发表机构
Technische Universität Berlin（柏林工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种双AI架构，利用LLM和VLM将高层意图转化为受限代码，并通过环境驱动重规划实现动态未知环境下的鲁棒机器人控制。
AI 中文摘要
在未知和动态环境中，将机器人部署为复杂自适应系统（CAS）需要从刚性命令库向基于意图的自主性转变，因为自然语言是唯一能够表达超出有限指令集能力的复杂目标的媒介。虽然大型语言模型（LLMs）为自然语言目标描述提供了途径，但其集成引入了重大挑战：不精确意图与可执行动作之间的形式化差距、不可预测环境导致的分类差距，以及维持时间状态和进度意识的挑战。本文介绍了一种利用生成式人工智能实现机器人控制的架构框架。该系统采用双AI设计：一个LLM将高层意图转换为受限于正式机器人库并受可验证语法约束的可执行程序代码，而一个视觉语言模型（VLM）通过蒸馏过程提供语义基础。为确保鲁棒性，该框架纳入了基于几何和语义阈值的环境驱动重规划触发器，并辅以连续运行时监控和自适应规划循环。在前沿模型上进行基准测试，我们的框架架构表明，将生成式人工智能锚定在反应式、受约束的循环中，能够在动态和未知环境中稳健地实现复杂意图。
英文摘要
Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based autonomy, as natural language represents the only medium capable of articulating complex goals beyond the capacity of finite instruction sets. While Large Language Models (LLMs) offer a path toward natural language goal description, their integration introduces significant challenges: the formalization gap between imprecise intentions and executable actions, the taxonomy gap induced by unpredictable environments, and the challenge of maintaining temporal state and progress awareness. This work introduces an architectural framework that enables robotic control by leveraging generative AI. The system follows a dual-AI design: an LLM translates high-level intentions into executable program code restricted to a formal robotic library and constrained by verifiable syntax, while a Vision-Language Model (VLM) provides semantic grounding via a distillation process. To ensure robustness, the framework incorporates environment-driven replanning triggers based on geometric and semantic thresholds, complemented by continuous runtime monitoring and an adaptive planning loop. Benchmarked across frontier models, our framework architecture demonstrates that grounding generative AI in a reactive, constrained loop enables robust fulfillment of complex intentions in dynamic and unknown environments.
CommentsInternational Symposium on Leveraging Applications of Formal Methods, Verification, and Validation 2026
