多大模型协作解决机器人长任务执行失败问题
Triple-S: A Collaborative Multi-LLM Framework for Solving Long-Horizon Implicative Tasks in Robotics
- 三阶段协作框架让多个大模型分工处理简化-求解-总结
- 在真实与部分可观测场景下成功执行89%的长任务
- 可从成功案例学习，自动修复曾失败的任务
利用大语言模型（LLMs）编写机器人控制策略代码受到广泛关注。但在长周期推理性任务中，该方法常因API参数错误、注释不当和序列混乱导致任务失败。为此，我们提出协同式Triple-S框架，通过上下文学习让多个LLM在闭环的简化-求解-总结流程中扮演特定角色，显著提升长周期推理性任务的成功率与鲁棒性。此外，引入一种基于成功案例学习的示范库更新机制，使系统能泛化至此前失败的任务。我们在长周期桌面推理性放置（LDIP）数据集上验证了框架效果，Triple-S在可观测与部分可观测场景下分别成功执行89%的任务。仿真与真实机器人实验进一步证实其有效性。代码与数据集已公开于：https://github.com/Ghbbbbb/Triple-S。
原文摘要 · Abstract (English)
Leveraging Large Language Models (LLMs) to write policy code for controlling robots has gained significant attention. However, in long-horizon implicative tasks, this approach often results in API parameter, comments and sequencing errors, leading to task failure. To address this problem, we propose a collaborative Triple-S framework that involves multiple LLMs. Through In-Context Learning, different LLMs assume specific roles in a closed-loop Simplification-Solution-Summary process, effectively improving success rates and robustness in long-horizon implicative tasks. Additionally, a novel demonstration library update mechanism which learned from success allows it to generalize to previously failed tasks. We validate the framework in the Long-horizon Desktop Implicative Placement (LDIP) dataset across various baseline models, where Triple-S successfully executes 89% of tasks in both observable and partially observable scenarios. Experiments in both simulation and real-world robot settings further validated the effectiveness of Triple-S. Our code and dataset is available at: https://github.com/Ghbbbbb/Triple-S.
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。