Deep multi-object symbol learning with self-attention based predictors
Type :
Conference paper
Publication Status :
Published
Access :
restrictedAccess
Abstract
This paper proposes an architecture that can learn symbolic representations from the continuous sensorimotor experience of a robot interacting with a varying number of objects. Unlike previous works, this work aims to remove constraints on the learned symbols such as a fixed number of interacted objects or pre-defined symbolic structures. The proposed architecture can learn symbols for single objects and relations between them in a unified manner. The architecture is an encoder-decoder network with a binary activation layer followed by self-attention layers. Experiments are conducted in a robotic manipulation setup with a varying number of objects. Results showed that the robot successfully encodes the interaction dynamics between a varying number of objects using the discovered symbols. We also showed that the discovered symbols can be used for planning to reach symbolic goal states by training a higher-level neural network.
Source :
2023 31st Signal Processing and Communications Applications Conference (SIU)
Date :
2023
Publisher :
IEEE
Collections
Share this page