Path planning is a crucial component of autonomous mobile robot (AMR) systems. The slime mould algorithm (SMA), as one of the most popular path-planning approaches, shows excellent performance in the AMR field. Despite its advantages, there is still room for SMA to improve due to the lack of a mechanism for jumping out of local optimization. This means that there is still room for improvement in the path planning of ARM based on this method. To find shorter and more stable paths, an improved SMA, called the Lévy flight-rotation SMA (LRSMA), is proposed. LRSMA utilizes variable neighborhood Lévy flight and an individual rotation perturbation and variation mechanism to enhance the local optimization ability and prevent falling into local optimization. Experiments in varying environments demonstrate that the proposed algorithm can generate the ideal collision-free path with the shortest length, higher accuracy, and robust stability.

Lane detection is a fundamental task in computer vision with broad applications in autonomous driving. Recent advances have focused on line-anchor-based representations for their efficiency and high accuracy. However, most existing methods adopt anchors that are continuous in point sampling yet discrete in width and fixed in direction. This leads to geometric misalignments with real-world lane lines, which exhibit continuous width representation and smoothly varying directions. These misalignments cause Symmetric Point Ambiguity and Magnified Localization Errors, ultimately degrading both evaluation reliability and detection accuracy. To address these issues, we propose Angle-Aware Rectangle Anchors (ARA), a novel representation with continuous width and adaptive directional alignment, that effectively captures the geometric variation of lane lines. In addition, we propose the Three-phase Angle-Thresholded Line-Area Transition (TALAT) Loss, which dynamically switches between loss formulations based on angular thresholds and overlap quality, enabling a smooth transition from coarse to fine supervision. Extensive experiments on multiple standard benchmarks (TuSimple, CULane, CurveLanes, and LLAMAS) demonstrate that our approach achieves competitive or state-of-the-art (SOTA) performance. Notably, ARA exhibits superior robustness in challenging scenarios, while maintaining real-time inference speed. Our code and models are publicly available at https://github.com/changehome717/ARA-Lane-Detection.

Monocular 3D lane detection is challenged by the loss of directional detail in distant markings during feature downsampling and by geometric ambiguity between lateral curvature and road elevation under single-view projection. R-A3D addresses both issues through frequency-aware Riemannian anchor learning in an anchor-regression pipeline. A Haar-based feature pyramid retains four frequency subbands before learned channel projection, strengthening thin and low-contrast lane responses. Each evolving 3D anchor is summarized in the lateral–elevation plane by Gaussian mean and covariance statistics, embedded in a symmetric positive-definite matrix, and mapped to a tangent-space feature with the Log-Euclidean metric. This Riemannian anchor feature is fused residually with anchor-aligned visual evidence and recomputed after each cascade stage. On OpenLane, the ResNet-50 model achieves 64.9% F1, 94.1% category accuracy, and far-range lateral and vertical errors of 0.215 m and 0.081 m at 23.5 frames/s; the ResNet-18 model reaches 63.0% F1 at 53.2 frames/s. On ApolloSim Visual Variations, R-A3D achieves 96.1% F1 and reduces the two far-range errors by 31.0% and 30.3% relative to GLane3D. These results demonstrate complementary benefits from frequency-preserving visual evidence and proposal-dependent Riemannian geometry.

Monocular 3D lane detection faces challenges due to the loss of directional detail in distant markings during feature downsampling and geometric ambiguity between lateral curvature and road elevation under single-view projection. R-A3D addresses both issues through frequency-aware Riemannian anchor learning in an anchor-regression pipeline. A Haar-based feature pyramid retains four frequency subbands before learned channel projection, strengthening thin and low-contrast lane responses. Each evolving 3D anchor is summarized in the lateral-elevation plane by Gaussian mean and covariance statistics, embedded in a symmetric positive-definite matrix, and mapped to a tangent-space feature with the Log-Euclidean metric. This Riemannian anchor feature is residually fused with anchor-aligned visual evidence and recomputed after each cascade stage. On OpenLane, the ResNet-50 model achieves 64.9% F1, 94.1% category accuracy, and far-range lateral and vertical errors of 0.215 m and 0.081 m at 23.5 frames/s; the ResNet-18 model reaches 63.0% F1 at 53.2 frames/s. Across the three ApolloSim subsets, R-A3D improves F1 over the reproducible Anchor3DLane baseline by 1.4–4.3 percentage points and reduces far-range lateral error by 18.7–23.2%. These results indicate complementary benefits from frequency-preserving visual evidence and proposal-dependent Riemannian geometry within the evaluated settings.