A Hybrid Deep Sea Navigation System of LBL/DR Integration Based on UKF and PSO-SVM
LIU Ben1,2, LIU Kaizhou1, WANG Yanyan1,2, ZHAO Yang1, CUI Shengguo1, WANG Xiaohui1
1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China
A Hybrid Deep Sea Navigation System of LBL/DR Integration Based on UKF and PSO-SVM
LIU Ben1,2, LIU Kaizhou1, WANG Yanyan1,2, ZHAO Yang1, CUI Shengguo1, WANG Xiaohui1
1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China
LIU Ben, LIU Kaizhou, WANG Yanyan, ZHAO Yang, CUI Shengguo, WANG Xiaohui. A Hybrid Deep Sea Navigation System of LBL/DR Integration Based on UKF and PSO-SVM[J]. 机器人, 2015, 37(5): 614-620.DOI: 10.13973/j.cnki.robot.2015.0614.
LIU Ben, LIU Kaizhou, WANG Yanyan, ZHAO Yang, CUI Shengguo, WANG Xiaohui. A Hybrid Deep Sea Navigation System of LBL/DR Integration Based on UKF and PSO-SVM. ROBOT, 2015, 37(5): 614-620. DOI: 10.13973/j.cnki.robot.2015.0614.
摘要
In order to improve the navigation accuracy of human occupied vehicle (HOV) precisely and efficiently, aninnovative hybrid approach based on unscented Kalman filter (UKF) and support vector machine (SVM) is proposed tofuse integrated navigation data. HOV is generally equipped with long baseline (LBL) acoustic positioning system and deadreckoning (DR) as an integrated navigation system. UKF is adopted to estimate the state of the dynamic model becauseof its good performance in filtering nonlinear problems. An accurate and stable filtering result can be obtained when bothLBL and DR are online. At the same time, SVM is utilized to train DR information with the result when LBL outrages, andthe particle swarm optimization (PSO) algorithm is employed for SVM parameters optimization. Therefore, the integratednavigation system can maintain a good performance when the LBL is off-line. Simulation results with the real navigationdata of Jiaolong HOV show that the methodology proposed here is able to meet the needs of HOV application.
In order to improve the navigation accuracy of human occupied vehicle (HOV) precisely and efficiently, aninnovative hybrid approach based on unscented Kalman filter (UKF) and support vector machine (SVM) is proposed tofuse integrated navigation data. HOV is generally equipped with long baseline (LBL) acoustic positioning system and deadreckoning (DR) as an integrated navigation system. UKF is adopted to estimate the state of the dynamic model becauseof its good performance in filtering nonlinear problems. An accurate and stable filtering result can be obtained when bothLBL and DR are online. At the same time, SVM is utilized to train DR information with the result when LBL outrages, andthe particle swarm optimization (PSO) algorithm is employed for SVM parameters optimization. Therefore, the integratednavigation system can maintain a good performance when the LBL is off-line. Simulation results with the real navigationdata of Jiaolong HOV show that the methodology proposed here is able to meet the needs of HOV application.
National High Technology Development Program of China （2009AA093302， 2014AA09A110）； the Chinese Academy of Strategic Leading Science and Technology Special （XDA11040104）
通讯作者:
LIU Kaizhou,liukzh@sia.cn
E-mail: liukzh@sia.cn
作者简介: LIU Ben (1990-), male, graduate students. His research interestsinclude the navigation and control of underwatervehicles. LIU Kaizhou (1976-), male, ph.D, Professor. His researchinterests include robot control, system simulation, andvirtual reality. WANG Yanyan (1986-), female, ph.D. candidate. Her researchinterests include trajectory planning of robots.
[1] Liu K Z, Li J, Guo W, et al. Navigation system of a class of underwater vehicle based on adaptive unscented Kalman fiter algorithm[J]. Journal of Central South University, 2014, 21(2): 550-557. [2] Liu F, CuiWC, Li X Y. China's first deep manned submersible, JIAOLONG[J]. Science China: Earth Sciences. 2010, 53(10): 1407-1410.[3] Kebkal O, Kebkal K, Bannasch R. Long-baseline Hydroacoustic positioning using D-MAC communication protocol[C]//OCEANS 2000 MTS/IEEE Conference. Piscataway, USA: IEEE, 2012: 1-7.[4] Larsen M B. Synthetic long baseline navigation of underwater vehicles[C]//OCEANS 2000 MTS/IEEE Conference and Exhibition. Piscataway, USA:IEEE, 2000: 2043-2050.[5] Bahr A, Leonard J J, Fallon M F. Cooperative localization for autonomous underwater vehicles[J]. International Journal of Robotics Research, 2009, 28(6): 714-728. [6] Alcocer A, Oliveira P, Pascoal A. Study and implementation of an EKF GIB-based underwater positioning system[J]. Control Engineering Practice, 2007, 15(6): 689-701. [7] Vasconcelos J F, Silvestre C, Oliveira P. INS/GPS aided by frequency contents of vector observations with application to autonomous surface crafts[J]. IEEE Journal of Oceanic Engineering, 2011, 36(2): 347-363. [8] Ding Q C, Zhao X G, Han J D. EMG-based estimation for multijoint continuous movement of human upper limb[J]. Robot, 2014, 36(4): 469-476.[9] Suykens J A K, de Brabanter J, Lukas L, et al. Weighted least squares support vector machines: Robustness and sparse approximation[ J]. Neurocomputing, 2002, 48(4): 85-105.[10] Selakov A, Cvijetinovic D, Milovic L, et al. Hybrid PSO-SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank[J]. Applied Soft Computing, 2014, 16: 80-88.[11] Sudheer C, Maheswaran R, Panigrahi B K, et al. A hybrid SVMPSO model for forecasting monthly streamflow[J]. Neural Computing and Applications, 2014, 24(6): 1381-1389. [12] Liu Y, Jia Q X, Chen G, et al. Load maximization trajectory optimization for free-floating space robot using multi-objective particle swarm optimization algorithm[J]. Robot, 2014, 36(4): 402-410.[13] Khare V, Nema S, Baredar P. Optimisation of the hybrid renewable energy system by HOMER, PSO and CPSO for the study area[J]. International Journal of Sustainable Energy, 2015 (ahead-of-print): 1-18.
