This article proposes a long-term dynamic object relocalization (L-DOR) solution to address the challenge of mobile robots efficiently relocalize task-related objects in human–robot coexisting environments over extended periods. Existing methods mainly focus on one-time object localization, neglecting long-term relocalization amidst dynamic changes caused by human activities. To tackle this issue, a probabilistic model of object distribution based on spatio-temporal patterns is first established. Then, a robot-object perception interaction is introduced to achieve dynamic object category discrimination, enabling the robot to handle sporadic events caused by human activities. Besides, a cost-expectation balance-based object matching method is presented to determine the suitable task object and gradually infer its potential locations with probabilistic model. On this basis, we suggest a hierarchical global planning and local decision-making to prioritize search efforts to improve localization efficiency. Extensive comparisons and long-term experiments in real-world scenarios with a Fetch robot demonstrate the efficacy of L-DOR in terms of search performance, adaptability to different scenarios, and long-term effectiveness.

Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learning-based segmentation techniques require extensive annotated datasets, which are impractical for the diversity of objects encountered in real-world scenarios. Unseen object instance segmentation (UOIS) methods aim to address this by training models on synthetic data to generalize to novel objects, but they often suffer from the simulation-to-reality gap. This article proposes a novel approach (ZISVFM) for solving UOIS by leveraging the powerful zero-shot capability of the segment anything model (SAM) and explicit visual representations from a self-supervised vision transformer (ViT). The proposed framework operates in the following three stages: generating object-agnostic mask proposals from colorized depth images using SAM, refining these proposals using attention-based features from the self-supervised ViT to filter nonobject masks, and applying K-Medoids clustering to generate point prompts that guide SAM toward precise object segmentation. Experimental validation on two benchmark datasets and a self-collected dataset demonstrates the superior performance of ZISVFM in complex environments, including hierarchical settings such as cabinets, drawers, and handheld objects.