Skip to content
View melihysk's full-sized avatar

Highlights

  • Pro

Block or report melihysk

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
melihysk/README.md

Hi there, I'm Melih! 👋

Robotics Software Engineer | Autonomous Mobile Robots (AMR/AGV) | ROS 2 & SLAM

I am a senior Computer Engineering student specializing in autonomous navigation, SLAM, and fleet management for industrial robotics.

I focus heavily on bridging the gap between low-level hardware kinematics (especially non-standard drive types) and high-level autonomous behaviors using ROS 2.

🔭 Current Focus & Professional Work

I am currently working long-term at Modoya, focusing on the autonomy of forklift-type AMRs and retrofitting manual electric forklifts into fully autonomous vehicles.

  • Natural SLAM & Sensor Fusion: Developing robust mapping, localization, and navigation pipelines by fusing raw 2D LiDAR data, IMU, and wheel odometry.
  • Scan Matching & Odometry: Testing, evaluating, and implementing advanced laser odometry packages for industrial environments (KISS-ICP, Kinematic-ICP, RF2O, laser_scan_matcher).
  • Advanced Kinematics: Developing custom ROS 2 controllers for tricycle drive structures, specifically handling the unique steering and translation kinematics of forklift AMRs.
  • Simulation & Optimization: Conducting rigorous offline tests via rosbags, managing complex TF trees (odom -> base_link -> map), and validating Nav2 performance in custom simulated environments before real-world deployment.

🚀 Featured Projects & Experience

  • TEKNOFEST AGV Development (Team Captain): Built an AGV from scratch on Ubuntu 22.04 with ROS 2 Humble (Raspberry Pi 4). Successfully implemented an odom-less mapping pipeline using Cartographer, configured Nav2 for autonomous navigation, and developed a .NET web-based GUI for control. Reached the finals for two consecutive years.
  • Multi-AMR Task Management System: Developed a centralized fleet management simulation in CoppeliaSim using Python/C++. Implemented A* path planning, 2D LiDAR grid mapping, and a Greedy algorithm for dynamic task assignment. Built a custom PyQt5 GUI for fleet monitoring.
  • Fleet Management & Protocols: Contributed to swarm robotics research, focusing on multi-robot communication protocols and industrial standards like VDA5050 and Open-RMF.
  • Industrial AMR Deployment: Gained hands-on experience in field deployment, localization mapping, and fleet software integration. Engineered an autonomous door-passing module by integrating an ESP-based relay with the fleet management system via Modbus-TCP.

🛠️ Tech Stack & Skills

  • Robotics Frameworks: ROS 2 (Humble), Nav2, Cartographer, Open-RMF, VDA5050
  • Odometry & SLAM: KISS-ICP, Kinematic-ICP, RF2O, Sensor Fusion (EKF/UKF)
  • Languages: C++, Python, .NET (for UI development)
  • Simulation & Tools: CoppeliaSim, Gazebo, Git, Linux (Ubuntu), Bash Scripting
  • Hardware: Raspberry Pi, ESP/Microcontrollers, 2D LiDAR (YDLidar), IMU, Modbus-TCP

📫 Let's Connect!

Pinned Loading

  1. OffsetTricycleRobotSimulation OffsetTricycleRobotSimulation Public

    An autonomous robot simulation in Gazebo with a custom ros2_control controller for offset tricycle kinematics.

    C++

  2. TaskAllocationInMulti-RobotSystems TaskAllocationInMulti-RobotSystems Public

    CoppeliaSim simülasyon ortamında çalışan, Python tabanlı çoklu robot görev atama ve otonom navigasyon sistemi

    Python

  3. AutomatedGuidedVehicle AutomatedGuidedVehicle Public

    C++

  4. Graduation-Project-2026 Graduation-Project-2026 Public

    ROS 2 tabanlı çok robotlu depo simülasyonunda üç farklı trafik yönetimi algoritmasının karşılaştırılması

    Python

  5. CupSealingMachine CupSealingMachine Public

    Otomatik çalışan bir bardak kapatma makinesinin kontrolü sağlanır

    C++