Learning spatial relationships between objects

By Benjamin Rosman, Subramanian Ramamoorthy. 2011

113 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Networks and Communications, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning human activities and object affordances from RGB-D videos (2012, background): “, 2012), semantic labeling of environments by modeling objects and their relations to other objects in the scene (Koppula et al., 2011; Lai et al., 2011b; Rosman and Ramamoorthy, 2011; Anand et al., 2012), developing frameworks for object recognition and pose estimation for manipulation (Collet et a”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, background): “o which part or object they belong (Schenck and Fox, 2018a; Myers et al., 2015). Interactions may be modeled at this level of the hierarchy as contact points (Kaul et al., 2016; Dang and Allen, 2012; Rosman and Ramamoorthy, 2011; Kopicki et al., 2016; Vina~ et al., 2013; Su et al., 2015; Veiga et al”
Metric learning for generalizing spatial relations to new objects (2017, methodology): “Related to this is the work by Rosman and Ramamoor-thy, which proposes constructing a contact point graph to classify spatial relations [23].”
Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning (2017, background): “In the context of robotics, learning spatial relations between objects has previously been phrased as a supervised classification problem based on handcrafted features such as contact points and relative poses [8], [9], [10].”
A Multitask Representation Using Reusable Local Policy Templates (2012, background): “Recurring motifs can be seen in other domains such as manipulation tasks, by taking into account topological descriptors of the objects in the robot’s workspace (Rosman and Ramamoorthy 2011).”