Long-term localization is an essential task for unmanned ground vehicles; however, it suffers from scene changes due to various environmental conditions (e.g., lighting conditions, seasonal shifts, viewpoint changes, or occlusions). In this article, we propose a novel end-to-end localizer for robust long-term localization in changing environments. First, a lightweight two-head place classification network is proposed in which a place is regarded as a category. Considering seasonal changes lead to severe variants of local structures, large-sized filters in the first layer and a large-scale average-pooling strategy are designed to focus regional context features of scenes. Motivated by the reward and punishment mechanisms in reinforcement learning, an incremental learning strategy is proposed to distinguish distinctive scenes for robust topological localization. Extensive experiments tested on three datasets whose collecting periods are over a year are utilized to validate the feasibility and performance of our method.

中文翻译：

---

用于大规模变化环境中长期拓扑定位的端到端定位器


长期定位是无人地面车辆的一项重要任务；然而，它会因各种环境条件（例如照明条件、季节变化、视点变化或遮挡）而发生场景变化。在本文中，我们提出了一种新颖的端到端定位器，用于在不断变化的环境中实现稳健的长期定位。首先，提出了一种轻量级的双头地点分类网络，其中地点被视为一个类别。考虑到季节变化会导致局部结构的严重变化，第一层的大尺寸过滤器和大规模平均池化策略被设计来关注场景的区域上下文特征。在强化学习中奖励和惩罚机制的推动下，提出了一种增量学习策略来区分独特的场景，以实现稳健的拓扑定位。对收集周期超过一年的三个数据集进行了广泛的实验，以验证我们方法的可行性和性能。