Dense Incremental Metric-Semantic Mapping for Multi-Agent Systems via Sparse Gaussian Process Regression

TL;DR

This paper presents an online probabilistic mapping method for multi-robot systems that combines metric and semantic information using sparse Gaussian Process regression, scalable to large environments and enabling distributed multi-robot mapping.

Contribution

It introduces a novel online Gaussian Process-based approach for metric-semantic mapping that scales with environment size and supports multi-robot distributed mapping.

Findings

Effective in 2-D and 3-D environments

Supports multi-robot distributed mapping

Accurate semantic and geometric surface estimation

Abstract

We develop an online probabilistic metric-semantic mapping approach for mobile robot teams relying on streaming RGB-D observations. The generated maps contain full continuous distributional information about the geometric surfaces and semantic labels (e.g., chair, table, wall). Our approach is based on online Gaussian Process (GP) training and inference, and avoids the complexity of GP classification by regressing a truncated signed distance function (TSDF) of the regions occupied by different semantic classes. Online regression is enabled through a sparse pseudo-point approximation of the GP posterior. To scale to large environments, we further consider spatial domain partitioning via an octree data structure with overlapping leaves. An extension to the multi-robot setting is developed by having each robot execute its own online measurement update and then combine its posterior parameters via local weighted geometric averaging with those of its neighbors. This yields a distributed information processing architecture in which the GP map estimates of all robots converge to a common map of the environment while relying only on local one-hop communication. Our experiments demonstrate the effectiveness of the probabilistic metric-semantic mapping technique in 2-D and 3-D environments in both single and multi-robot settings.