Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3246-3251.DOI: 10.11772/j.issn.1001-9081.2023101389

• Frontier and comprehensive applications • Previous Articles     Next Articles

Self-recovery adaptive Monte Carlo localization algorithm based on support vector machine

Enbao QIAO1,2, Xiangyang GAO2, Jun CHENG2()   

  1. 1.Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology),Guilin Guangxi 541006,China
    2.Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen Guangdong 518055,China
  • Received:2023-10-16 Revised:2023-12-27 Accepted:2024-01-08 Online:2024-10-15 Published:2024-10-10
  • Contact: Jun CHENG
  • About author:QIAO Enbao, born in 1996, M. S. candidate. His research interests include intelligent robots, embedded systems.
    GAO Xiangyang, born in 1982, M. S., senior engineer. His research interests include intelligent robots, embedded systems.
  • Supported by:
    National Natural Science Foundation of China(U21A20487)

基于支持向量机的自恢复自适应蒙特卡洛定位算法

乔恩保1,2, 高向阳2, 程俊2()   

  1. 1.广西高校先进制造与自动化技术重点实验室(桂林理工大学),广西 桂林 541006
    2.中国科学院 深圳先进技术研究院,广东 深圳 518055
  • 通讯作者: 程俊
  • 作者简介:乔恩保(1996—),男,安徽阜阳人,硕士研究生,CCF会员,主要研究方向:智能机器人、嵌入式系统
    高向阳(1982—),男,陕西咸阳人,高级工程师,硕士,主要研究方向:智能机器人、嵌入式系统
    程俊(1977—),男,安徽桐城人,研究员,博士,主要研究方向:机器视觉、智能机器人、人工智能 jun.cheng@siat.ac.cn
  • 基金资助:
    国家自然科学基金资助项目(U21A20487)

Abstract:

The localization technology of robots is crucial for the efficient, precise, and safe operation of intelligent robots. However, in actual localization processes, robots often encounter the “kidnapping” problem. In response to this challenge, a Self-Recovery Adaptive Monte Carlo Localization (AMCL) algorithm based on Support Vector Machine (SVM-SRAMCL) was proposed. Firstly, a detection model was constructed to identify the “kidnapping” state of the robot, known as the Kidnapping Detection Model based on SVM (SVM-KDM). Then, particle characteristic values were calculated from the particle set obtained through the AMCL algorithm and used as inputs for SVM-KDM. Once a “kidnapping” event was detected, an Extended Kalman Filter (EKF) was employed to fuse data from the Inertial Measurement Unit (IMU) and Odometry (Odom) to estimate the robot’s new pose. Finally, the AMCL algorithm was utilized for particle prediction, update, and resampling, ultimately achieving the robot’s relocalization. Compared to the Self-Recovery Monte Carlo Localization (SR-MCL) algorithm, the proposed algorithm reduced 4.1 required updates for post-kidnapping recovery and increased the success rate of relocalization by 3 percentage points. The experimental results validate the higher efficiency and success rate of the proposed algorithm when addressing the “kidnapping” issue in the localization of mobile robots.

Key words: mobile robot, Extended Kalman Filter (EKF), Support Vector Machine (SVM), location recovery, Adaptive Monte Carlo Localization (AMCL)

摘要:

机器人定位技术对智能机器人的高效、精确和安全运行至关重要,然而在实际的定位过程中,机器人常面临“绑架”问题。为了应对这一难题,提出一种基于支持向量机(SVM)的自恢复自适应蒙特卡洛定位(SVM-SRAMCL)算法。首先,构建用于识别机器人“绑架”状态的检测模型——基于SVM的绑架检测模型(SVM-KDM);其次,通过自适应蒙特卡洛定位(AMCL)算法所得的粒子集计算粒子特性值,并作为SVM-KDM的输入,一旦检测到“绑架”事件,使用扩展卡尔曼滤波器(EKF)融合惯性测量单元(IMU)和里程计(Odom)的数据估计机器人的新位姿;最后,使用AMCL算法进行粒子预测、更新和重采样,最终实现机器人的重新定位。相较于自恢复蒙特卡洛定位(SR-MCL)算法,绑架后恢复定位所需的更新减少了4.1次,重定位的成功率提高了3个百分点。实验结果验证了所提算法在解决移动机器人的定位“绑架”问题方面具有更高的效率和成功率。

关键词: 移动机器人, 拓展卡尔曼滤波器, 支持向量机, 定位恢复, 自适应蒙特卡洛定位

CLC Number: