# LLM解释器提升月球车轨迹规划可信度，忠实度达90.9%

> 原文链接：https://robotics.hellobike.com/papers/2026-11-11-2611-13292-f2bc68be
> 频道：papers | 更新日期：2026-11-11 | 标签：auto, arxiv
> 核心摘要：研究提出基于LLM的交互式助手解释月球车概率轨迹规划，采用ReAct架构调用工具链。实验显示响应忠实度达90.9%，较零样本提示提升近65%，验证了后规划解释范式在不确定性环境下的可信赖性。

# LLM解释器提升月球车轨迹规划可信度，忠实度达90.9%

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty](https://arxiv.org/abs/2611.13292)（arXiv 2611.13292）

## 核心内容

针对月球车在概率不确定性下轨迹规划难以人工验证的痛点，研究团队提出一种基于大语言模型的交互式解释助手。该系统不直接参与决策，而是作为后规划解释层，利用领域词汇解析采样规划器输出并支持重跑对比。在模拟NASA VIPER任务的测试中，助手对规划结果的解释忠实度达到90.9%，相比无工具调用的零样本提示提升约65%，解决了传统MCTS等算法缺乏科学目标可追溯性的问题。

技术架构采用ReAct模式构建可查询接口，通过检索增强与动作工具调用实现对规划器的精确溯源。系统将LLM限定在解释与查询环节，避免其直接干预底层控制决策以提升信任度。评估涵盖方案对比、可行性验证及参数查询三类任务，结果表明工具增强机制有效抑制了模型幻觉，为具身智能在非结构化环境中的复杂任务规划提供了高可信的人机交互验证范式。

## 关键看点

- **解释忠实度**：在计划对比与可行性查询测试中，LLM助手对规划器输出的解释准确率达90.9%
- **性能增益**：引入ReAct工具链后，解释准确性较纯LLM零样本提示提升近65%
- **架构范式**：采用后规划解释策略，LLM仅做结果阐释与重跑触发，不介入底层决策回路
- **仿真验证**：基于NASA VIPER任务模拟器构建测试环境，覆盖不确定性遍历场景

## 工程与产业观察

该研究确立了“规划器负责决策、LLM负责解释”的解耦范式，为具身智能在高风险场景落地提供关键参考。90.9%的忠实度证明工具增强是解决LLM幻觉、建立人机信任的有效路径，对地外探测及工业机器人的可解释性安全验证具有直接工程价值。

## 英文摘要 (Abstract)

Planning planetary rover trajectories under probabilistic uncertainty is a multi-objective optimization problem that science teams currently iteratively solve and verify by hand. This process becomes impractical when timelines and constraints frequently shift throughout the mission planning phase. Sampling-based planners such as Monte Carlo tree search can speed up this process, but their outputs do not preserve traceability to the science objectives that justify each plan, which the science team needs to verify. We propose an interactive assistant based on a large language model (LLM) that can explain planner trajectories using domain vocabulary and re-run the planner under user-specified conditions to compare alternatives. Previous work has used LLMs inside planner decision-making loops, but we explore using them for post-planning explanation, where they are more likely to be trusted since they do not directly influence planner decisions. Our framework pairs a simulator inspired by the NASA Volatiles Investigating Polar Exploration Rover (VIPER) mission with a ReAct queryable interface that calls curated action tools and retrieval functions. We evaluate the assistant on a query bank consisting of plan comparisons, feasibility, and lookup queries. Experiments show that 90.9% of the assistant's responses are faithful to the planner's outputs, a nearly 65% improvement over zero-shot prompting of the same LLM without tool access, demonstrating the potential for trustworthy explainability of uncertainty-aware traverses with an LLM-based system.

作者：Michelle Ho, Maximilian Adang, Zachary Booth, David E. Astle, Margaret Hansen, Edward Balaban, Mykel J. Kochenderfer
:::

## 原始参考来源 (Sources)

- [arXiv 2611.13292：Large Language Model Explainability for Planning Lunar Rover Trajectories under Uncertainty](https://arxiv.org/abs/2611.13292)