NavigationHardware: MaxRoadmap scaffold
ReMEmbR long-horizon memory
Remember-and-reason navigation across long mission horizons.
Lab runtime / NavigationOK / VIS-01
ReMEmbR long-horizon memory runs against the same observable edge stack used for testing and deployment.
This entry is a roadmap scaffold, not a finished demo. Its description records intended scope; the linked repository is the source of truth for current code.
About this demo
Memory-augmented navigation: the robot builds a persistent semantic map and answers queries like 'where did you last see my keys?' using LLM-grounded retrieval. Inspired by Abrar Anwar's Jetson AI Lab Research Group talk.
Highlights
- →Persistent semantic memory
- →LLM query interface
- →Episodic + semantic store
- →Works across multi-day deployments
Supported robots
Indoor mobile robots
Related demos
View all →Navigation
Missions
Multi-waypoint autonomous patrols with a state-machine orchestrator.
Open demo →NavigationNVBlox 3D mapping
Isaac-ROS volumetric mapping with TSDF + ESDF for navigation.
Open demo →NavigationVisual SLAM (GPS-denied)
Real-time stereo + IMU SLAM for indoor and drone navigation.
Open demo →