Indoor localization has long been a challenging task due to the complexity and dynamism of indoor environments. This paper proposes ULG-SLAM, a novel unsupervised learning and geometric-based visual SLAM algorithm for robot localizability estimation to improve the accuracy and robustness of visual SLAM. Firstly, a dynamic feature filtering based on unsupervised learning and moving consistency checks is developed to eliminate the features of dynamic objects. Secondly, an improved line feature extraction algorithm based on LSD is proposed to optimize the effect of geometric feature extraction. Thirdly, geometric features are used to optimize localizability estimation, and an adaptive weight model and attention mechanism are built using the method of region delimitation and region growth. Finally, to verify the effectiveness and robustness of localizability estimation, multiple indoor experiments using the EuRoC dataset and TUM RGB-D dataset are conducted. Compared with ORBSLAM2, the experimental results demonstrate that absolute trajectory accuracy can be improved by 95% for equivalent processing speed in walking sequences. In fr3/walking_xyz and fr3/walking_half, ULG-SLAM tracks more trajectories than DS-SLAM, and the ATE RMSE is improved by 36% and 6%, respectively. Furthermore, the improvement in robot localizability over DynaSLAM is noteworthy, coming in at about 11% and 3%, respectively.

Autonomous exploration in unknown environments is an essential capability for mobile robots. The complexity of autonomous exploration, however, means that existing algorithms struggle to balance efficiency and comprehensiveness, causing low mapping accuracy and redundant path planning. To perform accurate and efficient exploration tasks, we have proposed a novel autonomous exploration algorithm via LiDAR/IMU (Inertial Measurement Unit) Simultaneous Localization and Mapping (SLAM) and hierarchical subsystem for mobile robot in unknown environments. Firstly, to enhance mapping accuracy for mobile robot exploration, LiDAR/IMU SLAM is improved with the assistance of backward propagation and iterated Kalman filter, and Bidirectional Rapidly–Exploring Random Trees* (BI–RRT*) is applied for efficient frontier point detection. Secondly, we optimize local path planning by leveraging information theory through perceptual quality evaluation, which is then integrated with global path planning utilizing an enhanced Travelling Salesman Problem solver and a sparse grid map to amplify exploration efficiency. Thirdly, an enhanced hierarchical autonomous exploration method for mobile robots is proposed, which incorporates local path planning for seamless navigation around highly promising exploration spots, coupled with global path planning to effectively interconnect various sub–regions. Finally, simulations and field tests have demonstrated that the proposed method explores an unknown indoor environment with a 30.8% reduction in exploration time and a 29.9% reduction in exploration path in comparison with Dynamic Stage Viewpoint Planner. The map constructed in this paper has more accurate details and exploration paths have been shortened to ensure effective exploration.

Recent years have witnessed increased demands on battery systems due to the rapid global transition to renewable energy storage, necessitating reliable performance analysis under diverse conditions, ranging from low-power edge computing and Internet of Things applications to high-throughput materials screening in digital twin simulations. However, obtaining sufficient, high-quality battery performance and status-monitoring data remains challenging, particularly with limited or noisy datasets. To address this, this article proposes PLT-GRU, a physics-informed lightweight Transformer-GRU algorithm for few-shot battery state-of-health estimation. That is, a few-shot cross-domain adaptation is developed within the Transformer-GRU architecture to reduce the need for a complete set of different target battery degradation data and improve the predictive robustness. In addition, a lightweight architecture is proposed to minimize parameter counts to reduce inference time and memory overhead, reducing reliance on considerable prior knowledge and more intricate architectures. Then, a physics-informed capacity-resistance soft coupling is proposed to gather additional data for model training by capturing crucial physical priors, including internal resistance, constant current charge test, constant voltage charge test, and battery capacity, improving stability and interpretability with few-shot data. In order to demonstrate the advantage of the proposed PLT-GRU, the experiment conducted partial-cycle experiments on three kinds of lithium-ion batteries with limited data to detect their complex degradation patterns. The experimental results showcase that the proposed PLT-GRU reduces complexity by 94.93% while maintaining high prediction accuracy and effectively adapting to new battery types using few-shot target battery datasets. The proposed method attains an average root-mean-square error and a mean absolute error of 5.87% and 4.30% for the CS2 battery series, 4.26% and 3.01% for the CX2 series and 1.43% and 1.06% for the NASA battery series.