Skip to content
View het915's full-sized avatar
🤖
🤖

Highlights

  • Pro

Block or report het915

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. 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
het915/README.md
Image
01001000 01100101 01110100  00100000  01010000 01100001 01110100 01100101 01101100

Het Patel

Robotics Engineer & AI Researcher

Building intelligent autonomous systems that navigate, perceive, and act in the real world.


Website Email LinkedIn YouTube Twitter


Typing SVG


$ cat about.txt

class HetPatel:
    def __init__(self):
        self.location    = "Urbana-Champaign, IL"
        self.education   = "MS Autonomy & Robotics — UIUC"
        self.prev        = ["ISRO", "Samsung PRISM", "VIT University"]
        self.interests   = [
            "Vision-Language-Action Models",
            "Visual SLAM & Semantic Mapping",
            "6D Object Pose Estimation",
            "Edge AI & Real-Time Inference",
            "Humanoid Locomotion & Planning",
        ]
        self.building    = "VLA models for commercial robot navigation"
        self.open_to     = "Robotics roles & collaborations — Spring 2026"

    def philosophy(self):
        return "If it doesn't work in the real world, it doesn't work."

Impact Areas

Space

Satellite systems & mission ops at ISRO

Construction

Autonomous surveying & real-time SLAM

Conservation

Wildlife monitoring drones in Kaziranga

Healthcare

AR + robotics for mobility assistance


Featured Work

Humanoid Loco-Manipulation

Language-guided task execution on humanoid robots using VLA models and whole-body control in OmniGibson simulation.

ROS2 Isaac Sim PyTorch VLA

6D Pose Estimation

Language-guided zero-shot 6D object pose tracking achieving 88.31% ADD-S AUC using SAM-3 + foundation models.

Python OpenCV SAM-3 CUDA

Autonomous Navigation Stack

Full SLAM pipeline with <15cm localization drift — sensor fusion across LiDAR, RGB-D, and IMU on mobile robots.

ROS2 C++ Nav2 LiDAR

Solar Panel Cleaning Robot

Autonomous maintenance robot achieving 45% water reduction through intelligent path planning and coverage optimization.

Arduino OpenCV Python CAD


Tech Stack

Domain Technologies
Core C++ Python C MATLAB
Robotics ROS2 Gazebo OpenCV Arduino CUDA
AI / ML PyTorch TensorFlow scikit-learn NumPy Pandas
Infra AWS Docker Linux Git CMake

GitHub Analytics

Image    Image



Image



Image

Image

Contribution Graph

github-snake


"If it doesn't work in the real world, it doesn't work."

Interested in robotics, autonomy, or building something that matters?

Let's Talk Portfolio


Profile Views



Image

Pinned Loading

  1. OpenWorld-6DPose OpenWorld-6DPose Public

    Pose Estimation

    Python 1 1

  2. Adaptive_Vehicle_Control_Based_on_Pedestrian_Behavior Adaptive_Vehicle_Control_Based_on_Pedestrian_Behavior Public

    Forked from SunnyDeshpande/av-pedestrian-motion-prediction

    GEM Project by Team AutoShield for UIUC Fall '25 ECE484 Principles of Safe Autonomy

    C++

  3. T1_K1_Booster_Robot T1_K1_Booster_Robot Public

    C++ 1 1