Despite significant advancements in recent decades, autonomous vehicles (AVs) continue to face challenges in navigating certain traffic scenarios where human drivers excel. In such situations, AVs often become immobilized, disrupting overall traffic flow. Current recovery solutions, such as remote intervention (which is costly and inefficient) and manual takeover (which excludes non-drivers and limits AV accessibility), are inadequate. This paper introduces StuckSolver, a novel Large Language Model (LLM) driven recovery framework that enables AVs to resolve immobilization scenarios through self-reasoning and/or passenger-guided decision-making. StuckSolver is designed as a plug-in add-on module that operates on top of the AV's existing perception-planning-control stack, requiring no modification to its internal architecture. Instead, it interfaces with standard sensor data streams to detect immobilization states, interpret environmental context, and generate high-level recovery commands that can be executed by the AV's native planner. We evaluate StuckSolver on the Bench2Drive benchmark and in custom-designed uncertainty scenarios. Results show that StuckSolver achieves near-state-of-the-art performance through autonomous self-reasoning alone and exhibits further improvements when passenger guidance is incorporated.

翻译：尽管近几十年来取得了显著进展，自动驾驶车辆（AVs）在应对某些人类驾驶员擅长的交通场景时仍面临挑战。在此类情境下，自动驾驶车辆常陷入停滞状态，从而扰乱整体交通流。现有的脱困解决方案，如远程干预（成本高昂且效率低下）和人工接管（排除了非驾驶员并限制了自动驾驶车辆的可及性），均存在不足。本文提出StuckSolver，一种基于大型语言模型（LLM）的新型脱困框架，使自动驾驶车辆能够通过自主推理和/或乘客引导的决策机制解决停滞场景。StuckSolver被设计为插件式附加模块，运行于自动驾驶车辆现有的感知-规划-控制架构之上，无需修改其内部系统。该框架通过接入标准传感器数据流来检测停滞状态、解析环境上下文，并生成可由自动驾驶车辆原生规划器执行的高层恢复指令。我们在Bench2Drive基准测试及定制化不确定性场景中对StuckSolver进行评估。结果表明，仅通过自主推理，StuckSolver即能达到接近最先进水平的性能，且在融入乘客引导后表现出进一步的提升。