Aaryan Agrawal
← All projects

6-DoF Pose Estimation of Packaged Foods

NVIDIA Isaac ROS 2 · DOPE

ROS 2 on Linux · Coordinate Transformations · Model Validation & Testing · Computer Vision

Developed a real-time computer vision system for robotic manipulation using NVIDIA's DOPE algorithm and Isaac ROS 2. As the lead researcher, implemented an end-to-end pipeline from RGB camera input to 6-DoF pose estimation, achieving sub-5cm accuracy suitable for robotic grasping. Conducted comprehensive evaluation using industry-standard metrics with ground truth validation from optical tracking systems, demonstrating practical viability for autonomous manipulation applications.

Model inference in Rviz2 on ROS 2
Model inference in Rviz2 on ROS 2
Quaternions visualized in MATLAB
Quaternions visualized in MATLAB
Optical tracker POV for ground truth
Optical tracker POV for ground truth
RGBD camera POV for model inference
RGBD camera POV for model inference