# Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2606.10495 · HTML: https://mlsanity.com/paper/2606.10495/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Safety and adversarial attacks, one of 13 directions in Vision-language-action models.
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Placed in

- Vision-language-action models / [Safety and adversarial attacks](https://mlsanity.com/vla/safety-and-adversarial-attacks/)

## Builds on (most cited first, 30 of 31)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [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)
- [Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.07845/) (2016)
- [Principles and Guidelines for Evaluating Social Robot Navigation Algorithms](https://mlsanity.com/paper/2306.16740/) (2023)
- [VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers](https://mlsanity.com/paper/2203.17247/) (2022)
- [VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models](https://mlsanity.com/paper/2404.00210/) (2024)
- [Vision-Language Models Provide Promptable Representations for Reinforcement Learning](https://mlsanity.com/paper/2402.02651/) (2024)
- [A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challenges](https://mlsanity.com/paper/2311.06922/) (2023)
- [OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation](https://mlsanity.com/paper/2509.19480/) (2025)
- [Toward Human-Like Social Robot Navigation: A Large-Scale, Multi-Modal, Social Human Navigation Dataset](https://mlsanity.com/paper/2303.14880/) (2023)
- [Mechanistic interpretability for steering vision-language-action models](https://mlsanity.com/paper/2509.00328/) (2025)
- [Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces](https://mlsanity.com/paper/2501.09024/) (2024)
- [Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture](https://mlsanity.com/paper/2502.04558/) (2025)
- [Observing and Controlling Features in Vision-Language-Action Models](https://mlsanity.com/paper/2603.05487/) (2026)
- [AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning](https://mlsanity.com/paper/2503.07557/) (2025)
- [SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation](https://mlsanity.com/paper/2509.08757/) (2025)
- [TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments](https://mlsanity.com/paper/2602.02459/) (2026)
- [SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation](https://mlsanity.com/paper/2403.00991/) (2024)
- [VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation](https://mlsanity.com/paper/2510.20818/) (2025)
- [GSON: A Group-based Social Navigation Framework with Large Multimodal Model](https://mlsanity.com/paper/2409.18084/) (2024)
- [Learning World Transition Model for Socially Aware Robot Navigation](https://mlsanity.com/paper/2011.03922/) (2020)
- [From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection](https://mlsanity.com/paper/2602.09002/) (2026)
- [Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigation](https://mlsanity.com/paper/2509.17204/) (2025)

## Abstract (arXiv)

Safe social navigation requires robots to distinguish people from ordinary obstacles and to react before danger becomes imminent. We show that pretrained Vision-Language-Action (VLA) models already encode pedestrian-object distinctions and future collision signals in their internal representations, but behavior cloning fails to translate these signals into socially appropriate actions. To address this mismatch, we propose SALSA, a two-stage annotation-free post-training framework: (1) social behavioral alignment bridges intermediate-layer social features to the action head and trains on counterfactual human-object scene pairs to break visual saliency shortcuts; (2) temporal safety alignment provides automatically generated future-risk supervision to enable anticipatory collision avoidance. On SCAND and real-world deployment, SALSA reduces near-collisions by 86.4% and improves social counterfactual accuracy from 53% to 93%, demonstrating that safer social navigation can be achieved by teaching VLA policies to act on representations they already possess. These results show that pretrained VLA policies can be adapted for safer social navigation by better aligning their latent representations with action generation.