In order to realize the accurate obstacle avoidance function of intelligent car, we propose an intelligent car obstacle avoidance system based on optimized fuzzy control algorithm. Firstly, the kinematics model of int...In order to realize the accurate obstacle avoidance function of intelligent car, we propose an intelligent car obstacle avoidance system based on optimized fuzzy control algorithm. Firstly, the kinematics model of intelligent car obstacle avoidance is established, and an efficient environment information collection system composed of multiple sensors is designed to realize the comprehensive collection of obstacle information. Then, the optimized fuzzy control system is adopted to improve the position control accuracy and obstacle avoidance ability. Through the physical debugging and joint simulation of the intelligent car fuzzy controller in the MATLAB and Simulink environment, the simulation results show that the control method can make the collision-free path planned by the intelligent car from the initial state to the obstacle avoidance smoother, and at the same time, the obstacle avoidance of the intelligent car. The actual running distance is reduced by about 16%, which can ensure the practicability of the obstacle avoidance system, provide a new guarantee for the safe operation of the car, and also provide a new idea for the development of the unmanned car.展开更多
Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar perform...Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle detection.Achieving a balance between accuracy and detection speed is crucial for real-time object detection in real-world road scenes.This paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the background.Secondly,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of themodel.Finally,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid structure.Experimental results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/s.FBPN demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.展开更多
本文设计了一种基于STM32F103CBT6芯片的无人驾驶网约车调度系统。该系统由硬件和软件两部分构成,系统通过供电模块、主处理器模块、通用无线分组业务模块(General Packet Radio Service,GPRS)、全球定位系统模块(Global Positioning Sy...本文设计了一种基于STM32F103CBT6芯片的无人驾驶网约车调度系统。该系统由硬件和软件两部分构成,系统通过供电模块、主处理器模块、通用无线分组业务模块(General Packet Radio Service,GPRS)、全球定位系统模块(Global Positioning System,GPS)、Wi-Fi模块、路基单元(Road Side Unit,RSU)等硬件,采集无人驾驶网约车的运行信息及乘客的位置信息,并通过无线通信模块将其传输至上位机管理系统进行算法分析,从而确定出车策略。本系统针对目前巡游车和网约车“召唤-接单”模式的局限性,提出了一种基于优先级的淘汰算法,可提高网约车调度效率,同时也为缓解城市交通压力、提升交通运输整体效益提供了可行思路。展开更多
文摘In order to realize the accurate obstacle avoidance function of intelligent car, we propose an intelligent car obstacle avoidance system based on optimized fuzzy control algorithm. Firstly, the kinematics model of intelligent car obstacle avoidance is established, and an efficient environment information collection system composed of multiple sensors is designed to realize the comprehensive collection of obstacle information. Then, the optimized fuzzy control system is adopted to improve the position control accuracy and obstacle avoidance ability. Through the physical debugging and joint simulation of the intelligent car fuzzy controller in the MATLAB and Simulink environment, the simulation results show that the control method can make the collision-free path planned by the intelligent car from the initial state to the obstacle avoidance smoother, and at the same time, the obstacle avoidance of the intelligent car. The actual running distance is reduced by about 16%, which can ensure the practicability of the obstacle avoidance system, provide a new guarantee for the safe operation of the car, and also provide a new idea for the development of the unmanned car.
基金funded by Ministry of Science and Technology of the People’s Republic of China,Grant Numbers 2022YFC3800502Chongqing Science and Technology Commission,Grant Number cstc2020jscx-dxwtBX0019,CSTB2022TIAD-KPX0118,cstc2020jscx-cylhX0005 and cstc2021jscx-gksbX0058.
文摘Vehicle detection plays a crucial role in the field of autonomous driving technology.However,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle detection.Achieving a balance between accuracy and detection speed is crucial for real-time object detection in real-world road scenes.This paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the background.Secondly,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of themodel.Finally,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid structure.Experimental results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/s.FBPN demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.
文摘本文设计了一种基于STM32F103CBT6芯片的无人驾驶网约车调度系统。该系统由硬件和软件两部分构成,系统通过供电模块、主处理器模块、通用无线分组业务模块(General Packet Radio Service,GPRS)、全球定位系统模块(Global Positioning System,GPS)、Wi-Fi模块、路基单元(Road Side Unit,RSU)等硬件,采集无人驾驶网约车的运行信息及乘客的位置信息,并通过无线通信模块将其传输至上位机管理系统进行算法分析,从而确定出车策略。本系统针对目前巡游车和网约车“召唤-接单”模式的局限性,提出了一种基于优先级的淘汰算法,可提高网约车调度效率,同时也为缓解城市交通压力、提升交通运输整体效益提供了可行思路。
