What failed?
The fault that was injected, when, and what the robot was doing at that moment. A robot that died mid-haul is labeled differently from one that died parked.
Haul1 died at 130 s on its way to T5.
AUTON generates simulated data of multi-robot fleets failing and recovering. It is for teams training and testing fleet software and robot world models.
Simulated in NVIDIA Isaac Sim 6.2 on PhysX bodies. No physical robot or real site is shown.
A simulated shift is only useful as data if you know what went wrong in it. Each run AUTON returns carries a label that says so in plain terms, and in a form a training pipeline can read.
The fault that was injected, when, and what the robot was doing at that moment. A robot that died mid-haul is labeled differently from one that died parked.
Haul1 died at 130 s on its way to T5.
The fleet software decision that noticed it, the one that answered it, and, when the software caused the failure itself, the decision at the root. Each one is numbered and logged with the options it had.
Caught 6.0 s later from missed heartbeats. Its task went to Haul2.
Whether the displaced work was finished, how long that took, which robots were lost along the way, and how much later the shift ended than the same shift with no fault.
Yes. 16 of 16 tasks finished, 41 s later than the fault-free shift.
There is no integration to build before you can see data from your own site.
The robot types you run, a map of the site, and the list of tasks a shift has to get through.
Each shift gets one to three faults at seeded times: the kind that stop real fleets.
Use the set to train a coordination policy or a world model, or run it as a test suite before a release.
yard-radio-drop
Radio link dropped for 40 s
Robot presumed down after 2.5 s
T4 done twice, 41 s wasted
These are real runs from the generator, drawn as a site plan. Pick one, scrub through it, and read the label it produced. Yellow marks what was injected. The fleet software never sees the yellow.
Loading this run…
0.0 of 0 s
A fault changes a robot, the radio link or the site. The fleet software only sees symptoms: missing heartbeats, a robot that says it is driving but is not moving, an obstacle someone drove up to. That gap between what happened and what was known is what the labels measure.
| Fault | What is changed | What the coordinator can see | Injected | Detected | Median time to detect | Fleet recovered | Replay |
|---|---|---|---|---|---|---|---|
| Robot dies mid-taskA robot loses power and stops where it is, for the rest of the shift. | Drive actuators and the telemetry link, both cut at the same instant | Heartbeats stop; the body stays in place as an obstacle | 1,434 | 99% | 6.0 s | 48% | |
| Robot immobilizedThe drive fails or the robot bogs down. It still reports, but it cannot move. | Drive actuators only; telemetry keeps flowing | Reported position stops changing while the robot says it is driving | 888 | 96% | 8.1 s | 51% | |
| Degraded driveThe robot keeps working at a fraction of its normal speed. | Drive speed limit | Progress along the route falls behind the nominal rate | 924 | 85% | 5.1 to 5.2 s | 84% | |
| Tool failureOne tool stops working (bucket, bed, scanner). The robot can still drive. | The tool for one named capability | The robot reports a tool fault after its next attempt to use that tool | 1,002 | 100% | 2.0 s | 62% | |
| Intermittent dropoutThe robot freezes and goes silent for a while, then comes back on its own. | Drive actuators and telemetry together, for a fixed window | A heartbeat gap; the robot later reappears and reports again | 944 | 87% | 6.0 s | 77% | |
| Dropped radio linkThe radio link drops. The robot keeps working on its last order; the coordinator hears nothing. | Telemetry and command delivery, both directions | Heartbeats stop while the robot is in fact still moving and working | 1,287 | 96% | 6.0 s | 81% | |
| Blocked pathSomething lands in a lane: a dropped pallet, a spoil heap, a parked vehicle. | The site: a new rigid obstacle that is not on anyone's map | A robot senses it when it comes within range, then reports it | 1,276 | 100% | 0.0 to 17.8 s | 54% | |
| Head-on in a laneTwo robots are sent through the same single-lane aisle from opposite ends at the same time. | Two relocation orders released together at opposite mouths of one aisle | Both robots report that they are blocked by the other | 1,243 | 100% | 6.0 s | 74% |
Percentages are over faults that had any effect on the shift. Recovered means every task the fault displaced was finished, any deadlock it caused cleared, and the shift completed. The mix includes four coordinator policies, one of them with no deadlock breaker, so these are not the scores of a tuned system. A sampled blockage always lands at the midpoint of a lane, which in the warehouse is often on a pick face; that placement rule pulls the blocked-path figure down.
Some failures are the fleet software's own doing: a deadlock from two route choices, or a task done twice because a silent robot was written off too early. Those are traced to one decision, and the shift is replayed with only that decision changed. In 4,366 such replays, the incident went away 3,676 times. The label records which.
For coordination policies: every decision is logged with the state it was made in, the alternatives on the table, and what happened next. For world models: rendered frames come with the ground truth for that instant, including which robot is broken and how.
The same seeded shifts can be run again against a new version of your fleet software. A regression shows up as specific shifts that used to recover and now do not, each with the decision that changed.
The large campaigns run on simple moving bodies because that is fast. To see whether a label holds up under contact, slope and wheel slip, the same fleet software and the same fault schedule also drive articulated robots in NVIDIA Isaac Sim. The two do not always agree, and the table says where.
PhysX articulations rendered with RTX in Isaac Sim 6.2.0 on one L40S, headless. Footage plays at 12 times shift speed; the simulation itself ran at 1.9 times real time while rendering.
| Measure | Kinematic bodies | PhysX in Isaac Sim |
|---|---|---|
| Shift outcome | complete | complete |
| Tasks done | 16/16 | 16/16 |
| Time to finish | 374.9 s | 381.1 s |
4 of 7 schedules agree across the two backends on outcome, tasks done, detection path and recovery. Times differ because PhysX robots accelerate, turn on the spot and slip. In this run the worst body tilt was 6.1° and the closest two robots came was 0.46 m.
Read these before you rely on a number from this page.
A site map, the robot types you use and a typical task list are enough to produce a first labeled set for your operation. We would like to hear what breaks for you today.
Contact Qamba Labs