arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2509.00570cs.RO
收藏

ConceptBot:通过大语言模型与知识图谱的任务分解提升机器人自主性

ConceptBot: Enhancing Robot's Autonomy through Task Decomposition with Large Language Models and Knowledge Graph

Department of Innovative Technologies (DTI), Dalle Molle Institute for Artificial Intelligence (IDSIA), University of Applied Sciences(创新技术部门(DTI)、达摩迪人工智能研究所(IDSIA)、应用科学与艺术大学);Department of Mechanical Engineering, Politecnico di Milano(机械工程部门、米兰理工学院)

Alessandro Leanza, Angelo Moroncelli, Giuseppe Vizzari, Francesco Braghin, Loris Roveda, Blerina Spahiu

AI总结:

针对机器人因常识推理不足难以处理歧义指令与环境物体分析的问题,提出融合大语言模型和知识图谱的模块化规划框架ConceptBot,通过三个功能模块生成风险感知的可行规划,在多类任务与基准上大幅优于现有方法,无需领域训练即可泛化。

摘要:

ConceptBot是一种模块化机器人规划框架,它结合大语言模型(Large Language Models, LLM)与知识图谱,在自然语言指令存在歧义、且需正确分析环境中物体的情况下生成可行且具备风险感知的规划——这些挑战通常源于常识推理能力的缺失。为此,ConceptBot集成了三个模块:(1)物体属性提取(Object Property Extraction, OPE)模块,利用ConceptNet的语义概念丰富场景理解;(2)用户请求处理(User Request Processing, URP)模块,对指令进行消歧并结构化;(3)规划器,生成具备上下文感知能力的可行抓取-放置策略。在与Google SayCan的对比评估中,ConceptBot在显式任务上取得100%成功率,在隐式任务上保持87%准确率(SayCan为31%),在风险感知任务上达到76%(SayCan为15%),且在材料分类(70% vs 20%)、毒性检测(86% vs 36%)等特定应用场景中均优于SayCan。在SafeAgentBench基准上,ConceptBot的整体得分为80%(次优基线为46%)。这些结果在仿真与实验室实验中均得到验证,表明ConceptBot无需领域特定训练即可泛化,能显著提升非结构化环境中机器人策略的可靠性。项目网站:https://sites.google.com/view/conceptbot

英文摘要:

ConceptBot is a modular robotic planning framework that combines Large Language Models and Knowledge Graphs to generate feasible and risk-aware plans despite ambiguities in natural language instructions and correctly analyzing the objects present in the environment - challenges that typically arise from a lack of commonsense reasoning. To do that, ConceptBot integrates (i) an Object Property Extraction (OPE) module that enriches scene understanding with semantic concepts from ConceptNet, (ii) a User Request Processing (URP) module that disambiguates and structures instructions, and (iii) a Planner that generates context-aware, feasible pick-and-place policies. In comparative evaluations against Google SayCan, ConceptBot achieved 100% success on explicit tasks, maintained 87% accuracy on implicit tasks (versus 31% for SayCan), reached 76% on risk-aware tasks (versus 15%), and outperformed SayCan in application-specific scenarios, including material classification (70% vs. 20%) and toxicity detection (86% vs. 36%). On SafeAgentBench, ConceptBot achieved an overall score of 80% (versus 46% for the next-best baseline). These results, validated in both simulation and laboratory experiments, demonstrate ConceptBot's ability to generalize without domain-specific training and to significantly improve the reliability of robotic policies in unstructured environments. Website: https://sites.google.com/view/conceptbot

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。

↑