Skip to content
View djetshu's full-sized avatar
5 followers · 6 following

Block or report djetshu

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
djetshu/README.md

Banner

👋 About Me

Hello! I'm Daffer Queque, an experienced (3+ years) Robotics Software Engineer and AI developer specializing in autonomous vehicles, computer vision, ROS, machine learning, sensor integration, and navigation systems.

🚀 Selected Projects

Project 1: Grasslammer Autonomous Robot for Agriculture 4.0

Project 1 GIF

Description: Deployed YOLO NAS on Jetson Orin AGX with TensorRT FP16 in ROS2, achieving 24 FPS, 0.97 mAP, 0.89 Precision, 0.93 Recall. Enhanced with C++ for 2D to 3D conversion and EKF SLAM. Represented Politecnico di Milano at the 2024 Field Robotic Event in Germany. Github

Project 2: Wireless All-Terrain Robot for Autonomous Tunnel Inspection and Digitization

Project 2 GIF

Description: Led Level 3 autonomous navigation in GPS-denied underground galleries using RGB, thermal cameras, and 3D LIDAR with ROS and C++. Implemented YOLO V8 and YOLO NAS on Jetson Orin AGX, achieving 0.91 mAP and 30 FPS. Showcased the system at PERUMIN 2023, an international mining fair. Videos

🛠️ Skills

  • Programming Languages: Python, C++.
  • Robotics Frameworks: ROS 1/2 (Robot Operating System), Gazebo, NAV1/2, Isaac Sim Nvidia.
  • AI Frameworks: Pytorch, Tensorflow.
  • Tools and Technologies: Git, Docker, Jupyter.
  • Operating Systems: Ubuntu, Windows.

📫 Contact Me

Pinned Loading

  1. yolonas_trt_ros2 yolonas_trt_ros2 Public

    This repository provides a ROS2 package integrating YOLONAS with TensorRT for high-performance, real-time object detection using custom models. Easily configure input topics and models, and visuali…

    Python

  2. yolo_nas_trt_training yolo_nas_trt_training Public

    Anaconda environment to train YOLONAS, to convert yolonas.onnx to TensorRT model and to test it with webcam in real time.

    Jupyter Notebook

  3. Quadruped-AllTerrain-Robot Quadruped-AllTerrain-Robot Public

    This repository focuses on the development of a quadruped robot with 4 legs, designed for increased agility and towing capacity. It highlights the hermetic IP67 and scalable mechanical design, alon…

    8 1