发表机构
University of Massachusetts Dartmouth; California State University San Marcos（马萨诸塞大学达特茅斯分校; 加州州立大学圣马科斯分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出Skill-SLM框架，将SLM驱动的机器人操作转化为任务分解与技能组合问题，通过CFG构建技能库、LLM教师生成数据集及渐进式编排策略，在无人机、地面车辆任务上的性能优于蒸馏基线，泛化能力更强。
AI 中文摘要
小语言模型（SLMs）因支持智能决策，正越来越多地被用于机载机器人操作。然而，现有方法主要面向蒸馏，依赖枚举代表性任务-解决方案对，这使得数据集构建困难，且限制了其对各类机器人任务的泛化能力，这类任务的可能形式正快速增长。本文提出Skill-SLM，这是一个将SLM驱动的机器人操作重新表述为任务分解与技能组合问题的框架。给定自然语言任务指令，Skill-SLM会将任务分解为子任务，从技能库中选择合适的技能，并将所选技能编排为可执行的机器人操作。首先，为支持技能驱动的工作流，我们提出一种新颖的机器人操作技能感知上下文无关文法（CFG），以提取完成任务所需的技能并据此构建技能库。然后，我们配置大语言模型（LLM）教师来诱导并合成SLM的训练数据集，使SLM能够可靠地分解任务并编排技能。此外，我们采用渐进式技能编排策略，以提高技能执行和整体机器人操作的可靠性。在无人机（UAV）操作任务上的实验表明，Skill-SLM的性能显著优于面向蒸馏的基线方法，尤其是在需要能力泛化的未见任务上。在地面车辆任务上的额外实验进一步证明，Skill-SLM可应用于不同的机器人平台。
英文摘要
Small language models (SLMs) have been increasingly adopted for onboard robot operation because they enable intelligent decision-making. However, existing approaches are mainly distillation-oriented and rely on enumerating representative task-solution pairs. This makes dataset construction difficult and limits generalization to diverse robot tasks whose possible forms grow rapidly. This paper proposes Skill-SLM, a framework that reformulates SLM-driven robot operation as a task-decomposition and skill-composition problem. Given a natural language task instruction, Skill-SLM decomposes the task into subtasks, selects appropriate skills from the skill library, and orchestrates the selected skills into executable robot operations. First, to support the skill-driven workflow, we propose a novel robot operational skill aware context-free grammar (CFG) to extract the skills required to accomplish tasks and build the skill library accordingly. Then, we configure LLM teachers to induce and synthesize training datasets for the SLMs, enabling SLMs to decompose tasks and orchestrate skills reliably. Additionally, we employ a progressive skill orchestration strategy to improve the reliability of skill implementation and overall robot operation. Experiments on UAV operation tasks indicate that Skill-SLM substantially outperforms distillation-oriented baselines, especially on unseen tasks that require generalization of capabilities. Additional experiments on ground vehicle tasks further demonstrate that Skill-SLM can be applied to different robot platforms.
