Toward interactive learning of object categories by a robot: A case study with container and non-container objects

Authors:
Shane Griffith;Jivko Sinapov;Matthew Miller;Alexander Stoytchev
Affiliations:
Developmental Robotics Laboratory, Iowa State University, USA;Developmental Robotics Laboratory, Iowa State University, USA;Developmental Robotics Laboratory, Iowa State University, USA;Developmental Robotics Laboratory, Iowa State University, USA
Venue:
DEVLRN '09 Proceedings of the 2009 IEEE 8th International Conference on Development and Learning
Year:
2009

Citing 0
Cited 6

Traversability: A Case Study for Learning and Perceiving Affordances in Robots

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Goal emulation and planning in perceptual space using learned affordances

Robotics and Autonomous Systems
Ensembles of strong learners for multi-cue classification

Pattern Recognition Letters
From visual patterns to semantic description: A cognitive approach using artificial curiosity as the foundation

Pattern Recognition Letters
Structure-based object representation and classification in mobile robotics through a Microsoft Kinect

Robotics and Autonomous Systems
Autonomous knowledge acquisition based on artificial curiosity: Application to mobile robots in an indoor environment

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes an interactive approach to object categorization that is consistent with the principle that a robot's object representations should be grounded in its sensorimotor experience. The proposed approach allows a robot to: 1) form object categories based on the movement patterns observed during its interaction with objects, and 2) learn a perceptual model to generalize object category knowledge to novel objects. The framework was tested on a container/non-container categorization task. The robot successfully separated the two object classes after performing a sequence of interactive trials. The robot used the separation to learn a perceptual model of containers, which, which, in turn, was used to categorize novel objects as containers or non-containers.