Act on What You See: 在视觉-语言-动作模型中解锁安全社交导航
Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models
AI总结：
提出SALSA框架，通过两阶段无标注后训练（社交行为对齐和时间安全对齐），使预训练VLA模型利用已有表征实现安全社交导航，减少86.4%的近距离碰撞。
摘要：
安全社交导航要求机器人区分行人与普通障碍物，并在危险迫近前做出反应。我们表明，预训练的视觉-语言-动作（VLA）模型已在其内部表征中编码了行人-物体区分和未来碰撞信号，但行为克隆未能将这些信号转化为社交上合适的动作。为解决这一不匹配问题，我们提出SALSA，一个两阶段无标注后训练框架：（1）社交行为对齐将中间层社交特征桥接到动作头，并在反事实人-物场景对上训练以打破视觉显著性捷径；（2）时间安全对齐提供自动生成的未来风险监督，实现预期性碰撞避免。在SCAND和实际部署中，SALSA将近距离碰撞减少86.4%，并将社交反事实准确率从53%提升至93%，表明通过教导VLA策略利用其已拥有的表征来行动，可以实现更安全的社交导航。这些结果表明，通过更好地对齐潜在表征与动作生成，预训练VLA策略可被调整用于更安全的社交导航。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
