Deep Samplable Observation Model for Global Localization and Kidnapping

TL;DR

This paper introduces DSOM, a deep learning-based sampling model for particle filtering in robot localization, combined with AdaM MCL for adaptive updates, improving accuracy and efficiency in challenging scenarios.

Contribution

The paper proposes DSOM, a novel deep samplable observation model, and AdaM MCL, an adaptive particle update mechanism, enhancing global localization and kidnapping robustness.

Findings

DSOM improves sampling focus on high-likelihood regions.

AdaM MCL achieves faster convergence and higher accuracy.

Method works effectively in real and synthetic environments, even with long-term changes.

Abstract

Global localization and kidnapping are two challenging problems in robot localization. The popular method, Monte Carlo Localization (MCL) addresses the problem by iteratively updating a set of particles with a "sampling-weighting" loop. Sampling is decisive to the performance of MCL [1]. However, traditional MCL can only sample from a uniform distribution over the state space. Although variants of MCL propose different sampling models, they fail to provide an accurate distribution or generalize across scenes. To better deal with these problems, we present a distribution proposal model, named Deep Samplable Observation Model (DSOM). DSOM takes a map and a 2D laser scan as inputs and outputs a conditional multimodal probability distribution of the pose, making the samples more focusing on the regions with higher likelihood. With such samples, the convergence is expected to be more effective and efficient. Considering that the learning-based sampling model may fail to capture the true pose sometimes, we furthermore propose the Adaptive Mixture MCL (AdaM MCL), which deploys a trusty mechanism to adaptively select updating mode for each particle to tolerate this situation. Equipped with DSOM, AdaM MCL can achieve more accurate estimation, faster convergence and better scalability compared to previous methods in both synthetic and real scenes. Even in real environments with long-term changing, AdaM MCL is able to localize the robot using DSOM trained only by simulation observations from a SLAM map or a blueprint map.