NVIDIA-ISAAC-ROS/isaac_ros_dnn_inference

NVIDIA-accelerated DNN model inference ROS 2 packages using NVIDIA Triton/TensorRT for both Jetson and x86_64 with CUDA-capable GPU

52
/ 100
Established

This helps robotics engineers and developers integrate high-performance AI perception into their robotic systems. It takes raw sensor data like camera images and, using pre-trained deep neural networks, outputs real-time insights such as detected objects (e.g., people bounding boxes) or segmented areas. This is designed for professionals building autonomous robots, industrial automation, or other intelligent machines that need to understand their environment quickly.

130 stars.

Use this if you need to run deep learning models for perception tasks like object detection or segmentation on a robotic platform using ROS 2, and require NVIDIA GPU-accelerated performance.

Not ideal if your robotics application does not use ROS 2, you lack access to NVIDIA GPUs, or you are looking for a tool to train deep learning models rather than deploy them.

robotics computer-vision autonomous-systems perception industrial-automation
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

130

Forks

17

Language

C++

License

Apache-2.0

Last pushed

Feb 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA-ISAAC-ROS/isaac_ros_dnn_inference"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.