Training datafor underwaterautonomy
A public-data MVP for underwater autonomy. USIM video, IMU, depth, and control aligned for VLA training.
Two live replays
SLAM plus the USIM training-data pipeline.
SLAM replay
Raw · SAM2 · ORB · VOUnderwater AI lacks training data
Underwater data is mostly mapping data. Policies need perception plus action.
Underwater datasets today
Capture what pilots already do
Validate on USIM now. Design the same row contract for future ROV black-box traces.
Static dashboard first; real telemetry stays separate until a trace exists.
View demoA topside tap records MAVLink traffic without modifying the ROV or interrupting the pilot.
Streams become uniform rows with scaled PWM commands and consistent action vectors.
Physics labels and ACT-style action chunks export to static JSON first.
Ingest → align → label → export
Raw ROV streams in. Model-ready chunks out.
Smooth control sequences
Exports smoothed future-action chunks as fixed [k, 6] tensors.
Sydney Harbour after the USIM spine
Add paired optical and Oculus FLS sonar after the static USIM demo works.
No human annotator for hydrodynamics
Derives labels like fighting_current from command vs. IMU response.
MVP scope from idea.md
Prove the tokenization path on public USIM data. Keep the dashboard static. Add real MAVLink and sonar only when the source traces exist.
Who needs this data
One dataset format for defense, inspection, and research teams.
Policies for current, turbidity, and acoustic sensing.
Resident autonomy needs better pilot-derived data.
Benchmarks for policies, not just perception.
Data and policy, not another OS
Incumbents sell tools. We build the missing training layer.
Navigation OS and sensor integration. A VLA policy can sit above it.
Mission planning says where to go. Policies handle how to move.
Rules miss edge cases; pilot data captures them.
Work with Aronnax Labs
Built from the Bow Capital x UCSD StartBlue MVP blueprint. Open for pilot conversations and data access.
Teams building attritable underwater platforms that need robust autonomy software.
Inspection and IRM contractors looking to cut vessel days and pilot load.
Operators who can host passive capture hardware during routine missions.
Marine and oceanographic groups benchmarking underwater autonomy, not just mapping.