A Variational Observation Model of 3D Object for Probabilistic Semantic SLAM

TL;DR

This paper introduces a Bayesian model for 3D object observation in semantic SLAM, approximating complex shapes with tractable distributions and using variational likelihood from 2D images to improve pose estimation and loop closure.

Contribution

It proposes a novel probabilistic observation model for 3D objects that handles single-view 2D images, enabling more complete semantic SLAM with automatic loop closure.

Findings

Effective pose and feature estimation demonstrated.

Seamless automatic loop closure achieved.

Model handles single-view 2D observations for 3D shape inference.

Abstract

We present a Bayesian object observation model for complete probabilistic semantic SLAM. Recent studies on object detection and feature extraction have become important for scene understanding and 3D mapping. However, 3D shape of the object is too complex to formulate the probabilistic observation model; therefore, performing the Bayesian inference of the object-oriented features as well as their pose is less considered. Besides, when the robot equipped with an RGB mono camera only observes the projected single view of an object, a significant amount of the 3D shape information is abandoned. Due to these limitations, semantic SLAM and viewpoint-independent loop closure using volumetric 3D object shape is challenging. In order to enable the complete formulation of probabilistic semantic SLAM, we approximate the observation model of a 3D object with a tractable distribution. We also estimate the variational likelihood from the 2D image of the object to exploit its observed single view. In order to evaluate the proposed method, we perform pose and feature estimation, and demonstrate that the automatic loop closure works seamlessly without additional loop detector in various environments.