Skip to main content

Robotic Understanding of Spatial Relationships Using Neural-Logic Learning...

by Dali Wang
Publication Type
Conference Paper
Book Title
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publication Date
Page Numbers
8358 to 8365
Publisher Location
Nevada, United States of America
Conference Name
International Conference on Intelligent Robots and Systems (IROS)
Conference Location
Las Vages, Nevada, United States of America
Conference Sponsor
Conference Date

Understanding 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.