Deep SIMBAD: Active Landmark-based Self-localization Using Ranking -based Scene Descriptor

TL;DR

This paper introduces a novel active self-localization method using deep SIMBAD-based visual place recognition combined with a reinforcement learning planner for next-best-view selection, validated on the NCLT dataset.

Contribution

It presents a deep learning extension of SIMBAD for landmark-based scene description and transfers VPR knowledge to an RL-based NBV planner for improved active localization.

Findings

Effective landmark-based scene description with deep SIMBAD.

Successful transfer of VPR knowledge to the NBV planner.

Validated approach achieves accurate self-localization on NCLT dataset.

Abstract

Landmark-based robot self-localization has recently garnered interest as a highly-compressive domain-invariant approach for performing visual place recognition (VPR) across domains (e.g., time of day, weather, and season). However, landmark-based self-localization can be an ill-posed problem for a passive observer (e.g., manual robot control), as many viewpoints may not provide an effective landmark view. In this study, we consider an active self-localization task by an active observer and present a novel reinforcement learning (RL)-based next-best-view (NBV) planner. Our contributions are as follows. (1) SIMBAD-based VPR: We formulate the problem of landmark-based compact scene description as SIMBAD (similarity-based pattern recognition) and further present its deep learning extension. (2) VPR-to-NBV knowledge transfer: We address the challenge of RL under uncertainty (i.e., active self-localization) by transferring the state recognition ability of VPR to the NBV. (3) NNQL-based NBV: We regard the available VPR as the experience database by adapting nearest-neighbor approximation of Q-learning (NNQL). The result shows an extremely compact data structure that compresses both the VPR and NBV into a single incremental inverted index. Experiments using the public NCLT dataset validated the effectiveness of the proposed approach.