Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.07417 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918157039435776 |
|---|---|
| author | Rivera, Corban Byrd, Grayson Booker, Meghan Kemp, Bethany Gaines, Allison Holmes, Emma Uplinger, James de Melo, Celso M Handelman, David |
| author_facet | Rivera, Corban Byrd, Grayson Booker, Meghan Kemp, Bethany Gaines, Allison Holmes, Emma Uplinger, James de Melo, Celso M Handelman, David |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07417 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLEET: Formal Language-Grounded Scheduling for Heterogeneous Robot Teams Rivera, Corban Byrd, Grayson Booker, Meghan Kemp, Bethany Gaines, Allison Holmes, Emma Uplinger, James de Melo, Celso M Handelman, David Robotics 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. |
| title | FLEET: Formal Language-Grounded Scheduling for Heterogeneous Robot Teams |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.07417 |