在车辆高速剧烈运动场景下,现有激光雷达-惯性里程计(LiDAR-inertial odometry,LIO)因IMU前向传播误差的快速累积,导致车辆的运动畸变补偿精度下降,进而引发"补偿误差-配准误差-状态估计误差"的级联效应,最终造成车辆定位轨...在车辆高速剧烈运动场景下,现有激光雷达-惯性里程计(LiDAR-inertial odometry,LIO)因IMU前向传播误差的快速累积,导致车辆的运动畸变补偿精度下降,进而引发"补偿误差-配准误差-状态估计误差"的级联效应,最终造成车辆定位轨迹显著偏离真实状态,本文提出了基于迭代误差卡尔曼滤波(iterated error-state Kalman filter,IESKF)的自适应激光雷达-惯性里程计(state-adaptive update LiDAR-inertial odometry,SAU-LIO)。首先,提出基于协方差特征值阈值的动态调整策略,以实时监测LIO误差累积趋势,自适应缩短状态更新时间间隔,有效抑制剧烈运动下的误差发散;其次,结合线特征与面特征的联合提取策略,构建概率观测模型,通过观测协方差矩阵约束实现不同置信度特征的最优加权融合,实现环境特征的有效利用。最后,基于NCLT(the university of Michigan north campus long-term vision and LIDAR dataset)、UTBM(EU long-term dataset with multiple sensors for autonomous driving)标准数据集及实车试验平台的验证结果表明:SAU-LIO算法在保证实时性的前提下,与对比算法相比具有更高的定位精度,在低速工况下,平均定位误差较次优的对比算法减小14.3%,在组合工况下,平均定位误差较次优的对比算法减小9.4%。展开更多
To address the issues of poor adaptability in resource allocation and low multi-agent cooperation efficiency in Joint Radar and Communication(JRC)systems under dynamic environments,an intelligent optimization framewor...To address the issues of poor adaptability in resource allocation and low multi-agent cooperation efficiency in Joint Radar and Communication(JRC)systems under dynamic environments,an intelligent optimization framework integrating Deep Reinforcement Learning(DRL)and Graph Neural Network(GNN)is proposed.This framework models resource allocation as a Partially Observable Markov Game(POMG),designs a weighted reward function to balance radar and communication efficiencies,adopts the Multi-Agent Proximal Policy Optimization(MAPPO)framework,and integrates Graph Convolutional Networks(GCN)and Graph Sample and Aggregate(Graph-SAGE)to optimize information interaction.Simulations show that,compared with traditional methods and pure DRL methods,the proposed framework achieves improvements in performance metrics such as communication success rate,Average Age of Information(AoI),and policy convergence speed,effectively enabling resource management in complex environments.Moreover,the proposed GNN-DRL-based intelligent optimization framework obtains significantly better performance for resource management in multi-agent JRC systems than traditional methods and pure DRL methods.展开更多
文摘在车辆高速剧烈运动场景下,现有激光雷达-惯性里程计(LiDAR-inertial odometry,LIO)因IMU前向传播误差的快速累积,导致车辆的运动畸变补偿精度下降,进而引发"补偿误差-配准误差-状态估计误差"的级联效应,最终造成车辆定位轨迹显著偏离真实状态,本文提出了基于迭代误差卡尔曼滤波(iterated error-state Kalman filter,IESKF)的自适应激光雷达-惯性里程计(state-adaptive update LiDAR-inertial odometry,SAU-LIO)。首先,提出基于协方差特征值阈值的动态调整策略,以实时监测LIO误差累积趋势,自适应缩短状态更新时间间隔,有效抑制剧烈运动下的误差发散;其次,结合线特征与面特征的联合提取策略,构建概率观测模型,通过观测协方差矩阵约束实现不同置信度特征的最优加权融合,实现环境特征的有效利用。最后,基于NCLT(the university of Michigan north campus long-term vision and LIDAR dataset)、UTBM(EU long-term dataset with multiple sensors for autonomous driving)标准数据集及实车试验平台的验证结果表明:SAU-LIO算法在保证实时性的前提下,与对比算法相比具有更高的定位精度,在低速工况下,平均定位误差较次优的对比算法减小14.3%,在组合工况下,平均定位误差较次优的对比算法减小9.4%。
基金funded by Shandong Provincial Natural Science Foundation,grant number ZR2023MF111.
文摘To address the issues of poor adaptability in resource allocation and low multi-agent cooperation efficiency in Joint Radar and Communication(JRC)systems under dynamic environments,an intelligent optimization framework integrating Deep Reinforcement Learning(DRL)and Graph Neural Network(GNN)is proposed.This framework models resource allocation as a Partially Observable Markov Game(POMG),designs a weighted reward function to balance radar and communication efficiencies,adopts the Multi-Agent Proximal Policy Optimization(MAPPO)framework,and integrates Graph Convolutional Networks(GCN)and Graph Sample and Aggregate(Graph-SAGE)to optimize information interaction.Simulations show that,compared with traditional methods and pure DRL methods,the proposed framework achieves improvements in performance metrics such as communication success rate,Average Age of Information(AoI),and policy convergence speed,effectively enabling resource management in complex environments.Moreover,the proposed GNN-DRL-based intelligent optimization framework obtains significantly better performance for resource management in multi-agent JRC systems than traditional methods and pure DRL methods.
