Isaac Perceptor
Isaac Perceptor is a camera-based 3D perception system for mobile robots. It provides robust odometry together with local 3D scene reconstruction to enable autonomous navigation applications. It supports creating a map from a rosbag and localizing against the created map in order to improve localization quality and maintain a global frame of reference.
The Isaac ROS implementation of Isaac Perceptor is in here.
Isaac Perceptor leverages multiple other Isaac ROS modules:
Isaac ROS Nova for time-synchronized multi-cam data.
Isaac ROS Visual SLAM for GPU-accelerated camera-based odometry.
Isaac ROS Visual Global Localization for GPU-accelerated camera-based global localization.
Isaac ROS DNN Stereo Depth for learning-based stereo-depth estimation.
Isaac ROS Nvblox for GPU-accelerated local 3D scene reconstruction.
Isaac ROS Image Pipeline for GPU-accelerated image processing.
Isaac Perceptor supports running on the following robot platforms and simulation environment:
Isaac Perceptor supports different camera configurations, details please see:
Tutorials
- Tutorial: Stereo Camera Configurations for Isaac Perceptor
- Tutorial: Recording and Playing Back Data for Isaac Perceptor
- Tutorial: Running Isaac Perceptor on Nova Orin Developer Kit
- Tutorial: Running Isaac Perceptor on the Nova Carter
- Tutorial: Running Isaac Perceptor on RGBD Cameras
- Tutorial: Running Isaac Perceptor in Isaac Sim
- Tutorial: Mapping and Localization with Isaac Perceptor
Other Details