Show simple item record

dc.contributor.authorYan, Fujian
dc.contributor.authorWang, Dali
dc.contributor.authorHe, Hongsheng
dc.date.accessioned2021-03-28T00:11:42Z
dc.date.available2021-03-28T00:11:42Z
dc.date.issued2021-02-23
dc.identifier.citationSiddiqui, H., Rattani, A., Kisku, D. R., & Dean, T. (2020). Al-based BMI inference from facial images: An application to weight monitoring. Paper presented at the Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020, 1101-1105. doi:10.1109/ICMLA51294.2020.00177en_US
dc.identifier.isbn978-1-7281-6212-6
dc.identifier.isbn978-1-7281-6213-3
dc.identifier.issn2153-0866
dc.identifier.issn2153-0858
dc.identifier.urihttps://doi.org/10.1109/IROS45743.2020.9340917
dc.identifier.urihttps://soar.wichita.edu/handle/10057/19867
dc.descriptionClick on the DOI link to access the article (may not be free).en_US
dc.description.abstractUnderstanding spatial relations of objects is critical in many robotic applications such as grasping, manipulation, and obstacle avoidance. Humans can simply reason object’s spatial relations from a glimpse of a scene based on prior knowledge of spatial constraints. The proposed method enables a robot to comprehend spatial relationships among objects from RGB-D data. This paper proposed a neural-logic learning framework to learn and reason spatial relations from raw data by following logic rules on spatial constraints. The neural-logic network consists of three blocks: grounding block, spatial logic block, and inference block. The grounding block extracts high-level features from the raw sensory data. The spatial logic blocks can predicate fundamental spatial relations by training a neural network with spatial constraints. The inference block can infer complex spatial relations based on the predicated fundamental spatial relations. Simulations and robotic experiments evaluated the performance of the proposed method.en_US
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.ispartofseries2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA);
dc.subjectTrainingen_US
dc.subjectGroundingen_US
dc.subjectNeural networksen_US
dc.subjectRobot sensing systemsen_US
dc.subjectFeature extractionen_US
dc.subjectSpatial databasesen_US
dc.subjectRobotsen_US
dc.titleRobotic understanding of spatial relationships using neural-logic learningen_US
dc.typeConference paperen_US
dc.rights.holder© 2020 IEEEen_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record