Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.11063 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915836550184960 |
|---|---|
| author | Zeng, Haishan Wang, Mengna Li, Peng |
| author_facet | Zeng, Haishan Wang, Mengna Li, Peng |
| contents | In embodied artificial intelligence, enabling heterogeneous robot teams to execute long-horizon tasks from high-level instructions remains a critical challenge. While large language models (LLMs) show promise in instruction parsing and preliminary planning, they exhibit limitations in long-term reasoning and dynamic multi-robot coordination. We propose EmboTeam, a novel embodied multi-robot task planning framework that addresses these issues through a three-stage cascaded architecture: 1) It leverages an LLM to parse instructions and generate Planning Domain Definition Language (PDDL) problem descriptions, thereby transforming commands into formal planning problems; 2) It combines the semantic reasoning of LLMs with the search capabilities of a classical planner to produce optimized action sequences; 3) It compiles the resulting plan into behavior trees for reactive control. The framework supports dynamically sized heterogeneous robot teams via a shared blackboard mechanism for communication and state synchronization. To validate our approach, we introduce the MACE-THOR benchmark dataset, comprising 42 complex tasks across 8 distinct household layouts. Experiments show EmboTeam improves the task success rate from 12% to 55% and goal condition recall from 32% to 72% over the LaMMA-P baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11063 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration Zeng, Haishan Wang, Mengna Li, Peng Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems In embodied artificial intelligence, enabling heterogeneous robot teams to execute long-horizon tasks from high-level instructions remains a critical challenge. While large language models (LLMs) show promise in instruction parsing and preliminary planning, they exhibit limitations in long-term reasoning and dynamic multi-robot coordination. We propose EmboTeam, a novel embodied multi-robot task planning framework that addresses these issues through a three-stage cascaded architecture: 1) It leverages an LLM to parse instructions and generate Planning Domain Definition Language (PDDL) problem descriptions, thereby transforming commands into formal planning problems; 2) It combines the semantic reasoning of LLMs with the search capabilities of a classical planner to produce optimized action sequences; 3) It compiles the resulting plan into behavior trees for reactive control. The framework supports dynamically sized heterogeneous robot teams via a shared blackboard mechanism for communication and state synchronization. To validate our approach, we introduce the MACE-THOR benchmark dataset, comprising 42 complex tasks across 8 distinct household layouts. Experiments show EmboTeam improves the task success rate from 12% to 55% and goal condition recall from 32% to 72% over the LaMMA-P baseline. |
| title | EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2601.11063 |