基于语义树Markov随机场模型的地面机器人多尺度道路感知

doi:10.3969/j.issn.1000-1093.2016.03.017

兵工学报 ›› 2016, Vol. 37 ›› Issue (3): 512-517.doi: 10.3969/j.issn.1000-1093.2016.03.017

基于语义树Markov随机场模型的地面机器人多尺度道路感知

杜明芳¹²，王军政¹，李多杨¹，何玉东¹

收稿日期:2015-03-24 修回日期:2015-03-24 上线日期:2016-05-24
作者简介:杜明芳（1979—），女，副教授
基金资助:
国家自然科学基金项目(61103157)；北京市教育委员会科技计划面上项目（SQKM201311417010）

Ground Robot Multi-scale Road Perception Based on Semantic Tree MRF Model

DU Ming-fang^1,2, WANG Jun-zheng¹, LI Duo-yang¹, HE Yu-dong¹

(1. Key Laboratory of Intelligent Control and Decision of Complex System，Beijing Institute of Technology，Beijing 100081，China;2.College of Automation, Beijing Union University, Beijing 100101, China)

Received:2015-03-24 Revised:2015-03-24 Online:2016-05-24
Contact: DU Ming-fang E-mail:1314310@163.com

摘要/Abstract

摘要： 道路实时感知是自主式地面移动机器人实现自主导航的关键技术，但由于室外道路环境的复杂性与不确定性，其算法开发难度较大。提出了一种基于小波域语义树Markov模型的多尺度仿生道路感知算法。在时空域上采用三维随机场对机器人采集到的道路图像序列进行建模，提出了一种采用树结构约束、面向道路识别的语义树Markov随机场（RT-MRF）模型；采用遗传算法优化的有监督RT-MRF模型进行道路图像序列分割；机器人通过跟踪分割边界实现道路区域识别及自主导航。采用自主研制的四足仿生机器人作为研究和实验平台。实验结果表明：该方法能够在具有阴影、裂纹、坑洞、不平整及光照度变化的较差道路检测条件下鲁棒分割出道路边界，算法实时性高，可满足室外移动机器人自主导航需求。

关键词: 控制科学与技术, 四足机器人, 道路检测, 多尺度仿生感知, 语义树Markov模型, 小波域

Abstract: Road real-time perception is the key technology of autonomous ground mobile robot to realize autonomous navigation. But it is difficult to develop a road sensing algorithm because of the complexity and uncertainty of outdoor road environment. A multi-scale biomimetic road sensing algorithm in wavelet domain based on semantic tree Markov model is proposed. In time-space domain, the three-dimensional random field is used to express the road image sequence collected by robot. A road model named road best tree-Markov random field (RT-MRF) using the semantic tree structure Markov random field (MRF) is proposed. The genetic algorithm is used to optimize the supervised RT-MRF model for image segmentation of road sequences. The road recognition and autonomous navigation are realized through tracking segmentation boundary. An independently developed quadruped bionic robot is used as the research and experiment platform. The experimental results show that the proposed algorithm is a robust road image sequence segmentation method, which can be used under the poor detection conditions, such as shadow, cracks, holes, uneven and illumination change. And the real time of the algorithm is enough high to meet the demand of outdoor mobile robot autonomous navigation.

Key words: control science and technology, quadruped robot, road detection, multi-scale biomimetic sensing, semantic tree Markov model, wavelet domain

中图分类号:

TP391.41

. 基于语义树Markov随机场模型的地面机器人多尺度道路感知[J]. 兵工学报, 2016, 37(3): 512-517.

DU Ming-fang, WANG Jun-zheng, LI Duo-yang, HE Yu-dong. Ground Robot Multi-scale Road Perception Based on Semantic Tree MRF Model[J]. Acta Armamentarii, 2016, 37(3): 512-517.

参考文献

［1］ Semini C，Tsagarakis N G，Guglielmino E，et al. Design of HyQ-a hydraulically and electrically actuated quadruped robot[J]. Proceedings of the Institution of Mechanical Engineers，Part I：Journal of Systems and Control Engineering，2011，225(6)：831-849.
[2］张秀丽. 四足机器人节律运动及环境适应性的生物控制研究[D]. 北京：清华大学，2004.
ZHANG Xiu-li. Biological-inspired rhythmic motion & environmental adaptability for quadruped robot[D].Beijing：Tsinghua University，2004. (in Chinese)
[3］李贻斌，李彬，荣学文，等. 液压驱动四足仿生机器人的结构设计和步态规划[J]. 山东大学学报，2011，41(5)：32-36，45.
LI Yi-bin，LI Bin，RONG Xue-wen，et al. Mechanical design and gait planning of a hydraulically actuated quadruped bionic robot[J]. Journal of Shandong University，2011，41(5)：32-36，45.（in Chinese）
[4］王立鹏,王军政,汪首坤,等.基于足端轨迹规划算法的液压四足机器人步态控制策略[J]. 机械工程学报，2013，49（1）：39-44.
WANG Li-peng, WANG Jun-zheng, WANG Shou-kun, et al. Strategy of foot trajectory generation for hydraulic quadruped robots gait planning[J]. Journal of Mechanical Engineering, 2013，49（1）： 39-44. (in Chinese)
[5］ Crouse M S, Nowak R D, Baraniuk R G. Wavelet-based statistical signal processing using hidden Markov models[J]. IEEE Transactions on Signal Processing, 1998, 46(4): 886-902.
[6］ Choi H，Baraniuk R. Multiscale image segmentation using wavelet-domain hidden Markov models[J]. IEEE Transactions on Image Processing, 2001, 10(9): 1309-1321.
[7］ Li J，Gray R M，Olshen R A. Multiscale image classification by hierarchical modeling with two dimensional hidden Markov models[J]. IEEE Transactions on Information Theory, 2000, 46(5): 1826-1841.
[8］周建军，林春生，赵建扬. 无人飞行器背景磁场学习方法研究[J]. 兵工学报, 2014, 35(1): 76-82.
ZHOU Jian-jun， LIN Chun-sheng，ZHAO Jian-yang. Research on learning flight for unmanned aircraft in background magnetic field[J]. Acta Armamentarii, 2014, 35(1): 76-82. (in Chinese)
[9］伍飞云，周跃海，童峰，等. 可适应稀疏度变化的非均匀范数约束水声信道估计算法[J]. 兵工学报, 2014, 35(9): 1503-1509.
WU Fei-yun, ZHOU Yue-hai, TONG Feng, et al. Non-uniform norm constraint estimation algorithm for underwater acoustic channels at the presence of varying sparsity[J]. Acta Armamentarii, 2014, 35(9): 1503-1509. (in Chinese)
[10］丁良宏. BigDog四足机器人关键技术分析[J]. 机械工程学报, 2015，51(7): 66-87.
DING Liang-hong. Key technology analysis of BigDog quadruped robot[J]. Journal of Mechanical Engineering，2015，51(7): 66- 87. (in Chinese)
[11］张天, 杨晨曦, 朱颖. 多传感器信息融合在四足机器人避障中的应用[J]. 传感器与微系统, 2015(5): 150-153.
ZHANG Tian, YANG Chen-xi, ZHU Ying. Application of multi-sensor information fusion in obstacle avoidance of quadruped robot[J]. Transducer and Microsystem Technologies, 2015(5): 150-153. (in Chinese)
[12］ Zhang T H, Wei Q, Ma H X. Position/force control for a single leg of a quadruped robot in an operation space[J]. International Journal of Advanced Robotic Systems, 2013, 10(137): 1-7.
[13］ Lei J T, Wang F, Yu H Y, et al. Energy efficiency analysis of quadruped robot with trot gait and combined cycloid foot trajectory[J]. Chinese Journal of Mechanical Engineering, 2014, 27(1): 138-145.

[1]	桑董辉，陈原，高军. 由2自由度并联髋关节构成的脊柱式四足步行机器人步态规划和稳定性分析[J]. 兵工学报, 2020, 41(6): 1188-1200.
[2]	刘志成，郑莉芳，王旭. 基于混合神经振荡器的爬行四足机器人运动协调控制[J]. 兵工学报, 2020, 41(11): 2303-2312.
[3]	张云，郭振武，陈迪剑，王斌锐. 基于Kimura振荡器和虚拟模型的气动肌肉四足机器人步态控制[J]. 兵工学报, 2018, 39(7): 1411-1418.
[4]	苗建明，王少萍，范磊，李元. 欠驱动自主水下航行器空间曲线路径跟踪控制研究[J]. 兵工学报, 2017, 38(9): 1786-1796.
[5]	查峰，覃方君，李京书，叶斌. 三轴旋转惯性导航系统的旋转控制建模研究[J]. 兵工学报, 2017, 38(8): 1610-1618.
[6]	伍明，张国良，李琳琳，付光远，李承剑. 基于动态和静态环境对象观测一致性约束的移动机器人多传感器标定优化方法[J]. 兵工学报, 2017, 38(8): 1630-1641.
[7]	王世峰，都凯悦，孟颖，王锐. 基于机器学习的车辆路面类型识别技术研究[J]. 兵工学报, 2017, 38(8): 1642-1648.
[8]	周荻，董金鲁. 带襟翼的飞行器非线性控制系统分析和设计[J]. 兵工学报, 2017, 38(7): 1322-1329.
[9]	郑睿，赵伟，方明星，杜友武. 基于多圈环绕结构的超流体陀螺噪声抑制方法[J]. 兵工学报, 2017, 38(7): 1330-1335.
[10]	邢丽, 熊智, 刘建业, 杭义军. 基于对偶四元数的圆锥及划船误差补偿改进算法[J]. 兵工学报, 2017, 38(7): 1336-1347.
[11]	庞辉, 陈嘉楠, 刘凯. 汽车磁流变半主动悬架系统自适应反推跟踪控制[J]. 兵工学报, 2017, 38(7): 1430-1442.
[12]	马艳彤，郑荣，韩晓军. 面向海底光学探测使命的自治水下机器人水平路径跟随控制[J]. 兵工学报, 2017, 38(6): 1147-1153.
[13]	陈慧岩，陈舒平，龚建伟. 智能汽车横向控制方法研究综述[J]. 兵工学报, 2017, 38(6): 1203-1214.
[14]	廖自力，阳贵兵，高强，袁东. 多轮独立电驱动车辆转向稳定性集成控制研究[J]. 兵工学报, 2017, 38(5): 833-842.
[15]	王斌锐，沈国阳，金英连，王凌. 基于干扰观测器的级联气动肌肉肘关节滑模控制[J]. 兵工学报, 2017, 38(4): 793-801.

基于语义树Markov随机场模型的地面机器人多尺度道路感知

Ground Robot Multi-scale Road Perception Based on Semantic Tree MRF Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价