类脑同步定位与建图(simultaneous localization and mapping,SLAM)通过模仿大脑神经导航机制实现环境建模,同时获得环境中的位置信息,具有较好的导航能力与较高的鲁棒性,但当前的类脑SLAM系统大都在预先获取的环境数据集上进行定位建图,对于新环境的兼容性较差.为此提出一种主动的类脑SLAM方法,设计基于Bug算法的环境自主探索方法,驱动机器人在环境中自主移动,主动获取环境信息,同时调用经典的类脑SLAM(RatSLAM)方法对环境信息进行处理,形成环境的认知地图.仿真环境和真实环境下的实验结果表明,本文方法取得了较好的建图效果,与通过人工采集数据建立的环境地图相似度较高,具备可行性.
Abstract
With brain-inspired simultaneous localization and mapping(SLAM),environmental modeling can be achieved and location information can be obtained by imitating the brain neural navigation mechanism.SLAM has good navigation ability and high robustness.However,most of the current brain-inspired SLAM systems perform localization and mapping on pre-acquired envi-ronmental data sets,and have poor compatibility with new environment.For this case,an active brain-inspired SLAM method is proposed.An autonomous exploration method based on Bug algo-rithm is designed to drive the robot to move autonomously in the environment and actively obtain environmental information.During the movements of the robot,one classical brain-inspired SLAM referred to as RatSLAM is utilized to process the environment data and subsequently obtain the ex-perience map of the environment.The experimental results in both simulation and the real environ-ment show that the proposed method has achieved good mapping results,and has a high similarity with the environmental map established by manually collecting data,it is feasible.
维普
万方数据