Domain-invariant NBV Planner for Active Cross-domain Self-localization (2102.11530v1)

Abstract: Pole-like landmark has received increasing attention as a domain-invariant visual cue for visual robot self-localization across domains (e.g., seasons, times of day, weathers). However, self-localization using pole-like landmarks can be ill-posed for a passive observer, as many viewpoints may not provide any pole-like landmark view. To alleviate this problem, we consider an active observer and explore a novel "domain-invariant" next-best-view (NBV) planner that attains consistent performance over different domains (i.e., maintenance-free), without requiring the expensive task of training data collection and retraining. In our approach, a novel multi-encoder deep convolutional neural network enables to detect domain invariant pole-like landmarks, which are then used as the sole input to a model-free deep reinforcement learning -based domain-invariant NBV planner. Further, we develop a practical system for active self-localization using sparse invariant landmarks and dense discriminative landmarks. In experiments, we demonstrate that the proposed method is effective both in efficient landmark detection and in discriminative self-localization.