ManiAgent：面向通用机器人操作的智能体框架
ManiAgent: An Agentic Framework for General Robotic Manipulation
AI总结：
ManiAgent提出多智能体协作框架，通过环境感知、子任务分解与动作生成，实现端到端机器人操作，在SimplerEnv和真实任务上分别达到86.8%和95.8%成功率。
摘要：
尽管视觉-语言-动作（VLA）模型在机器人操作中展现了令人印象深刻的能力，但它们在复杂推理和长时程任务规划中的性能受到数据稀缺和模型容量的限制。为解决这一问题，我们引入了ManiAgent，一种面向通用操作任务的智能体架构，实现了从任务描述和环境输入到机器人操作动作的端到端输出。在该框架中，多个智能体通过智能体间通信进行环境感知、子任务分解和动作生成，从而高效处理复杂操作场景。评估表明，ManiAgent在SimplerEnv基准上实现了86.8%的成功率，在真实世界抓取放置任务上达到95.8%，实现了高效的数据收集，使得训练出的VLA模型性能与基于人工标注数据集训练的模型相当。项目网页见https://yi-yang929.github.io/ManiAgent/。
英文摘要：
While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address this, we introduce ManiAgent, an agentic architecture for general manipulation tasks that achieves end-to-end output from task descriptions and environmental inputs to robotic manipulation actions. In this framework, multiple agents involve inter-agent communication to perform environmental perception, sub-task decomposition and action generation, enabling efficient handling of complex manipulation scenarios. Evaluations show ManiAgent achieves an 86.8% success rate on the SimplerEnv benchmark and 95.8% on real-world pick-and-place tasks, enabling efficient data collection that yields VLA models with performance comparable to those trained on human-annotated datasets. The project webpage is available at https://yi-yang929.github.io/ManiAgent/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
