Don’t Freeze, Don’t Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds

arXiv:2603.06729v1 Announce Type: cross
Abstract: Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a density-invariant observation encoding with density-randomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted $K$ nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with $N!in![11,16]$ pedestrians in a $3mathrmmtimes3mathrmm$ arena and evaluated up to $N!=!21$ pedestrians ($1.3times$ denser), our policy reaches the goal in $>99%$ of episodes and achieves $86%$ collision-free success in random crowds, with markedly less freezing than analytical methods and a $>!60$-point collision-free margin over learning-based benchmark methods. Codes are available at hrefhttps://github.com/jznmsl/PSS-Socialhttps://github.com/jznmsl/PSS-Social.