用3D场景图推断物体常识可用性，让机器人像人一样规划任务。
Leveraging Computation of Expectation Models for Commonsense Affordance Estimation on 3D Scene Graphs
- 基于图卷积网络学习物体上下文关系的概率分布。
- 在真实室内环境验证，性能接近人类常识水平。
- 适合需要智能理解环境的机器人任务规划场景。
本文研究了用于城市环境中具身机器人任务规划与优化的常识性物体可用性概念。重点在于推理任务执行中物体固有用途的有效识别，本工作通过分析3D场景图中的稀疏信息上下文关系实现。所提出的框架构建了相关性信息（CECI）模型，利用图卷积网络学习概率分布，从而为语义类别中的个体提取常识性可用性。整体框架在真实室内环境中进行了实验验证，展示了该方法在常识推理上达到与人类相当的水平。相关实验演示视频请见：https://youtu.be/BDCMVx2GiQE
原文摘要 · Abstract (English)
This article studies the commonsense object affordance concept for enabling close-to-human task planning and task optimization of embodied robotic agents in urban environments. The focus of the object affordance is on reasoning how to effectively identify object's inherent utility during the task execution, which in this work is enabled through the analysis of contextual relations of sparse information of 3D scene graphs. The proposed framework develops a Correlation Information (CECI) model to learn probability distributions using a Graph Convolutional Network, allowing to extract the commonsense affordance for individual members of a semantic class. The overall framework was experimentally validated in a real-world indoor environment, showcasing the ability of the method to level with human commonsense. For a video of the article, showcasing the experimental demonstration, please refer to the following link: https://youtu.be/BDCMVx2GiQE
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。