Learning to identify new objects

Identifying objects based on language descriptions is an important capability for robots interacting with people in everyday environments. People naturally use attributes and names to refer to objects of interest. Due to the complexity of indoor environments and the fact that people use various ways to refer to objects, a robot frequently encounters new objects or object names. To deal with such situations, a robot must be able to continuously grow its object knowledge base. In this work we introduce a system that organizes objects and names in a semantic hierarchy. Similarity between name words is learned via a hierarchy embedded vector representation. The hierarchy enables reasoning about unknown objects and names. Novel objects are inserted automatically into the knowledge base, where the exact location in the hierarchy is determined by asking a user questions. The questions are informed by the current hierarchy and the appearance of the object. Experiments demonstrate that the learned representation captures the meaning of names and is helpful for object identification with new names.

Authors

• Yuyin Sun
• Liefeng Bo
• Dieter Fox

Keywords

• Vectors
• Robots
• Object recognition
• Semantics
• Training
• Measurement
• Natural languages
• Representation Learning
• Object Of Interest
• Vector Representation
• Object Identification
• Object Naming
• Object Appearance
• Unknown Objects
• Word Naming
• Scoring Function
• Vector Space
• System Identification
• New Words
• Word Meaning
• Target Object
• Word Embedding
• Leaf Node
• Natural Objects
• Child Nodes
• Objects In The Scene
• Original Representation
• Original Vector
• Correct Path
• WordNet
• Cutting-plane
• Learning Vector
• Slack Variables
• Active Constraints
• Tree Nodes
• High Scores