.

Technologies Used: Python, React, FastAPI, Docker, PostgreSQL, CARLA

😊 Face Mood Analyzer

Repository: face-mood-analyzer

An AI-powered emotion analyzer that detects faces in photos, analyzes emotions, and generates corresponding music. This project combines computer vision, deep learning, and audio generation.

Project Highlights

  • Face Detection: Using advanced computer vision techniques
  • Emotion Recognition: Deep learning models for emotion classification
  • Music Generation: AI-generated music based on detected emotions
  • Web Interface: Flask-based application for easy interaction

What I Discovered

Working on this project opened my eyes to the power of AI and how different technologies can be combined to create something truly innovative. The integration of computer vision with audio generation was particularly fascinating.

Technologies Used: Python, Flask, TensorFlow, PyTorch, DeepFace

⚡ Go Task Queue v2

Repository: GoTaskQueue_v2

A high-performance task queue system built in Go, designed for distributed computing and concurrent task processing. This project explores the power of Go’s concurrency model.

Why Go?

Go’s goroutines and channels make it perfect for building concurrent systems. This project was an exploration of how to build scalable, high-performance applications using Go’s unique concurrency patterns.

Key Features

  • Concurrent Processing: Leveraging Go’s goroutines for parallel task execution
  • Distributed Architecture: Designed for scalability across multiple nodes
  • Performance Optimization: Focused on high-throughput task processing
  • Resource Management: Efficient memory and CPU utilization

Technologies Used: Go, Concurrency Patterns, Distributed Systems

🧠 Machine Learning Experiments

GPU Classification

Repository: GPU-Classification

A project focused on classifying GPUs based on various parameters with hyperparameter optimization for improved accuracy. This was my first deep dive into machine learning model development.

CPU Classification

Repository: CPU-Classification-RFC-DTC-SVM

Exploring different machine learning algorithms (Random Forest, Decision Trees, SVM) for CPU performance classification. This project helped me understand the strengths and weaknesses of different ML approaches.

ML Learnings

These projects taught me the importance of:

  • Data Preprocessing: Clean data is crucial for good model performance
  • Feature Engineering: Creating meaningful features from raw data
  • Model Selection: Understanding when to use which algorithm
  • Hyperparameter Tuning: The art of optimizing model parameters

📝 Question Paper Creator

Repository: QuestionPapaerCreator

An automated question paper creation system built in C# for educational institutions. This project combined software development with educational technology.

Educational Impact

This project showed me how software can directly impact education and learning. Building tools that help educators create better assessments was both challenging and rewarding.

Technologies Used: C#, .NET, Document Generation

🌐 Personal Website

Repository: akshay.chikhalkar.com

This website you’re currently reading! Built with Hugo and the PaperMod theme, it’s a testament to the power of static site generators.

Why Hugo?

  • Speed: Generates sites in milliseconds
  • Simplicity: Focus on content, not complexity
  • Performance: Static sites are fast and reliable
  • Flexibility: Easy to customize and extend

🏠 Homelab Adventures

Beyond GitHub, I’ve been building a comprehensive homelab setup that includes:

  • Proxmox VE for virtualization
  • Docker Compose for service orchestration
  • Home Assistant for smart home automation
  • Grafana + Prometheus for monitoring
  • Pi-hole for network-wide ad-blocking

This homelab has been my playground for learning infrastructure management, automation, and self-hosting.

Key Takeaways from My Project Journey

1. Diversity Breeds Growth

Working across different technologies (Python, Go, C#, React) has given me a broader perspective on software development. Each language and framework has its strengths, and understanding multiple approaches makes you a better developer.

2. Real-World Applications Matter

Projects like the CARLA simulator and face mood analyzer have real-world applications. This makes the work more meaningful and helps you understand the impact of your code.

3. Learning Never Stops

From machine learning to autonomous driving simulation, there’s always something new to learn. Each project has pushed me out of my comfort zone and taught me something valuable.

4. Open Source is Powerful

All my projects are open source, and this has taught me the importance of documentation, clean code, and community collaboration.

5. Infrastructure Matters

My homelab projects have taught me that understanding infrastructure and deployment is just as important as writing good code.

What’s Next?

I’m constantly working on new projects and experiments. Some areas I’m exploring:

  • Advanced ML/AI: More sophisticated deep learning models
  • Edge Computing: Bringing AI to edge devices
  • Distributed Systems: Scaling applications across multiple nodes
  • DevOps Automation: Streamlining deployment and monitoring

Connect and Collaborate

I’m always open to collaboration and learning from others. Feel free to:

The journey of a thousand miles begins with a single commit. 🚀

What projects are you working on? I’d love to hear about your journey too!