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 2011.05817cs.RO
收藏

FINO-Net:一种用于操作故障检测的深度多模态传感器融合框架

FINO-Net: A Deep Multimodal Sensor Fusion Framework for Manipulation Failure Detection

Istanbul Technical University(伊斯坦布尔理工大学);Halmstad University(哈尔姆斯塔德大学)

Arda Inceoglu, Eren Erdal Aksoy, Abdullah Cihan Ak, Sanem Sariel

摘要:

服务机器人在非结构化环境中的安全操作是一个具有挑战性的问题。需要一个故障检测系统来监测和检测非预期的结果。我们提出了FINO-Net,一种新型的基于多模态传感器融合的深度神经网络来检测和识别操作故障。我们还介绍了一个多模态数据集,包含229个真实世界的操作数据记录与巴克斯特机器人。我们的网络结合了RGB、深度和音频读数,可以有效地检测和分类故障。结果表明,融合RGB与深度和音频模态显着提高了性能。FINO-Net在我们的新数据集上实现了98.60%的检测和87.31%的分类准确率。代码和数据可在https://github.com/ardai/fino-net上公开获取。

英文摘要:

Safe manipulation in unstructured environments for service robots is a challenging problem. A failure detection system is needed to monitor and detect unintended outcomes. We propose FINO-Net, a novel multimodal sensor fusion based deep neural network to detect and identify manipulation failures. We also introduce a multimodal dataset, containing 229 real-world manipulation data recorded with a Baxter robot. Our network combines RGB, depth and audio readings to effectively detect and classify failures. Results indicate that fusing RGB with depth and audio modalities significantly improves the performance. FINO-Net achieves 98.60% detection and 87.31% classification accuracy on our novel dataset. Code and data are publicly available at https://github.com/ardai/fino-net.

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。

↑