Knowledge propagation and relation learning for predicting action effects

Learning to predict the effects of actions applied to pairs of objects is a difficult task that requires learning complex relations with sparse, incomplete and noisy information. Our Knowledge Propagation approach propagates affordance predictions by exploiting similarities among object properties, action parameters and resulting effects. The knowledge is propagated in a graph where a missing edge, corresponding to an unknown interaction between two objects (nodes), is predicted via the superposition of all paths connecting those objects in the graph. The high complexity of affordance representation is addressed through the use of Maximum Margin Multi-Valued Regression (MMMVR), which scales well to complex problems of multiple layers. With increased diversity and size of object databases and the addition of other parametric combinatory actions, we expect to achieve complex systems that leverage learned structure for subsequent learning, achieving structural bootstrapping over lifelong development and learning. In this paper, we extend MMMVR for learning of paired-object affordances, i. e. , for predicting the effects of actions applied to pairs of objects. In our experiments, we evaluated this method on a dataset composed of 83 objects and 83×83 interactions. We compared the prediction performance with standard classifiers that predict the effect category given the object pair's low-level features or single-object affordances. The experiments show that our proposed method achieves significantly higher prediction performance especially when supported with Active Learning.

Authors

• Sándor Szedmák
• Emre Ugur
• Justus H. Piater

Keywords

• Vectors
• Stacking
• Robots
• Support vector machines
• Databases
• Shape
• Optimization
• General Knowledge
• Effect Of Activity
• Predictive Performance
• Active Learning
• Low-level Features
• Object Pairs
• Maximum Margin
• Training Set
• Optimization Problem
• Basic Characteristics
• Classification Performance
• Matrix Elements
• Learning Task
• Small Datasets
• Learning Problem
• Object Features
• Hilbert Space
• Nodes In The Graph
• Human Experts
• Recommender Systems
• Multilinear
• Interaction Datasets
• Object Affordances
• Shape Descriptors
• Missing Elements
• Object Labels
• Tensor Product