从语义决策到可行轨迹：自进化LLM引导的窄空间泊车最优控制
From Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking
查看机构详情
- xLean Robotics Co., Ltd.（xLean机器人有限公司）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出SE-LLM-OCP框架，结合LLM高层机动决策与最优控制低层约束，通过在线重规划与离线知识库自进化，实现狭窄空间安全泊车并跨平台迁移。
中文摘要 AI 辅助
在非凸且狭窄的环境中进行自主泊车仍然具有挑战性。尽管最优控制方法能够显式地强制执行车辆动力学和碰撞约束，但非凸性会损害求解器的鲁棒性并可能导致失败。大型语言模型（LLMs）展现出强大的语义推理能力，但直接生成稠密轨迹难以保证物理可行性。我们提出了SE-LLM-OCP，一个统一框架，其中LLM做出高层离散机动决策，而最优控制模块强制执行低层车辆动力学和碰撞约束。在线阶段，LLM提出稀疏机动计划，将泊车任务分解为一系列短时域轨迹优化问题。随后，低层求解器依次求解最优控制问题。如果求解器失败，LLM会聚合来自求解器和验证阶段的失败证据以指导重新规划。离线阶段，SE-LLM-OCP从零开始自动演化一个结构化的决策知识库，由累积的在线失败驱动。我们在仿真中验证了所提出的框架，使用类车车辆模型和差速驱动机器人。实验结果表明，SE-LLM-OCP能够在狭窄场景中实现更安全的自主泊车，并展示了相同机动表示向不同运动学平台的迁移能力。
英文摘要
Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collision constraints, nonconvexity compromises solver robustness and can cause failures. Large language models (LLMs) exhibit strong semantic reasoning capabilities, but directly generating dense trajectories makes it difficult to guarantee physical feasibility. We introduce SE-LLM-OCP, a unified framework in which LLMs make high-level discrete maneuver decisions, while an optimal-control module enforces low-level vehicle dynamics and collision constraints. Online, the LLM proposes sparse maneuver plans, decomposing the parking task into a sequence of short-horizon trajectory-optimization problems. A low-level solver then sequentially solves optimal-control problems. If the solver fails, the LLM aggregates failure evidence from the solver and validation stages to guide replanning. Offline, SE-LLM-OCP automatically evolves a structured decision-making knowledge base from scratch, driven by accumulated online failures. We validate our proposed framework in simulation on a car-like vehicle model and on a differential-drive robot. Our experimental results show that SE-LLM-OCP enables safer autonomous parking in narrow scenarios and demonstrates transfer of the same maneuver representation to a different kinematic platform.
