首页> 外文会议>International technical meeting of the Satellite Division of the Institute of Navigation >SmartSLAM – an efficient smartphone indoor positioning system exploiting machine learning and opportunistic sensing
【24h】

SmartSLAM – an efficient smartphone indoor positioning system exploiting machine learning and opportunistic sensing

机译:SmartSLAM –利用机器学习和机会感测的高效智能手机室内定位系统

获取原文

摘要

The most promising solution to the ubiquitouspositioning problem is the smartphone, and many smartphonebasedindoor tracking methods exist today. To ensure consumeracceptance of the technologies, it is critical that these systems donot have a significant effect on the battery life of the device.Methods exploiting signal fingerprinting have been shown toprovide good performance with low processing overhead butrequire prior surveying. Methods exploiting opportunisticsensing and machine learning techniques such as SimultaneousLocalization and Mapping (SLAM) need no prior data but at thecost of high computational load. This paper describes asmartphone-based indoor positioning system that exploits a newintelligent filtering approach to reduce this computational load.SmartSLAM moves between different sensor fusion algorithmsdepending on the current level of certainty in the system,reducing the computational load of the tracking engine,maintaining good positioning performance, improving batterylife and freeing CPU cycles for foreground processes.
机译:解决无处不在的最有希望的解决方案 定位问题是智能手机,而且很多基于智能手机的 室内追踪方法已存在。为了确保消费者 接受技术,这些系统必须做到 不会对设备的电池寿命产生重大影响。 已经证明利用信号指纹的方法可以 以较低的处理开销提供良好的性能,但 需要事先调查。利用机会主义的方法 感应和机器学习技术,例如“同步” 本地化和映射(SLAM)不需要先验数据,而只需 高计算量的成本。本文介绍了一个 基于智能手机的室内定位系统,该系统利用了新的 智能过滤方法来减少这种计算量。 SmartSLAM在不同的传感器融合算法之间移动 根据系统当前的确定性水平, 减少跟踪引擎的计算量, 保持良好的定位性能,改善电池 寿命并释放CPU周期供前台进程使用。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号