Accurate and real-time traffic-sign detection is a cornerstone of Advanced Driver-Assistance Systems (ADAS) and autonomous vehicles. However, existing one-stage detectors miss distant signs, and two-stage pipelines are impractical for embedded deployment. To address this issue, we present YOLO-SMM, a lightweight two-stage framework. This framework is designed to augment the YOLOv8 baseline with three targeted modules. (1) SlimNeck replaces PAN/FPN with a CSP-OSA/GSConv fusion block, reducing parameters and FLOPs without compromising multi-scale detail. (2) The MCA model introduces row- and column-aware weights to selectively amplify small sign regions in cluttered scenes. (3) MPDIoU augments CIoU loss with a corner-distance term, supplying stable gradients for sub-20-pixel boxes and tightening localization. An evaluation of YOLO-SMM on the German Traffic Sign Recognition Benchmark (GTSRB) revealed that it attained 96.3% mAP50 and 93.1% mAP50-90 at a rate of 90.6 frames per second (FPS). This represents an improvement of +1.0% over previous performance benchmarks. The mAP at 64 × 64 resolution was found to be 50% of the maximum attainable value, with an FPS of +8.3 when compared to YOLOv8. This result indicates superior performance in terms of accuracy and speed compared to YOLOv7, YOLOv5, RetinaNet, EfficientDet, and Faster R-CNN, all of which were operated under equivalent conditions.

Most existing path planning approaches rely on discrete expansions or localized heuristics that can lead to extended re-planning, inefficient detours, and limited adaptability to complex obstacle distributions. These issues are particularly pronounced when navigating cluttered or large-scale environments that demand both global coverage and smooth trajectory generation. To address these challenges, this paper proposes a Wave Water Simulator (WWS) algorithm, leveraging a physically motivated wave equation to achieve inherently smooth, globally consistent path planning. In WWS, wavefront expansions naturally identify safe corridors while seamlessly avoiding local minima, and selective corridor focusing reduces computational overhead in large or dense maps. Comprehensive simulations and real-world validations—encompassing both indoor and outdoor scenarios—demonstrate that WWS reduces path length by 2%–13% compared to conventional methods, while preserving gentle curvature and robust obstacle clearance. Furthermore, WWS requires minimal parameter tuning across diverse domains, underscoring its broad applicability to warehouse robotics, field operations, and autonomous service vehicles. These findings confirm that the proposed wave-based framework not only bridges the gap between local heuristics and global coverage but also sets a promising direction for future extensions toward dynamic obstacle scenarios and multi-agent coordination.

This paper presents a smart checkout system designed to mitigate the issues of noise and errors present in the existing barcode and RFID-based systems used at retail stores’ checkout counters. This is achieved by integrating a novel AI algorithm, called Improved Laser Simulator Logic (ILSL) into the RFID system. The enhanced RFID system was able to improve the accuracy of item identification, reduce noise interference, and streamline the overall checkout process. The potential of the system for noise detection and elimination was initially investigated through a simulation study using MATLAB and ILSL algorithm. Subsequently, it was deployed in a small-scale environment to validate its real-world performance. Results show that RFID with the proposed new algorithm ILSL and AI basket is capable of accurately detecting the related items while eliminating noise originating from unrelated objects, achieving an accuracy rate of 88%.