The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving sy...The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.展开更多
Although the development of machine intelligence is far from simulating all the cognitive competence of our brains, still it is absolutely possible to peel the driving activity from people＇s cognitive activities and ...Although the development of machine intelligence is far from simulating all the cognitive competence of our brains, still it is absolutely possible to peel the driving activity from people＇s cognitive activities and then make the machine finish some low-level, complicated and lasting driving cognition by simulating our brains. The goal of driving is to replace drivers and free them from boring driving activities. Based on some studies on unmanned driving, this paper summarizes and analyzes the background, significance, research status and key technology of unmanned driving and the research group also introduces some research on brain cognition of driving and sensor placement of intelligent vehicles, which offers more meaningful reference to push the study of unmanned driving.展开更多
井下斜坡道的定位与建图是实现井下斜坡道无人驾驶的关键技术之一,矿山井下斜坡道区域为典型非结构化环境特征,且道路具有一定倾斜角度,采用传统SLAM算法无法获得精确里程计信息,导致定位与建图精度难以满足无人矿卡行驶需求。针对上述...井下斜坡道的定位与建图是实现井下斜坡道无人驾驶的关键技术之一,矿山井下斜坡道区域为典型非结构化环境特征,且道路具有一定倾斜角度,采用传统SLAM算法无法获得精确里程计信息,导致定位与建图精度难以满足无人矿卡行驶需求。针对上述问题,通过研究激光SLAM(Simultaneous Localization And Mapping)算法LeGO-LOAM,笔者提出一种适用于矿山井下斜坡道环境的定位与建图方法。首先,针对井下斜坡道口两侧均为光滑水泥墙壁,特征点稀少问题,设计了基于人工路标的辅助增强定位方法,有效增加点云特征数量,从而优化位姿估计结果,避免建图漂移现象;然后在特征预处理阶段,提出了一种基于激光点云高度差与坡度信息融合的提取地面点高效算法,通过改善地面地点的选取策略,针对倾斜坑洼路面仍能有效识别地面点,解决了井下斜坡道定位与建图倾斜角度大、误差大等问题;其次,基于CVC(Curved-Voxel Clustering)聚类算法设计了一种斜坡道点云曲率体素聚类算法,采用曲率体素和基于哈希的数据结构对点云进行分割,大幅提高在井下稀疏、噪声环境下点云聚类的鲁棒性;最后,运用Scan-To-Map进行点云匹配,同时兼顾点云配准的性能与速度。在中钢集团山东某井下斜坡道的现场实验证明:与原算法相比精度提升13.15%,Z轴误差降低22.3%,地图质量明显提升,能有效解决井下无人驾驶建图及定位的难题。展开更多
无人驾驶技术的关键是决策层根据感知环节输入信息做出准确指令。强化学习和模仿学习比传统规则更适用于复杂场景。但以行为克隆为代表的模仿学习存在复合误差问题,使用优先经验回放算法对行为克隆进行改进,提升模型对演示数据集的拟合...无人驾驶技术的关键是决策层根据感知环节输入信息做出准确指令。强化学习和模仿学习比传统规则更适用于复杂场景。但以行为克隆为代表的模仿学习存在复合误差问题,使用优先经验回放算法对行为克隆进行改进,提升模型对演示数据集的拟合能力;原DDPG(deep deterministic policy gradient)算法存在探索效率低下问题,使用经验池分离以及随机网络蒸馏技术(random network distillation,RND)对DDPG算法进行改进,提升DDPG算法训练效率。使用改进后的算法进行联合训练,减少DDPG训练前期的无用探索。通过TORCS(the open racing car simulator)仿真平台验证,实验结果表明该方法在相同的训练次数内,能够探索出更稳定的道路保持、速度保持和避障能力。展开更多
露天矿区场景复杂,行车障碍物检测受扬尘和颗粒物等粉尘噪声干扰严重,难以准确识别障碍物,尤其是光线较差的夜间,不利于做出正确决策,从而影响无人作业的安全性和整体效率。针对以上问题,提出了一种基于YOLOv8n模型的露天矿区行车障碍...露天矿区场景复杂,行车障碍物检测受扬尘和颗粒物等粉尘噪声干扰严重,难以准确识别障碍物,尤其是光线较差的夜间,不利于做出正确决策,从而影响无人作业的安全性和整体效率。针对以上问题,提出了一种基于YOLOv8n模型的露天矿区行车障碍物检测算法YOLOv8n-Enhanced。该算法主要从3个方面进行了改进,具体包括:首先,针对受粉尘噪声干扰严重和夜间光线不足的问题,提出了C2fCA模块结构,提高了模型特征提取能力;其次,使用轻量级卷积技术GSConv和VoV-GSCSP模块,减轻模型复杂性,实现检测器更高的计算成本效益;最后,使用WIOU损失函数,提高了模型泛化能力。试验结果表明:改进算法在保持实时性的前提下,可将YOLOv8n的平均精度(mean Average Precision,mAP)分别提高1.8%和2.6%,实现白天与夜间场景下不同尺度的障碍物识别。展开更多
为了提高无人方程式赛车运行的安全性,设计了一种基于鸿蒙系统的无人方程式赛车远程监控与数据管理系统。该系统主要包括数据采集软件、远程监控平台、云数据库。数据采集软件使用鸿蒙系统开发,通过使用控制器局域网(controller area ne...为了提高无人方程式赛车运行的安全性,设计了一种基于鸿蒙系统的无人方程式赛车远程监控与数据管理系统。该系统主要包括数据采集软件、远程监控平台、云数据库。数据采集软件使用鸿蒙系统开发,通过使用控制器局域网(controller area network,CAN)总线传输、蓝牙传输、WebSocket协议、HTTP协议,实现对CAN数据的解析、显示、转发。监控系统使用Spring Boot框架开发,实现对无人方程式赛车的远程监控。云数据库使用MySQL数据库开发,实现无人方程式赛车数据的快速存储。测试结果表明,该套系统可以实现对无人方程式赛车的远程监控,实现十万级以上数据量低延迟储存,数据丢失率平均为0.0424%。目前,该套系统已经应用到无人方程式赛车的调试中。展开更多
基金supported in part by the National Key RD Program of China (2021YFF0602104-2,2020YFB1804604)in part by the 2020 Industrial Internet Innovation and Development Project from Ministry of Industry and Information Technology of Chinain part by the Fundamental Research Fund for the Central Universities (30918012204,30920041112).
文摘The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.
基金This work is supported by National Natural Science Foundation of China under Grant No. 61300006, No. 61305055, No. 61035004, No. 61273213, No. 61203366 and No. 90920305, and China National High-Tech Project （863） under grant No. 2015AA015401, and Chinese Academy of engineering consulting Project No. 2015-XY-42.
文摘Although the development of machine intelligence is far from simulating all the cognitive competence of our brains, still it is absolutely possible to peel the driving activity from people＇s cognitive activities and then make the machine finish some low-level, complicated and lasting driving cognition by simulating our brains. The goal of driving is to replace drivers and free them from boring driving activities. Based on some studies on unmanned driving, this paper summarizes and analyzes the background, significance, research status and key technology of unmanned driving and the research group also introduces some research on brain cognition of driving and sensor placement of intelligent vehicles, which offers more meaningful reference to push the study of unmanned driving.
文摘井下斜坡道的定位与建图是实现井下斜坡道无人驾驶的关键技术之一,矿山井下斜坡道区域为典型非结构化环境特征,且道路具有一定倾斜角度,采用传统SLAM算法无法获得精确里程计信息,导致定位与建图精度难以满足无人矿卡行驶需求。针对上述问题,通过研究激光SLAM(Simultaneous Localization And Mapping)算法LeGO-LOAM,笔者提出一种适用于矿山井下斜坡道环境的定位与建图方法。首先,针对井下斜坡道口两侧均为光滑水泥墙壁,特征点稀少问题,设计了基于人工路标的辅助增强定位方法,有效增加点云特征数量,从而优化位姿估计结果,避免建图漂移现象;然后在特征预处理阶段,提出了一种基于激光点云高度差与坡度信息融合的提取地面点高效算法,通过改善地面地点的选取策略,针对倾斜坑洼路面仍能有效识别地面点,解决了井下斜坡道定位与建图倾斜角度大、误差大等问题;其次,基于CVC(Curved-Voxel Clustering)聚类算法设计了一种斜坡道点云曲率体素聚类算法,采用曲率体素和基于哈希的数据结构对点云进行分割,大幅提高在井下稀疏、噪声环境下点云聚类的鲁棒性;最后,运用Scan-To-Map进行点云匹配,同时兼顾点云配准的性能与速度。在中钢集团山东某井下斜坡道的现场实验证明:与原算法相比精度提升13.15%,Z轴误差降低22.3%,地图质量明显提升,能有效解决井下无人驾驶建图及定位的难题。
文摘无人驾驶技术的关键是决策层根据感知环节输入信息做出准确指令。强化学习和模仿学习比传统规则更适用于复杂场景。但以行为克隆为代表的模仿学习存在复合误差问题,使用优先经验回放算法对行为克隆进行改进,提升模型对演示数据集的拟合能力;原DDPG(deep deterministic policy gradient)算法存在探索效率低下问题,使用经验池分离以及随机网络蒸馏技术(random network distillation,RND)对DDPG算法进行改进,提升DDPG算法训练效率。使用改进后的算法进行联合训练,减少DDPG训练前期的无用探索。通过TORCS(the open racing car simulator)仿真平台验证,实验结果表明该方法在相同的训练次数内,能够探索出更稳定的道路保持、速度保持和避障能力。
文摘露天矿区场景复杂,行车障碍物检测受扬尘和颗粒物等粉尘噪声干扰严重,难以准确识别障碍物,尤其是光线较差的夜间,不利于做出正确决策,从而影响无人作业的安全性和整体效率。针对以上问题,提出了一种基于YOLOv8n模型的露天矿区行车障碍物检测算法YOLOv8n-Enhanced。该算法主要从3个方面进行了改进,具体包括:首先,针对受粉尘噪声干扰严重和夜间光线不足的问题,提出了C2fCA模块结构,提高了模型特征提取能力;其次,使用轻量级卷积技术GSConv和VoV-GSCSP模块,减轻模型复杂性,实现检测器更高的计算成本效益;最后,使用WIOU损失函数,提高了模型泛化能力。试验结果表明:改进算法在保持实时性的前提下,可将YOLOv8n的平均精度(mean Average Precision,mAP)分别提高1.8%和2.6%,实现白天与夜间场景下不同尺度的障碍物识别。
文摘为了提高无人方程式赛车运行的安全性,设计了一种基于鸿蒙系统的无人方程式赛车远程监控与数据管理系统。该系统主要包括数据采集软件、远程监控平台、云数据库。数据采集软件使用鸿蒙系统开发,通过使用控制器局域网(controller area network,CAN)总线传输、蓝牙传输、WebSocket协议、HTTP协议,实现对CAN数据的解析、显示、转发。监控系统使用Spring Boot框架开发,实现对无人方程式赛车的远程监控。云数据库使用MySQL数据库开发,实现无人方程式赛车数据的快速存储。测试结果表明,该套系统可以实现对无人方程式赛车的远程监控,实现十万级以上数据量低延迟储存,数据丢失率平均为0.0424%。目前,该套系统已经应用到无人方程式赛车的调试中。
