Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference

doi:10.1109/TRO.2022.3197106

Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference

2023-02-01

6

OA

AI

DOI：10.1109/TRO.2022.3197106

Original

Original request for help

Save

Abstract

En 中文

In this article, we present a novel and flexible multitask multilayer Bayesian mapping framework with readily extendable attribute layers. The proposed framework goes beyond modern metric-semantic maps to provide even richer environmental information for robots in a single mapping formalism while exploiting intralayer and interlayer correlations. It removes the need for a robot to access and process information from many separate maps when performing a complex task, advancing the way robots interact with their environments. To this end, we design a multitask deep neural network with attention mechanisms as our front-end to provide heterogeneous observations for multiple map layers simultaneously. Our back-end runs a scalable closed-form Bayesian inference with only logarithmic time complexity. We apply the framework to build a dense robotic map, including metric-semantic occupancy and traversability layers. Traversability ground truth labels are automatically generated from exteroceptive sensory data in a self-supervised manner. We present extensive experimental results on publicly available datasets and data collected by a three-dimensional bipedal robot platform and show reliable mapping performance in different environments. Finally, we also discuss how the current framework can be extended to incorporate more information, such as friction, signal strength, temperature, and physical quantity concentration using Gaussian map layers. The software for reproducing the presented results or running on customized data is made publicly available.

Keywords:

Robots

Robot sensing systems

Task analysis

Semantics

Nonhomogeneous media

Planning

Estimation

Bayesian inference

continuous mapping

mutlitask learning

robot sensing systems

semantic scene understanding

traversability estimation

Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference

Abstract

Journal

Organization