基于陆标动态配置的移动机器人主动探索

Mobile robot active exploration based on dynamic deployment of landmarks

针对无预置陆标的环境,研究移动机器人动态在线配置陆标问题及基于此的主动探索.首先,提出陆标动态在线配置准则,并分析陆标配置对机器人定位与建图的影响;然后基于扩展的卡尔曼滤波器,将机器人的主动探索转化为多目标最优控制问题,优化目标包含3个部分,分别对应定位与建图的准确性、机器人预期探索的新区域大小和陆标配置对定位与建图的影响,机器人选取最优化目标函数的控制输入以实现准确的定位、建图和对环境的充分探索;最后对陆标进行有效的增补和去冗余.仿真结果表明该方法的有效性。

The on-line dynamic deployment of landmarks and the active exploration in environment without pre-placed landmarks are investigated. Firstly, the rules for landmark deployment are proposed and the effect of the deployed landmarks is analyzed. Secondly, based on the extended Kalman filter （EKF）, we convert the active exploration into a problem of multi-objective optimal control, in which the objective function includes three parts, i.e. the accuracy of localization and mapping, the predictive area of the unknown environment to be explored by the robot, and the information obtained from the deployed landmarks. The robot employs the control inputs that optimize the objective function such that the accurate map building and the complete exploration are realized. Afterwards, the supplementation and the redundancy elimination for landmarks are implemented. Finally, the simulation is presented to show the effectiveness of our approach.