Several robots building one map. Each robot drifts in its own frame, so the team has to find where their maps overlap (inter-robot loop closures), agree on a common frame, and merge, over links that are slow, lossy and sometimes absent.
Pipeline
- Each robot runs its own SLAM.
- Robots exchange something small enough to send: place descriptors, object maps, scene graphs.
- A candidate match between two robots’ data becomes a relative-pose constraint.
- An outlier filter decides which constraints to believe, and a pose graph optimiser merges everything.
A team is most fragile at step 4. PCM keeps the largest set of inter-robot loop closures that agree with each other, GNC down-weights the ones that fit badly, and Kimera borrowed PCM for a single robot. See robust estimation.
Messages
| System | What crosses the link | Setting |
|---|---|---|
| Hydra-Multi | each robot’s whole scene graph and mesh, at every update | indoor, centralised |
| CURB-SG | lidar submaps, with ground-truth start poses | simulated cars |
| ROMAN | open-set object maps, under 250 KB per 40-object submap | forest and campus |
| SGM-SLAM | object labels and centroids | legged robots, indoor and outdoor |
| CERPE | fixed-size descriptors, images only on request | brief encounters |
| DRACo-SLAM2 | 1.35 kbit object summaries, scans only after a match | sonar robots, 62.5 kbps modem |
| Above and Below | loop closures on structure seen from both sides of the waterline | one surface vessel, several AUVs |
Across air and ground, MAG-VLAQ matches ground camera and lidar against aerial images (61.1 Recall@1 against 34.5 for the next best), and Hickory aligns maps from different sessions by object shape alone, with 0.24 m error against 0.82 m for ROMAN.
Assumptions
- Honest teammates. Outlier filters are designed for perceptual aliasing: look-alike rooms, repeated pier pilings. A coordinated set of wrong measurements wins under PCM, because it is the largest consistent set. TEASER++ proves that with adversarial outliers, exact recovery needs at least three more inliers than outliers.
- Good links. Hydra-Multi resends everything every update. DRACo-SLAM2 replays separately recorded sessions, so real packet loss is never tested.
- Privacy is free. CILC shows that a compromised teammate can reconstruct an honest robot’s images from the descriptors it broadcasts for loop closure, and fixes it with secure multi-party computation on the similarity step only.
- A guarantee survives merging. Conformal map fusion is one of the few papers that proves something about the merged map: robots exchange scalar e-values, and the fused occupancy map recovers its target coverage on any communication graph.
Questions
- What does a robot do with a loop closure from a teammate it can’t verify?
- How small can the exchanged summary be before matches become unreliable?
- Which part of the pipeline should carry the trust model: the matcher, the outlier filter, or the merge?
Related: 3D scene graphs, resilient consensus, Byzantine faults, underwater perception, multi-robot multimodal perception.