Laser-based cooperative tracking of vehicles and people by multiple mobile robots in GNSS-denied environments

DOI PDF 参考文献25件 オープンアクセス

書誌事項

公開日
2017-07
資源種別
journal article
DOI
  • 10.1109/aim.2017.8014186
公開者
IEEE

説明

This paper presents laser-based tracking (estimation of pose and size) of moving objects using multiple mobile robots as sensor nodes in Global navigation satellite system (GNSS)-denied environments. Each sensor node is equipped with a multilayer laser scanner and detects moving objects, such as people, cars, and bicycles, in its own laser-scanned images by applying an occupancy-grid-based method. It then sends measurement information related to the moving objects to a central server. The central server estimates the objects' poses (positions and velocities) and sizes using Bayesian filter. In this cooperative-tracking method, the nearby sensor nodes always share their tracking information, allowing tracking of invisible or partially visible objects. To perform reliable cooperative tracking, sensor nodes should accurately identify their relative pose. In GNSS-denied environments, the relative pose is estimated by scan matching using laser measurements captured by nearby sensor nodes. Such cooperative scan matching is performed by 4-points congruent sets (4PCS) matching method for coarse registration and Iterative closest point (ICP) method for fine registration. The experimental results of tracking a car, a motorcycle, and a pedestrian with two sensor nodes in an outdoor GNSS-denied environment validate the proposed method.

収録刊行物

参考文献 (25)*注記

もっと見る

関連プロジェクト

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ