Probabilistic Data Association via Mixture Models for Robust Semantic SLAM

TL;DR

This paper introduces a probabilistic data association method using mixture models for semantic SLAM, enhancing robustness by effectively handling non-Gaussian uncertainties and multiple hypotheses in noisy environments.

Contribution

It proposes a max-mixture model that marginalizes data association variables, allowing standard Gaussian SLAM frameworks to incorporate semantic and geometric uncertainties.

Findings

Improves robustness in semantic SLAM with noisy data.

Handles multiple data association hypotheses effectively.

Demonstrates superior performance in indoor and outdoor navigation tasks.

Abstract

Modern robotic systems sense the environment geometrically, through sensors like cameras, lidar, and sonar, as well as semantically, often through visual models learned from data, such as object detectors. We aim to develop robots that can use all of these sources of information for reliable navigation, but each is corrupted by noise. Rather than assume that object detection will eventually achieve near perfect performance across the lifetime of a robot, in this work we represent and cope with the semantic and geometric uncertainty inherent in methods like object detection. Specifically, we model data association ambiguity, which is typically non-Gaussian, in a way that is amenable to solution within the common nonlinear Gaussian formulation of simultaneous localization and mapping (SLAM). We do so by eliminating data association variables from the inference process through max-marginalization, preserving standard Gaussian posterior assumptions. The result is a max-mixture-type model that accounts for multiple data association hypotheses as well as incorrect loop closures. We provide experimental results on indoor and outdoor semantic navigation tasks with noisy odometry and object detection and find that the ability of the proposed approach to represent multiple hypotheses, including the "null" hypothesis, gives substantial robustness advantages in comparison to alternative semantic SLAM approaches.