用自然语言指挥不同机器人协作，自动生成高效调度方案。
FLEET: Formal Language-Grounded Scheduling for Heterogeneous Robot Teams
- 语言转任务图+机器人匹配矩阵，结合大模型与形式化优化
- 在多任务场景下成功率达92%，比现有方法提升18%
- 适合需要跨机器人协作的现实应用，如救援、物流
从自由形式的自然语言指令协调异构机器人团队极具挑战。仅依赖语言的规划器在长时程协作和幻觉问题上表现不佳，而纯形式化方法需封闭世界假设。我们提出FLEET，一种混合式去中心化框架，将语言指令转化为优化的多机器人调度方案。大语言模型前端生成（i）含持续时间与先后顺序的任务图，以及（ii）能力感知的机器人-任务适配矩阵；形式化后端则求解最小完工时间问题，底层机器人通过代理式闭环控制执行自由形式子任务。在多个自然语言引导的自主协调基准测试中，FLEET在双机器人异构任务组合上相较最先进生成式规划器显著提升成功率。消融实验表明，混合整数线性规划（MILP）主要增强时间结构，而LLM生成的适配矩阵对能力耦合任务至关重要；二者结合实现最佳整体性能。我们在一对能力互补的四足机器人上完成了硬件验证，展示了其在真实世界挑战中的可行性。
原文摘要 · Abstract (English)
Coordinating heterogeneous robot teams from free-form natural-language instructions is hard. Language-only planners struggle with long-horizon coordination and hallucination, while purely formal methods require closed-world models. We present FLEET, a hybrid decentralized framework that turns language into optimized multi-robot schedules. An LLM front-end produces (i) a task graph with durations and precedence and (ii) a capability-aware robot--task fitness matrix; a formal back-end solves a makespan-minimization problem while the underlying robots execute their free-form subtasks with agentic closed-loop control. Across multiple free-form language-guided autonomy coordination benchmarks, FLEET improves success over state of the art generative planners on two-agent teams across heterogeneous tasks. Ablations show that mixed integer linear programming (MILP) primarily improves temporal structure, while LLM-derived fitness is decisive for capability-coupled tasks; together they deliver the highest overall performance. We demonstrate the translation to real world challenges with hardware trials using a pair of quadruped robots with disjoint capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。