Active Domain-Invariant Self-Localization Using Ego-Centric and World-Centric Maps

TL;DR

This paper introduces a domain-invariant next-best-view planner for visual place recognition in autonomous navigation, leveraging CNN features from both ego-centric and world-centric maps to improve robot localization without extensive data collection.

Contribution

It proposes a novel domain-invariant NBV planning framework that uses CNN intermediate and output layer cues, trained with deep reinforcement learning, to enhance robot self-localization.

Findings

Validated on NCLT dataset showing improved localization accuracy

Effective transfer of domain-invariant features to NBV planning

Reduced data collection costs for visual place recognition

Abstract

The training of a next-best-view (NBV) planner for visual place recognition (VPR) is a fundamentally important task in autonomous robot navigation, for which a typical approach is the use of visual experiences that are collected in the target domain as training data. However, the collection of a wide variety of visual experiences in everyday navigation is costly and prohibitive for real-time robotic applications. We address this issue by employing a novel {\it domain-invariant} NBV planner. A standard VPR subsystem based on a convolutional neural network (CNN) is assumed to be available, and its domain-invariant state recognition ability is proposed to be transferred to train the domain-invariant NBV planner. Specifically, we divide the visual cues that are available from the CNN model into two types: the output layer cue (OLC) and intermediate layer cue (ILC). The OLC is available at the output layer of the CNN model and aims to estimate the state of the robot (e.g., the robot viewpoint) with respect to the world-centric view coordinate system. The ILC is available within the middle layers of the CNN model as a high-level description of the visual content (e.g., a saliency image) with respect to the ego-centric view. In our framework, the ILC and OLC are mapped to a state vector and subsequently used to train a multiview NBV planner via deep reinforcement learning. Experiments using the public NCLT dataset validate the effectiveness of the proposed method.