Simple and efficient geometric controllers, like Pure-Pursuit, have been widely used in various types of autonomous vehicles to solve tracking problems. In this paper, we developed a new pursuit method, named CF-Pursuit, which has based on Pure-Pursuit but with certain differences. order reduce fitting errors, clothoid C 1 curve replace the circle employed Pure-Pursuit. This improvement method helps Pursuit decrease errors. As regards selection look-ahead distance, fuzzy system directly...

Autonomous driving is experiencing rapid development. A lane-level map essential for autonomous driving, and a road network fundamental part of map. large amount research has been performed on generation based various on-board systems. However, there lack analysis summaries with regards to previous work. This paper presents an overview techniques the maps vehicles systems, including representation networks. First, sensors data collection are discussed. Then, geometry extraction methods...

Path planning is a crucial component of autonomous mobile robot (AMR) systems. The slime mould algorithm (SMA), as one the most popular path-planning approaches, shows excellent performance in AMR field. Despite its advantages, there still room for SMA to improve due lack mechanism jumping out local optimization. This means that improvement path ARM based on this method. To find shorter and more stable paths, an improved SMA, called Lévy flight-rotation (LRSMA), proposed. LRSMA utilizes...

The rapid advancement of artificial intelligence technology has significantly enhanced the mobile robots, facilitating their widespread utilization in unmanned driving, smart home systems, and various other domains. As scope, scale, complexity robot deployment continue to expand, there arises a heightened demand for computational power real-time performance, with path planning emerging as prominent research focus. In this study, we present an adaptive Lévy flight–rotation slime mold...

High-definition (HD) maps have gained increasing attention in highly automated driving technology and show great significance for self-driving cars. An HD road network (HDRN) is one of the most important parts an map. To date, there been few studies focusing on road-segment extraction automatic generation HDRN. improve precision HDRN further represent topological relations between segments lanes better, this paper, we propose model (HDRNM) a car. The HDRNM divides into layer road-network...

With the development of autonomous driving, lane-level maps have attracted significant attention. Since road network is an important part map, efficient, low-cost, and automatic generation networks has become increasingly important. We propose a new method here that generates using only position information based on vehicle existing from road-level professionally surveyed without lane details. This uses parallel relationship between centerline corresponding segment. direct point-by-point...

摘要: 针对经典集总参数模型无法表述半主动悬置幅变特性的问题,建立了修正的集总参数模型,用于描述半主动悬置的幅变特性。首先,在MTS831试验台上分别对半主动悬置和橡胶主簧进行了不同位移振幅激励下的动特性试验。根据试验结果,采用遗传算法对半主动悬置的主要集总参数进行了辨识,确定了受幅值影响较大的集总参数。其次,根据参数辨识结果,采用幂指数模型拟合了惯性通道液阻的幅变修正系数,应用二次多项式响应面方法获得了橡胶主簧动特性关于幅值和频率的回归方程,最终建立了修正的集总参数模型。修正的集总参数模型不仅能同时反映半主动悬置的幅变和频变特性,还具有很好的预测功能。通过修正的集总参数模型,分析了半主动悬置幅变动特性的产生机理。

For the purpose of dealing with closely-spaced and spectrally-overlapped sources, a direction-of-arrival (DOA) estimation algorithm based on time-frequency (TF) sparse representation is proposed. Firstly short-time Fourier transform (STFT) single-source TF points selection method briefly introduced. On this basis, we extract STFT values corresponding to each source from array outputs construct received data matrix. We then enforce sparsity by imposing l1 norm penalties signal solve...

Autonomous mobile robot encompasses modules such as perception, path planning, decision-making, and control. Among these modules, planning serves a prerequisite for robots to accomplish tasks. Enhancing capability of can effectively save costs, reduce energy consumption, improve work efficiency. The primary slime mold algorithm (SMA) exhibits characteristics reduced number parameters, strong robustness, relatively high level exploratory ability. SMA performs well in robots. However, it is...