{"paper":{"title":"DynoSLAM: Dynamic SLAM with Generative Graph Neural Networks for Real-World Social Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DynoSLAM uses Monte Carlo rollouts from graph neural networks to capture pedestrian uncertainty and embed it into SLAM optimization.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Danil Tokhchukov, Gonzalo Ferrer, Veronika Morozova","submitted_at":"2026-05-04T15:58:08Z","abstract_excerpt":"Traditional Simultaneous Localization and Mapping (SLAM) algorithms rely heavily on the static environment assumption, which severely limits their applicability in real-world spaces populated by moving entities, such as pedestrians. In this work, we propose DynoSLAM, a tightly-coupled Dynamic GraphSLAM architecture that integrates socially-aware Graph Neural Networks (GNNs) directly into the factor graph optimization. Unlike conventional approaches that use rigid constant-velocity heuristics or deterministic single-agent neural priors, our framework formulates pedestrian motion forecasting as "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By utilizing Monte Carlo rollouts from a trained GNN, we capture the multimodal epistemic uncertainty of human interactions and embed it into the SLAM graph via a dynamic Mahalanobis distance factor.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That Monte Carlo samples from the pre-trained GNN will produce uncertainty estimates that integrate stably into the factor-graph optimizer without introducing new failure modes or requiring post-hoc tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DynoSLAM embeds stochastic pedestrian motion predictions from generative GNNs into a dynamic GraphSLAM factor graph to enable safer robot navigation in human environments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DynoSLAM uses Monte Carlo rollouts from graph neural networks to capture pedestrian uncertainty and embed it into SLAM optimization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8dc13203bd341c8606f0bf74fd11e1b6edb3e2b89d6e4a3309d27182da49c2cb"},"source":{"id":"2605.02759","kind":"arxiv","version":2},"verdict":{"id":"29e17ef0-44f2-471c-92b0-d6d3bdbcd15e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T17:38:25.901378Z","strongest_claim":"By utilizing Monte Carlo rollouts from a trained GNN, we capture the multimodal epistemic uncertainty of human interactions and embed it into the SLAM graph via a dynamic Mahalanobis distance factor.","one_line_summary":"DynoSLAM embeds stochastic pedestrian motion predictions from generative GNNs into a dynamic GraphSLAM factor graph to enable safer robot navigation in human environments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That Monte Carlo samples from the pre-trained GNN will produce uncertainty estimates that integrate stably into the factor-graph optimizer without introducing new failure modes or requiring post-hoc tuning.","pith_extraction_headline":"DynoSLAM uses Monte Carlo rollouts from graph neural networks to capture pedestrian uncertainty and embed it into SLAM optimization."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02759/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:01:38.021742Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8c92a413ac3ef3309b11c04503c95b572578234e1ddbde9145a9f94f6bfc557a"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}