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

arXiv: https://arxiv.org/abs/2603.06729 · HTML: https://mlsanity.com/paper/2603.06729/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [Socially Aware Motion Planning with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.08862/) (2017)
- [Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation](https://mlsanity.com/paper/2203.15041/) (2022)
- [Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning](https://mlsanity.com/paper/1805.01956/) (2018)
- [Principles and Guidelines for Evaluating Social Robot Navigation Algorithms](https://mlsanity.com/paper/2306.16740/) (2023)
- [VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models](https://mlsanity.com/paper/2404.00210/) (2024)
- [Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning](https://mlsanity.com/paper/2011.04820/) (2020)
- [DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles](https://mlsanity.com/paper/2301.06512/) (2023)
- [DenseCAvoid: Real-time Navigation in Dense Crowds using Anticipatory Behaviors](https://mlsanity.com/paper/2002.03038/) (2020)
- [DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs](https://mlsanity.com/paper/1909.13003/) (2019)
- [Frozone: Freezing-Free, Pedestrian-Friendly Navigation in Human Crowds](https://mlsanity.com/paper/2003.05395/) (2020)
- [Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion](https://mlsanity.com/paper/2409.16950/) (2024)
- [Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation](https://mlsanity.com/paper/2308.14947/) (2023)
- [Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd Navigation](https://mlsanity.com/paper/2407.13567/) (2024)

## Built on by (most cited first, 1 of 1)

- [CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise](https://mlsanity.com/paper/2609.33106/) (2026)

## Abstract (arXiv)

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!∈![11,16] pedestrians in a 3m×3m arena and evaluated up to N!=!21 pedestrians (1.3× 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.