提出分层框架解决多机器人控制中的幻觉问题，提升实际任务执行能力。
EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Control
- 分层架构结合动作预测与结构化记忆，分解任务并动态验证动作可行性。
- 在100种场景的1.8万条规划数据上，实现71.85%的评估得分，优于现有模型。
- 适用于需协调异构机器人的长周期服务任务，适合真实场景部署。
本文提出EmbodiedAgent，一种用于异构多机器人控制的分层框架。该方法针对不切实际任务中幻觉问题的关键局限，融合下一步动作预测范式与结构化记忆系统，将任务分解为可执行的机器人技能，并动态验证动作是否符合环境约束。我们构建了MultiPlan+数据集，包含超过18,000个标注的规划实例，覆盖100个场景，其中包含子集不切实际案例以缓解幻觉。为评估性能，提出机器人规划评估体系（RPAS），结合自动化指标与大模型辅助专家评分。实验表明，EmbodiedAgent在多项基准上超越现有最先进模型，达到71.85%的RPAS得分。真实办公室服务任务验证了其协调异构机器人完成长时目标的能力。
原文摘要 · Abstract (English)
This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction paradigm with a structured memory system to decompose tasks into executable robot skills while dynamically validating actions against environmental constraints. We present MultiPlan+, a dataset of more than 18,000 annotated planning instances spanning 100 scenarios, including a subset of impractical cases to mitigate hallucination. To evaluate performance, we propose the Robot Planning Assessment Schema (RPAS), combining automated metrics with LLM-aided expert grading. Experiments demonstrate EmbodiedAgent's superiority over state-of-the-art models, achieving 71.85% RPAS score. Real-world validation in an office service task highlights its ability to coordinate heterogeneous robots for long-horizon objectives.
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。