arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13248cs.AIcs.CLcs.RO
收藏

X-Blocks: 自然语言解释的语义构建块用于自动驾驶车辆

X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles

Queensland University of Technology (QUT)(昆士兰科技大学);ARC Training Centre for Automated Vehicles in Rural and Remote Regions (AVR3)(农村和偏远地区自动化车辆培训中心)

Ashkan Y. Zadeh, Xiaomeng Li, Andry Rakotonirainy, Ronald Schroeter, Sebastien Glaser, Zishuo Zhu

AI总结:

X-Blocks框架通过分层分析识别自动驾驶车辆自然语言解释的构建块,提供场景感知解释的设计原则,提升透明性和用户信任。

摘要:

自然语言解释在建立自动驾驶车辆(AVs)的信任和接受度方面起着关键作用,但现有的方法缺乏系统性的框架来分析人类如何在多样化的场景中用语言构建驾驶理由。本文介绍了X-Blocks(X解释块),一种分层分析框架,用于识别自动驾驶车辆的自然语言解释的语义构建块,分为三个层次:上下文、语法和词汇。在上下文层次,我们提出了RACE(推理对齐的解释分类),一种多LLM集成框架,结合了链式推理和自一致性机制,以稳健地将解释分类为32种场景感知的类别。应用于伯克利DeepDrive-X数据集的人工解释,RACE在准确率上达到91.45%,与人类标注者一致的Cohens kappa值为0.91,表明上下文分类的近人类可靠性。在词汇层次,利用信息量大的狄利克雷先验进行对数几率分析,揭示出特定上下文的词汇模式,这些模式能够区分驾驶场景。在语法层次,依赖解析和模板提取显示,解释来源于有限的可重用语法家族,不同上下文中的谓语类型和因果构造存在系统性变化。X-Blocks框架是数据无关且任务无关的,可以广泛应用于其他自动驾驶数据集和安全关键领域。总体而言,我们的发现提供了生成场景感知解释的基于证据的语言设计原则,以支持自动驾驶系统的透明性、用户信任和认知可访问性。

英文摘要:

Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs), yet existing approaches lack systematic frameworks for analysing how humans linguistically construct driving rationales across diverse scenarios. This paper introduces X-Blocks (eXplanation Blocks), a hierarchical analytical framework that identifies the linguistic building blocks of natural language explanations for AVs at three levels: context, syntax, and lexicon. At the context level, we propose RACE (Reasoning-Aligned Classification of Explanations), a multi-LLM ensemble framework that combines Chain-of-Thought reasoning with self-consistency mechanisms to robustly classify explanations into 32 scenario-aware categories. Applied to human-authored explanations from the Berkeley DeepDrive-X dataset, RACE achieves 91.45 percent accuracy and a Cohens kappa of 0.91 against cases with human annotator agreement, indicating near-human reliability for context classification. At the lexical level, log-odds analysis with informative Dirichlet priors reveals context-specific vocabulary patterns that distinguish driving scenarios. At the syntactic level, dependency parsing and template extraction show that explanations draw from a limited repertoire of reusable grammar families, with systematic variation in predicate types and causal constructions across contexts. The X-Blocks framework is dataset-agnostic and task-independent, offering broad applicability to other automated driving datasets and safety-critical domains. Overall, our findings provide evidence-based linguistic design principles for generating scenario-aware explanations that support transparency, user trust, and cognitive accessibility in automated driving systems.

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。

↑