In this letter,by employing Gaussian distribution to approximate the probability density function(pdf) of the extrinsic information at the output of the multiuser detector as a function of the pdf of the input extrins...In this letter,by employing Gaussian distribution to approximate the probability density function(pdf) of the extrinsic information at the output of the multiuser detector as a function of the pdf of the input extrinsic messages,it is concluded that the Probabilistic Data Association(PDA) algorithm is equivalent to the Soft Interference Cancellation plus Minimum Mean Square Error algo-rithm(SIC-MMSE) .展开更多
Joint Probabilistic Data Association (JPDA) is a very fine optimal multitarget tracking and association algorithm in clutter. However, the calculation explosion effect in computation of association probabilities has b...Joint Probabilistic Data Association (JPDA) is a very fine optimal multitarget tracking and association algorithm in clutter. However, the calculation explosion effect in computation of association probabilities has been a difficulty. This paper will discuss a method based on layered searching construction of association hypothesis events. According to the method, the searching schedule of the association events between two layers can be recursive and with independence, so it can also be implemented in parallel structure. Comparative analysis of the method with relative methods in other references and corresponding computer simulation tests and results are also given in the paper.展开更多
研究了同步定位与地图创建(SLAM)中的数据关联问题。针对环境特征数未知时,数据关联的误关联率增加,导致SLAM的定位精度偏低的问题,提出了高斯混合概率假设密度SLAM算法。首先采用UFastSLAM解决SLAM中的粒子退化和耗尽问题,其次针对地...研究了同步定位与地图创建(SLAM)中的数据关联问题。针对环境特征数未知时,数据关联的误关联率增加,导致SLAM的定位精度偏低的问题,提出了高斯混合概率假设密度SLAM算法。首先采用UFastSLAM解决SLAM中的粒子退化和耗尽问题,其次针对地图特征数未知的情况,将UFastSLAM算法中的数据关联问题转换成有限集统计理论跟踪算法的高斯混合问题,利用高斯混合概率假设密度(Gaussian Mixture Probability Hypothesis Density,GMPHD)算法解决UFastSLAM中数据关联问题。仿真实验结果表明本文提出的GMPHD-UFastSLAM算法在地图特征个数未知的情况下,数据关联准确率和定位精度都得到了提高。展开更多
文摘In this letter,by employing Gaussian distribution to approximate the probability density function(pdf) of the extrinsic information at the output of the multiuser detector as a function of the pdf of the input extrinsic messages,it is concluded that the Probabilistic Data Association(PDA) algorithm is equivalent to the Soft Interference Cancellation plus Minimum Mean Square Error algo-rithm(SIC-MMSE) .
基金Supported by Defense Advanced Research Fund of China
文摘Joint Probabilistic Data Association (JPDA) is a very fine optimal multitarget tracking and association algorithm in clutter. However, the calculation explosion effect in computation of association probabilities has been a difficulty. This paper will discuss a method based on layered searching construction of association hypothesis events. According to the method, the searching schedule of the association events between two layers can be recursive and with independence, so it can also be implemented in parallel structure. Comparative analysis of the method with relative methods in other references and corresponding computer simulation tests and results are also given in the paper.
文摘研究了同步定位与地图创建(SLAM)中的数据关联问题。针对环境特征数未知时,数据关联的误关联率增加,导致SLAM的定位精度偏低的问题,提出了高斯混合概率假设密度SLAM算法。首先采用UFastSLAM解决SLAM中的粒子退化和耗尽问题,其次针对地图特征数未知的情况,将UFastSLAM算法中的数据关联问题转换成有限集统计理论跟踪算法的高斯混合问题,利用高斯混合概率假设密度(Gaussian Mixture Probability Hypothesis Density,GMPHD)算法解决UFastSLAM中数据关联问题。仿真实验结果表明本文提出的GMPHD-UFastSLAM算法在地图特征个数未知的情况下,数据关联准确率和定位精度都得到了提高。
