Skip to content
View abubakar1107's full-sized avatar
πŸ’­
A curious Student
πŸ’­
A curious Student

Block or report abubakar1107

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
abubakar1107/README.md

Hi there, I'm Abu! πŸ‘‹

πŸš€ AI/ML Engineer | Deep Learning & Computer Vision | 3D Perception | Multimodal AI

πŸš€ About Me

  • πŸŽ“ Master's in Robotics from University of Maryland, College Park
  • πŸ€– Specializing in Deep Learning, Perception & Multimodal AI
  • πŸ† Passionate about Autonomous Vehicles, Transformers, & 3D Object Detection
  • 🌍 Open to collaborations, research, and industry projects

πŸ”₯ Current Work

πŸ”­ Currently Working On:

  • Building an Agentic AI system that can simulate court trails.. (hell yeah! I'm building an AI Harvey spectre)

πŸ› οΈ Tech Stack & Skills

  • Programming: Python, C++, MATLAB
  • Frameworks: PyTorch, TensorFlow, OpenCV, Open3D, TIMM, Hugging Face
  • Tools & Simulators: ROS, CARLA, Gazebo, Webots, MoveIt
  • Domain Expertise: Deep Learning, Perception, SLAM, Path Planning

πŸ“Œ Featured Projects

πŸš€ Multimodal Alignment Model for LiDAR & Image Data

πŸ”— Repo Link
πŸ”Ή Tech: Python, PyTorch, Open3D, Hugging Face
πŸ”Ή Description: Designed a transformer-based alignment model to bridge LiDAR & RGB image data. Utilized PointNet++ and ViT encoders to unify embeddings.

πŸ“‘ Transformers for 3D Object Detection in LiDAR Point Clouds

πŸ”— Repo Link
πŸ”Ή Tech: Python, PyTorch, Open3D, CUDA
πŸ”Ή Description: Custom transformer-based 3D object detection model for LiDAR data, leveraging PointNet++ embeddings & a custom loss function.

🌎 3D Reconstruction of AV Environments using Vectorized Kernel Mixtures

πŸ”— Repo Link
πŸ”Ή Tech: PyTorch, Open3D, CARLA, PCPNet
πŸ”Ή Description: Built a 3D environment reconstruction pipeline achieving 92% reduction in compute time over baseline methods.

πŸ“· Structure from Motion & Visual NeRF Implementation

πŸ”— Repo Link
πŸ”Ή Tech: OpenCV, SciPy, PyTorch
πŸ”Ή Description: 3D reconstruction & rendering pipeline using SfM & Tiny NeRF for photorealistic view synthesis.

🏎️ Fuzzy Adaptive RRT*N Path Planning in CARLA

πŸ”— Repo Link
πŸ”Ή Tech: Python, Path Planning, CARLA
πŸ”Ή Description: Implemented FA-RRT*N algorithm, achieving an 84% decrease in planning time for AV navigation.


πŸ“Š GitHub Stats

GitHub Stats
GitHub Streak
Top Languages



πŸ”₯ Always open to new opportunities & collaborations. Let’s build something amazing together! πŸš€

Pinned Loading

  1. Fuzzy-Adaptive-RRT-N-path-planning-and-control-of-Autonomous-Vehicle-in-CARLA Fuzzy-Adaptive-RRT-N-path-planning-and-control-of-Autonomous-Vehicle-in-CARLA Public

    This project implements a Fuzzy Adaptive RRT*N algorithm for autonomous vehicle path planning in CARLA. By integrating fuzzy logic with RRT*N, the vehicle adapts dynamically to obstacles and traffi…

    Python 15

  2. Multimodal-alignment-modal-for-Lidar-and-Image-data Multimodal-alignment-modal-for-Lidar-and-Image-data Public

    Aligns LiDAR point clouds and RGB images for autonomous systems using PointNet++, Vision Transformer, and a Q-Former-inspired module. Trained on the KITTI dataset, it generates unified embeddings w…

    Python 7

  3. 3D-reconstruction-of-Autonomous-Vehicle-environment-using-Vectorized-kernel-Mixtures 3D-reconstruction-of-Autonomous-Vehicle-environment-using-Vectorized-kernel-Mixtures Public

    **3D Reconstruction of an Autonomous Vehicle’s Environment Using VecKM** This project leverages the VecKM method for efficient 3D reconstruction of autonomous vehicle environments using point cloud…

    Python

  4. 3D-Building-Reconstruction-with-Structure-from-Motion-and-Neural-Radiance-Fields 3D-Building-Reconstruction-with-Structure-from-Motion-and-Neural-Radiance-Fields Public

    This project combines classical computer vision and modern deep learning techniques to reconstruct a building's 3D structure. We used Structure from Motion (SfM) with Fundamental/Essential matrix c…

    Python