网络出版地址：http://www.cnki.net/kcms/detail/23.1538.tp.20150508.1546.002.html

一种未知环境下机器人多目标跟踪算法

伍明，李琳琳，魏振华，汪洪桥

(第二炮兵工程大学 指挥信息工程系，陕西 西安 710025)

摘要：针对未知环境下移动机器人多目标跟踪问题，设计了一种基于联合概率数据关联的粒子滤波算法。该算法利用联合概率数据关联方法对Rao-Blackwellized粒子滤波算法进行改进，使机器人能够完成未知环境条件下对自身状态、环境特征状态和多目标状态的在线联合估计。算法将系统状态变量分为代表多目标、环境特征状态的线性变量和代表机器人状态的非线性变量，并利用联合概率数据关联Kalman滤波和粒子滤波对系统状态进行更新。通过仿真实验证明了该算法对机器人状态、环境特征状态以及多目标状态的估计准确性，验证了算法对未知环境下多目标的跟踪能力。

关键词：机器人；同时定位与地图构建；多目标跟踪；粒子滤波；联合概率数据关联；Rao-Blackwellised粒子滤波；Kalman滤波

DOI:10.3969/j.issn.1673-4785.201405051

中图分类号：TP242.6 文献标志码：A

收稿日期：2014-05-23. 网络出版日期：2015-05-08.

基金项目：国家自然科学基金资助项目(61202332)；陕西省自然科学基础研究计划项目(2013JQ8030).

作者简介：

中文引用格式：伍明，李琳琳，魏振华，等. 一种未知环境下机器人多目标跟踪算法[J]. 智能系统学报, 2015, 10(3): 448-453.

英文引用格式：WU Ming, LI Linlin, WEI Zhenhua, et al. A robot multi-object tracking algorithm in unknown environments[J]. CAAI Transactions on Intelligent Systems, 2015, 10(3): 448-453.

A robot multi-object tracking algorithm in unknown environments

WU Ming, LI Linlin, WEI Zhenhua, WANG Hongqiao

(Command Information Engineering Department, The Second Artillery Engineering College, Xian 710025, China)

Abstract：In this paper, a particle filtering algorithm based on the joint integrated probabilistic data association (JIPDA) is proposed in order to solve the problem of motile robot multi-object tracking in unknown environments. The Rao-Blackwellized particle filtering is reconstructed based on the JIPDA in the new algorithm. It allows the robot to estimate joint states of itself, environment features and multi-object states simultaneously. The algorithm divides the system variables into two parts: the lineal variable representing multi-object and environment feature states, and the non-linear variable representing robot states. The system state is updated by JIPDA Kalman filtering and particle filtering. Estimation precision of robot states, environment feature states and multi-object states is verified by simulation results, verifying the ability of multi-object tracking in unknown environments.

Keywords：robot; simultaneous localization and mapping (SLAM); multi-object tracking; particle filtering; joint integrated probabilistic data association (JIPDA); Rao-Blackwellized particle filtering; Kalman filtering

通信作者：伍明. E-mail: hyacinth531@163.com.

机器人同时定位与地图构建问题(simultaneous localization and mapping, SLAM)和目标跟踪问题(object tracking, OT)在机器人学界通常被作为2个独立问题加以研究，而对于某些实际任务，需要将SLAM和OT问题作为耦合问题来处理，例如未知环境下目标跟踪任务[1]、未知环境下机器人围捕任务[2-3]。……