EmboTeam: Asymmetric State Grounding for Heterogeneous Multi-Robot Collaboration
Organizations: University of Chinese Academy of Sciences · Institute of Software, Chinese Academy of Sciences
Abstract
Heterogeneous multi-robot collaboration over long horizons requires both global task planning and robust coordination during execution. Existing plan- ners using large language models (LLMs) can generate task decompositions or symbolic plans, but often execute them as rigid action sequences, making them fragile to local state mismatches and synchronization failures. We propose Em- boTeam, a neuro-symbolic framework for asymmetric state grounding. An LLM generates structured state expectations, which are verified and coordinated through symbolic search using Planning Domain Definition Language (PDDL) and then grounded into a team-level parallel behavior tree. Robot-specific subtrees per- form precondition checking, skill execution, effect validation, local replanning, and blackboard-based synchronization. We further introduce MACE-THOR, con- taining 42 heterogeneous multi-robot tasks across 8 indoor layouts. EmboTeam improves task success rate from 12% to 55% and goal condition recall from 32% to 75% over LaMMA-P, demonstrating the effectiveness of synchronized reactive grounding for collaboration over long horizons.
Figures & tables
| Benchmark | Tasks | Layouts | Robots | Avg. goals | Avg. subtasks | Avg. objects | Dependency depth |
| SMART-LLM [ 12 ] | 36 | 7 | 1–4 | 1.58 | 5.50 | 2.19 | 4.28 |
| MAT-THOR [ 24 ] | 70 | 7 | 2–4 | 1.76 | 6.63 | 2.47 | 4.94 |
| MACE-THOR-PI | 21 | 6 | 2–3 | 2.14 | 10.19 | 3.19 | 7.71 |
| MACE-THOR-TD | 21 | 8 | 2–4 | 3.38 | 19.00 | 4.24 | 16.67 |
| MACE-THOR | 42 | 8 | 2–4 | 2.76 | 14.60 | 3.71 | 12.19 |
| Methods | Parallel-Independent | Temporal-Dependent | ||||||
| SR | GCR | Exec | ESC | SR | GCR | Exec | ESC | |
| CoT (GPT-4o) | ||||||||
| SMART-LLM (GPT-4o) | ||||||||
| LaMMA-P (GPT-4o) | ||||||||
| Ours (Llama-3.1) | ||||||||
| Ours (Claude-3.5) | ||||||||
| Methods | Parallel-Independent | Temporal-Dependent | ||||||
| SR | GCR | Exec | ESC | SR | GCR | Exec | ESC | |
| Ours (w/o SEG & SSEM) | ||||||||
| Ours (w/o SSEM) | ||||||||
| Ours (w/o RSG) | ||||||||
| Ours (w/o sync) | ||||||||
| Ours (w/o recovery) | ||||||||
Multi-Robot Coordination
Multi-robot coordination studies how teams of robots plan, communicate, allocate tasks, and act together safely and efficiently.
See all 347 papers