Skip to content
View Dartayous's full-sized avatar

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report Dartayous

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 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
Dartayous/README.md

Dartayous Hunter — Computer Vision / Digital Twin / Robotics Simulation Engineer (NVIDIA Ecosystem Track)

OpenUSD Omniverse Isaac Sim Python Digital Twin Simulation

Building production-ready Digital Twin systems using:

  • OpenUSD
  • Omniverse
  • Isaac Sim
  • Simulation + Robotics + Synthetic Data

Core Skills

  • OpenUSD + Omniverse (Advanced)
  • Robotics Simulation (Isaac Sim)
  • Perception Systems (Camera + LiDAR)
  • Synthetic Data Pipelines
  • AI Decision Systems (Cosmos-ready)

→ Full Skills Matrix: [Digital Twin Engineer Skills Matrix]

My learning approach:

Build → Break → Debug → Understand

Portfolio Projects

OpenUSD Foundations

🔹 Omniverse OpenUSD Scene Construction Demo
OpenUSD scene graph, instancing, lighting, and physics in Omniverse

🤖 Robotics Simulation

Franka Pick and Place Demo

🔹 Isaac Sim Franka Pick & Place
→ Physics-based manipulation pipeline

🔹 AI Digital Twin Camera Agent (Navigation) → AI-driven camera agent that performs target detection and lock-on inside an OpenUSD digital twin environment using perception-based logic.

Synthetic Data / Computer Vision

🔹 Synthetic Data Generation Pipeline
OpenUSD + Replicator pipeline for generating labeled datasets

🔹 Real-time Digital Twin Lighting Omniverse Real-time digital twin office environment built in NVIDIA Omniverse using OpenUSD, focused on lighting, materials, and scene composition.

🔹 Real-time Computer Vision Simulation to Detection Pipeline Real-time digital twin environment built in NVIDIA Omniverse using OpenUSD, focused on computer vision, materials, and pipeline.

Pipeline Engineering

🔹 OpenUSD Pipeline Tool
Python-based tool for USD stage manipulation, transform control, and variant authoring

🔹 Cosmos Ready Digital Twin Evaluation Pipeline Isaac Sim digital twin evaluation pipeline with telemetry-aware run packaging, simulated Cosmos Predict outputs, and dual-mode Cosmos Reason integration.

Current Focus

  • Building real-world → USD digital twin environments
  • Advancing robotics + perception pipelines
  • Strengthening OpenUSD pipeline engineering skills

Tech Stack

  • OpenUSD (USD composition, variants, instancing)
  • NVIDIA Omniverse
  • Isaac Sim
  • Python (pipeline tooling + simulation)
  • Synthetic Data (Replicator)

Career Goal

To work on:

  • Digital Twin systems
  • Robotics simulation
  • NVIDIA Omniverse / Isaac ecosystem
  • Simulation-driven AI systems

Connect with me

What I’m Doing Right Now

Building Multiple Digital Twin / Robotics Simulation Projects to develop an impressive and robust demo reel.

Pinned Loading

  1. computer-vision-simulation-to-detection-pipeline computer-vision-simulation-to-detection-pipeline Public

    Built an end-to-end computer vision pipeline using NVIDIA Omniverse Replicator and Detectron2, generating synthetic datasets from a digital twin environment, converting annotations to COCO format, …

    Python

  2. ai-digital-twin-camera-agent ai-digital-twin-camera-agent Public

    AI-driven camera agent that performs target detection and lock-on inside an OpenUSD digital twin environment using perception-based logic.

    Python

  3. isaacsim-franka-pick-place isaacsim-franka-pick-place Public

    Isaac Sim robotics demo implementing a physics-based pick-and-place pipeline with interpolated motion and stable grasp control

    Python

  4. synthetic-data-generation-pipeline synthetic-data-generation-pipeline Public

    Synthetic data pipeline using OpenUSD and Omniverse Replicator to generate labeled datasets for computer vision workflows

  5. real-time-digital-twin-lighting-omniverse real-time-digital-twin-lighting-omniverse Public

    Real-time digital twin office environment built in NVIDIA Omniverse using OpenUSD, focused on lighting, materials, and scene composition.

  6. cosmos-ready-digital-twin-evaluation-pipeline cosmos-ready-digital-twin-evaluation-pipeline Public

    Isaac Sim digital twin evaluation pipeline with telemetry-aware run packaging, simulated Cosmos Predict outputs, and dual-mode Cosmos Reason integration.

    Python