Multiple Hypothesis Semantic Mapping for Robust Data Association

TL;DR

This paper introduces a semantic SLAM method using multiple hypothesis tracking and pose graphs to improve urban environment mapping, reducing drift and hypothesis complexity.

Contribution

It presents a novel semantic SLAM approach with multiple hypothesis trees and covisibility graphs for better data association and environment representation.

Findings

33% average drift reduction compared to raw odometry

55% fewer hypotheses than traditional multiple hypothesis methods

Effective in urban scenarios with similar surroundings

Abstract

In this paper, we present a semantic mapping approach with multiple hypothesis tracking for data association. As semantic information has the potential to overcome ambiguity in measurements and place recognition, it forms an eminent modality for autonomous systems. This is particularly evident in urban scenarios with several similar looking surroundings. Nevertheless, it requires the handling of a non-Gaussian and discrete random variable coming from object detectors. Previous methods facilitate semantic information for global localization and data association to reduce the instance ambiguity between the landmarks. However, many of these approaches do not deal with the creation of complete globally consistent representations of the environment and typically do not scale well. We utilize multiple hypothesis trees to derive a probabilistic data association for semantic measurements by means of position, instance and class to create a semantic representation. We propose an optimized mapping method and make use of a pose graph to derive a novel semantic SLAM solution. Furthermore, we show that semantic covisibility graphs allow for a precise place recognition in urban environments. We verify our approach using real-world outdoor dataset and demonstrate an average drift reduction of 33 % w.r.t. the raw odometry source. Moreover, our approach produces 55 % less hypotheses on average than a regular multiple hypotheses approach.