E3AD：面向以人为中心的端到端自动驾驶的情感感知视觉-语言-动作模型
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
把连续 VAD 情感状态作为条件注入 VLA 驾驶策略，并设计自我中心/异我中心双通路空间融合模块；对做端到端驾驶或指令跟随的研究者，这是一个可复用的「语言意图+情感先验→轨迹」条件化范式与一致性对齐训练流程。
原文依据 a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论端到端自动驾驶（AD）系统越来越多地采用视觉-语言-动作（VLA）模型，但这些系统忽略了乘客的情绪状态，而情绪状态对乘坐舒适性与自动驾驶的接受度至关重要。我们提出开放域端到端（OD-E2E）自动驾驶设定：自动驾驶车辆需要理解自由形式的自然语言指令、推断情绪，并规划出物理上可行的轨迹。我们提出 E3AD，一个情感感知的 VLA 框架，它通过两个受认知科学启发的组件来增强语义理解：一个连续的效价-唤醒-支配（VAD）情绪模型，用于从语言中捕捉语气与紧迫程度；以及一个双通路空间推理模块，融合自我中心与异我中心视角，以实现类人的空间认知。一种面向一致性的训练方案，将模态预训练与基于偏好的对齐相结合，进一步强化情绪意图与驾驶动作之间的连贯性。在真实世界数据集上，E3AD 提升了视觉定位与路点规划，并在情绪估计上取得了最优的 VAD 相关性。这些结果表明，将情绪注入 VLA 风格的驾驶可带来更符合人类习惯的视觉定位、规划与反馈。
英文原文摘要 1200 字符
End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) AD, where an autonomous vehicle must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valence-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and feedback.