基于识别图模型的多足机器人导航数据提取信息方法Information Extraction Method of Beidou Navigation Data Based on Identification Graphical Model
刘罡,朱茂飞,张春鹏,钟华
摘要(Abstract):
从传感器数据中学习行为模式对于高级活动推理极其重要。展示了如何从北斗导航数据的痕迹中提取多足机器人的活动和重要的地方。设计的系统使用识别图模型中的分层条件随机场来生成多足机器人的活动和地点的一致模型。实验显示了系统能够使用收集的数据中训练的模型来稳健地估计多足机器人的活动。
关键词(KeyWords): 识别图;条件随机场;多足机器人;北斗导航数据
基金项目(Foundation): 合肥学院科学研究发展基金项目(20ZR01ZDA);; 新能源汽车产业创新发展和推广应用政策支持研发创新项目(wfgcyh2020447)
作者(Author): 刘罡,朱茂飞,张春鹏,钟华
参考文献(References):
- [1] P.Abbeel,A.Coates,M.Montemerlo,A.Ng,and S.Thrun.Discriminative training of Kalman filters.In Proc.of Robotics:Science and Systems,2005.
- [2] D.Anguelov,B.Taska,V.Chatalbashev,D.Koller,D.Gupta,G.Heitz,and A.Ng.Discriminative learning of Markov random fields for segmentation of 3d range data.In Proc.of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),2005.
- [3] 刘威.应用于移动机器人视觉SLAM的地点识别研究[D].杭州:杭州电子科技大学,2019.
- [4] Neverova N,Wolf C,Lacey G,et al.Learning human identity from motion patterns[J].IEEE Access,2016,4:1810-1820.
- [5] 陈广大.复杂动态行人场景下的机器人导航[D].合肥:中国科学技术大学,2021.
- [6] Poux F,Billen R.A Smart Point Cloud Infrastructure for intelligent environments[M]//Laser Scanning.CRC Press,2019:127-149.
- [7] Neves J C,Santos G,Filipe S,et al.Quis-campi:Extending in the wild biometric recognition to surveillance environments[C]//International Conference on Image Analysis and Processing.Springer,Cham,2015:59-68.
- [8] Collins M .Discriminative Training Methods for Hidden Markov Models:Theory and Experiments with Perceptron Algorithms[J].Theoretical Computer ence,2002,410( 21–23):2279-2284.
- [9] Ribeiro R,Cruz G,Matos J,et al.A data set for airborne maritime surveillance environments[J].IEEE Transactions on Circuits and Systems for Video Technology,2017,29(9):2720-2732.