为了解决路口等非结构化场景中无人驾驶车辆的运动规划问题,提出了一种改进型的矢量场直方图(Vector Field Histogram,VFH)算法。上述方法充分的考虑了车辆的动力学和运动学模型,使得依据上述方法规划的运动轨迹是可执行的和可到达的,...为了解决路口等非结构化场景中无人驾驶车辆的运动规划问题,提出了一种改进型的矢量场直方图(Vector Field Histogram,VFH)算法。上述方法充分的考虑了车辆的动力学和运动学模型,使得依据上述方法规划的运动轨迹是可执行的和可到达的,一方面,因为考虑到了最小转弯半径,能够保证在新的活动区域中的所有状态点对车辆来讲都是可到达的;另一方面,改进的代价函数综合考虑了轨迹的安全性和平滑性,保证了最终规划的运动轨迹对执行机构来讲是可执行的,实验结果表明了上述算法的有效性。展开更多
针对复杂室外场景,提出一种基于拓扑高程模型的三维环境建模方法.采用自适应可变阈值聚类算法,将映射到二维水平栅格中的激光点云划分为垂直单元和水平单元,可实现三维场景中悬空环境特征的有效表述.在此基础上对垂直单元进行高度离散采...针对复杂室外场景,提出一种基于拓扑高程模型的三维环境建模方法.采用自适应可变阈值聚类算法,将映射到二维水平栅格中的激光点云划分为垂直单元和水平单元,可实现三维场景中悬空环境特征的有效表述.在此基础上对垂直单元进行高度离散采样,从而构建与其相对应的拓扑结构,并结合BOW(Bag of words)模型对室外三维环境中的典型景物进行辨识.采用面向拓扑结构和高程图单元的分级匹配策略,实现不同场景间的精确匹配,构建具有全局一致性的拓扑高程地图.利用辨识出来的环境特征和高程地图产生双重环境约束,实现与室外地形相适应的自主路径规划.实验结果和数据分析证明了本文环境建模与路径规划方法的有效性和实用性.展开更多
Several representative studies on China's carbon emission scenarios in 2050 are compared in scenario settings, methodologies, macro parameters, energy consumption and structure, carbon emissions, and carbon emission ...Several representative studies on China's carbon emission scenarios in 2050 are compared in scenario settings, methodologies, macro parameters, energy consumption and structure, carbon emissions, and carbon emission intensity. Under the baseline scenario of the present policy framework, the future energy structure will be optimized and carbon emission intensity will decrease continually. China's carbon emissions up to 2050 show a significant increase reaching between 11.9 Gt and 16.2 Gt CO2 in 2050. By strengthening a low carbon policy, the optimization of energy structure and the decline in carbon emission intensity will become more obvious within the comparative scenarios, which show a significant decrease in carbon emission until 2050 reaching only between 4.3 Gt and 9.5 Gt CO2 bv then.展开更多
文摘为了解决路口等非结构化场景中无人驾驶车辆的运动规划问题,提出了一种改进型的矢量场直方图(Vector Field Histogram,VFH)算法。上述方法充分的考虑了车辆的动力学和运动学模型,使得依据上述方法规划的运动轨迹是可执行的和可到达的,一方面,因为考虑到了最小转弯半径,能够保证在新的活动区域中的所有状态点对车辆来讲都是可到达的;另一方面,改进的代价函数综合考虑了轨迹的安全性和平滑性,保证了最终规划的运动轨迹对执行机构来讲是可执行的,实验结果表明了上述算法的有效性。
文摘针对复杂室外场景,提出一种基于拓扑高程模型的三维环境建模方法.采用自适应可变阈值聚类算法,将映射到二维水平栅格中的激光点云划分为垂直单元和水平单元,可实现三维场景中悬空环境特征的有效表述.在此基础上对垂直单元进行高度离散采样,从而构建与其相对应的拓扑结构,并结合BOW(Bag of words)模型对室外三维环境中的典型景物进行辨识.采用面向拓扑结构和高程图单元的分级匹配策略,实现不同场景间的精确匹配,构建具有全局一致性的拓扑高程地图.利用辨识出来的环境特征和高程地图产生双重环境约束,实现与室外地形相适应的自主路径规划.实验结果和数据分析证明了本文环境建模与路径规划方法的有效性和实用性.
基金supported by the "Low Carbon Economy Academy Special Programs,Tsinghua University Independent Research Plan"
文摘Several representative studies on China's carbon emission scenarios in 2050 are compared in scenario settings, methodologies, macro parameters, energy consumption and structure, carbon emissions, and carbon emission intensity. Under the baseline scenario of the present policy framework, the future energy structure will be optimized and carbon emission intensity will decrease continually. China's carbon emissions up to 2050 show a significant increase reaching between 11.9 Gt and 16.2 Gt CO2 in 2050. By strengthening a low carbon policy, the optimization of energy structure and the decline in carbon emission intensity will become more obvious within the comparative scenarios, which show a significant decrease in carbon emission until 2050 reaching only between 4.3 Gt and 9.5 Gt CO2 bv then.