Two-wheeled balancing Mobile Robots (2WBMRs) are inherently unstable, posing significant challenges in control. This paper addresses the problem of optimizing control parameters for such systems to improve stability and overall performance. The proposed solution integrates Hierarchical Sliding Mode Control (HSMC) with the Firefly Algorithm, which is a stochastic algorithm inspired by the flashing behavior of fireflies, to optimize control performance. The research contribution is the development of an optimized control system where the Firefly Algorithm is used to fine-tune HSMC parameters, ensuring improved stability and responsiveness. Additionally, the integration of Sliding Mode Control (SMC) within the HSMC framework provides precise yaw angle stabilization, contributing to comprehensive robot control. In this approach, the Firefly Algorithm is applied to optimize the HSMC parameters due to its capability to optimize multidimensional variables and its robust optimization abilities, aiming to enhance the stability of the vehicle in the best possible way. Simulations were conducted to compare the proposed method before and after applying the optimization algorithm, evaluating key performance metrics such as response time and stability. The results indicate a (10%) improvement in stability, demonstrating that the Firefly Algorithm significantly enhances control performance. These findings suggest that the optimized control system not only improves the stability of 2WBMRs but also has potential applications in broader dynamic control systems. In conclusion, based on the research results, we can conclude that the use of the HSMC-SMC controller for nonlinear systems like 2WBMRs is feasible and can be applied to many other nonlinear systems. Furthermore, the Firefly Algorithm has proven to be a powerful tool for optimizing parameters in control systems and can be applied in robotics and automation systems.
Despite the significant advancements in learning-based stereo matching algorithms, a significant challenge remains: the high computational cost and memory demands of 3D convolutions, which hinder real-time deployment on resource-constrained platforms like edge devices. In this paper, we present a novel approach that completely avoids the use of 3D convolutions, with the goal of achieving faster inference speeds while maintaining comparable accuracy to existing state-of-the-art methods. Our proposed solution revolves around a 2D cost aggregation technique, which serves as a viable alternative to traditional 3D convolutions, delivering similar results in terms of accuracy. This innovative method significantly reduces computational overhead, facilitating more efficient resource utilization and paving the way for real-time applications. Complementing our 2D cost aggregation module, we introduce a multi-stage feature extractor, designed to enhance feature representation while remaining straightforward and lightweight. The integration of the 2D cost aggregation and multi-stage feature extraction results in an efficient architecture for cost aggregation, simplifying the model and ensuring computational efficiency without sacrificing accuracy. This framework delivers high-performance stereo matching suitable for devices with limited computational capabilities. Through evaluation on benchmark datasets, we demonstrate the effectiveness of our approach, highlighting its potential for real-time 3D perception in applications. By addressing the constraints imposed by 3D convolutions and offering a more pragmatic alternative, this work bridges the gap between high-performance stereo matching algorithms and the realities of edge computing environments.
Adverse weather (rain, fog, snow) corrupts LiDAR through backscatter and attenuation, producing near-range clutter and far-range sparsity that degrade downstream perception and planning. Classical geometric filters depend on hand-tuned thresholds and often erode valid structure at long range; recent learning methods improve accuracy but are heavy for embedded deployment. We present LRINet, a straightforward and efficient range-image network for denoising LiDAR point clouds in adverse weather. LRINet operates entirely in a 2-D cylindrical projection. This approach preserves sensor topology and ensures computational efficiency. The network pairs depth-guided attention with a coordinate encoder and a global-context block. It then uses an attention-gated decoder for the final output. Despite its minimalist design, LRINet delivers competitive performance against state-of-the-art methods across rainy, foggy, and snowy conditions while maintaining a markedly smaller memory and latency footprint suitable for real-time on-board use. Experiments on climate-chamber rain/fog data and semi-synthetic snowy driving data show a practical balance of accuracy, robustness, and throughput, making LRINet a drop-in preprocessing module for safety-critical autonomy stacks.