OPENTECHNICAL PUBLICATION
OT-2026-000001196

Methods for tokenization representation and learning of robotic perception data based on graph neural network

Published: 2026-09-15T19:04:03.936384Z
Permanent URL: https://opentechnical.org/p/OT-2026-000001196
Categories: Robotics & Automation > Robot Architectures

------------------------------------------------------------------------

ABSTRACT

Provided is a method for token-based representation and learning of robotic
perception data based on a graph neural network, comprising: obtaining a
plurality of types of perception data of a robot; performing token-based
representation according to types of the plurality of types of perception
data; constructing an initial feature graph based on the plurality of types of
perception data after the token-based representation; learning a compact
representation of the initial feature graph based on an autoencoder and
reconstructing a graph structure; after the autoencoder completes learning of
the graph structure, fixing the graph structure; and converting the plurality
of types of perception data into node feature vectors, constructing a feature
graph based on the graph structure, and performing numerical encoding on each
of the node feature vectors by utilizing the graph neural network to obtain a
representation of high-dimensional feature vectors of the plurality of types
of perception data.

------------------------------------------------------------------------

OpenTechnical publication OT-2026-000001196
Published 2026-09-15T19:04:03.936384Z
https://opentechnical.org/p/OT-2026-000001196