DynoSLAM embeds stochastic GNN-based pedestrian forecasts via Monte Carlo rollouts and a dynamic Mahalanobis factor into GraphSLAM to maintain accurate tracking and produce probabilistic safety envelopes in crowded scenes.
Reinforcement learning-based dynamic obstacle avoid- ance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DynoSLAM: Dynamic SLAM with Generative Graph Neural Networks for Real-World Social Navigation
DynoSLAM embeds stochastic GNN-based pedestrian forecasts via Monte Carlo rollouts and a dynamic Mahalanobis factor into GraphSLAM to maintain accurate tracking and produce probabilistic safety envelopes in crowded scenes.