レーザスキャナを搭載する複数移動ロボットによる非GNSS環境下での協調移動物体追跡

抄録

This paper presents a laser-based tracking (estimation of pose and size) of moving objects using multiple mobile robots in outdoor GNSS-denied environments. Each robot 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 and sizes from the measurement information using Bayesian filter. To perform a reliable cooperative tracking, robots should accurately identify their relative pose. In the GNSS-denied environment, the relative pose is estimated by scan matching using laser measurements captured by nearby robots. Such cooperative scan matching is performed by 4-points-congruent-sets (4PCS)-based coarse registration and Iterative-closest-point (ICP)-based fine registration methods. The experimental results validate the proposed method.