Large Language Models (LLMs) have demonstrated remarkable abilities in various language tasks, making them promising candidates for decision-making in robotics. Inspired by Hierarchical Reinforcement Learning (HRL), we propose Retrieval-Augmented Hierarchical in-context reinforcement Learning (RAHL), a novel framework that decomposes complex tasks into sub-tasks using an LLM-based high-level policy, in which a complex task is decomposed into sub-tasks by a high-level policy on-the-fly. The sub-tasks, defined by goals, are assigned to the low-level policy to complete. To improve the agent's performance in multi-episode execution, we propose Hindsight Modular Reflection (HMR), where, instead of reflecting on the full trajectory, we let the agent reflect on shorter sub-trajectories using intermediate goals to improve reflection efficiency. We evaluated the decision-making ability of the proposed RAHL in three benchmark environments, ALFWorld, Webshop, and HotpotQA, where the results show that RAHL can achieve an improvement in the performance of, respectively, 9%, 42%, and 10% in 5 execution episodes compared to state-of-the-art baselines. We also implemented RAHL on the Boston Dynamics SPOT robot, which is shown to effectively scan the environment, find entrances, and navigate to new rooms controlled by the LLM policy.

Recent advances in segmentation models such as the Segment Anything Model (SAM) have made it possible to generate high-quality masks for arbitrary regions in an image. However, these models lack semantic reasoning and cannot assign meaningful labels without predefined class prompts. Similarly, models like YOLO-Seg are restricted to fixed vocabularies, and CLIP-based segmentors struggle with abstract or hierarchical concepts. In this paper, we propose a Large Vision-Language Model (LVLM)-assisted information-rich semantic segmentation framework that bridges this gap by integrating SAM with open-vocabulary segmentation and multimodal language understanding. Our approach begins by generating precise masks using SAM and querying an LVLM to extract semantically relevant object names via carefully designed prompts. We then use a CLIP-based segmentor to produce rough masks corresponding to the object list and apply a voting-based mechanism to align rough and fine masks, enriching the final output with detailed and hierarchically organized semantic information. Through extensive evaluations on the COCO 2017 dataset, we demonstrate that our method not only outperforms traditional models in abstract and implicit labeling tasks but also provides semantically rich outputs that support human-in-the-loop and open-world applications.

The matching algorithm is an important part of simultaneous location and mapping. Aiming at the problem of large computation and poor real‐time performance of two‐dimensional lidar traditional correlation scan matching (CSM) algorithm, a multi‐resolution auxiliary historical point cloud matching algorithm is proposed, which combines high and low resolution and adopts a single‐frame to multi‐frame step‐by‐step matching scheme. The algorithm was carried out on the sweeping robot. Compared with the traditional CSM algorithm and iterative closest points algorithm, the single position accuracy of the method in this study is improved. In the indoor space of ∼10 m × 10 m, the cumulative error is reduced by 16.24 and 33.96%, respectively. Consequently, our algorithm can still manage to process in real‐time.