A pre-integrated Isaac ROS perception graph — ESS depth, segmentation, AprilTag pose, and pedestrian detection — packaged as a single Docker image with sample launch files for Jetson AGX Orin and IGX.
Isaac Perception Pack
NVIDIA Isaac ROS perception bundle: depth, segmentation, AprilTag, person detection.
A pre-integrated Isaac ROS perception graph — ESS depth, segmentation, AprilTag pose, and pedestrian detection — packaged as a single Docker image with sample launch files for Jetson AGX Orin and IGX.
- Outdoor inspection robots
- Sidewalk delivery perception
- Cobot safety zones
Brings up the Isaac ROS perception graph (depth + segmentation + AprilTag + pedestrian) on a Jetson Orin device.
- Jetson AGX Orin / Orin NX with JetPack 6.0+
- nvidia-container-toolkit installed and `--runtime nvidia` working
- Camera: Hawk, Realsense D455, or Zed 2i connected over USB3 / GMSL
- 01Pull the perception image
docker pull registry.roslab.ai/isaac-perception:2.1.0-jp6 - 02Run the container with GPU + camera access
docker run --rm -it --runtime nvidia --network host \ -v /dev:/dev --privileged \ registry.roslab.ai/isaac-perception:2.1.0-jp6 - 03Launch the graph
Starts ESS depth, segmentation, AprilTag and pedestrian nodes.
ros2 launch roslab_isaac_perception full_graph.launch.py camera:=realsense - 04Inspect outputs in Foxglove
ros2 topic list | grep -E '/depth|/seg|/apriltag|/pedestrian'
Depth at ≥30 FPS, segmentation at ≥15 FPS — check with the bundled perf script.
ros2 run roslab_isaac_perception perf_reportA hardened ROS 2 Nav2 distribution with behavior-tree recoveries, multi-floor map switching, costmap plugins for dynamic obstacles, and Foxglove-ready telemetry. One-command deploy to any ROS 2 Humble or Jazzy robot.
Production-tuned ROS 2 Nav2 stack with BT-based recovery and multi-floor maps.
A library of MoveIt 2 task plans for bin picking, kitting and machine tending. Ships with calibration routines for Franka FR3, UR-series and legacy OEM arms, plus a skill-runner that exposes each routine as a ROS 2 action.
Drop-in MoveIt 2 skills: bin picking, kitting, machine tending — calibrated per arm.
A π0 vision-language-action grasping policy fine-tuned on 200k teleop episodes, served as a ROS 2 action with a runtime safety envelope (force, workspace, timeout). Bring your own parallel or suction gripper.
Pre-trained π0 grasping policy with ROS 2 skill server and safety envelope.