Predication Method of Fall State for Quadrupedal Robot in Field Based on IPO-VMD-GRNN
Abstract
The complex operating environment of agricultural quadruped robots causes them to fall easily when walking in the field, which affects the operating efficiency of the robot, and accurate prediction of the body fall state is of great significance to the walking stability of the robot. A critical state prediction method for robot fall was proposed based on ontology sensor signal processing. Firstly, the inertial measurement sensor signals of the quadruped robot walking and falling in a corn field and the fall state of the robot during field walking simulated by Gazebo software were collected, and the signals of the robot’s normal walking, the two phases of the critical stable state of falling and the four working conditions of complete falling were classified to generate signal datasets of different body states. Secondly, a population optimisation algorithm was used to optimize the parameters of variational mode decomposition (VMD), and an improved population optimization variational mode decomposition ( IPO VMD) algorithm was proposed. And IPO algorithm was adopted to optimize the parameters of general regression neural network (GRNN), and improved population optimization general regression neural network (IPO GRNN) was proposed. Finally, based on the above signal processing method, a fall prediction method for field operation robots based on the IPO VMD GRNN model was established, and the signals of the traverse roll and pitch attitude angle of the robot’s actual field walking were used as the model test data to verify the performance of the fall prediction model for field operation robots. The test results showed that the IPO VMD GRNN model outputed a total error of 0.146 7, an average relative error of 0.006 5, and a mean square error of 0.000 3, and the extracted features were well represented;compared with the VMD BPNN, VMD GRNN, and PSO VMD GRNN models, the average prediction of a successful response time was faster than the average predicted response times of 127.75 ms, 91.5 ms, and 39.5 ms. The algorithm can provide the ability to predict the critical state of robot fall when the robot walked in the field, and the results can provide technical support to improve the field passability of quadruped robots for autonomous operation.
Keywords: agricultural robot, quadruped robot, IPO-VMD-GRNN, variable modal decomposition, fall state prediction
Download Full Text:
PDFReferences
CHEN Xuegeng,WEN Haojun,ZHANG Weirong,et al. Advances and progress of agricultural machinery and sensing technology fusion [J ]. Smart Agriculture,2020,2(4) :1 - 16. (in Chinese)
HAN Jiavei,ZHU Wenying,ZHANG Bo,et al. Equipment and information collaboration to promote development of modem smart agriculture [J ]. Strategic Study of CAE,2022,24( 1 ) :55 -63. (in Chinese)
WANG XiaoleiJIN Zhenlin,LI Xiaodan,et al. Dynamic modeling and analysis of serial-parallel hybrid quadruped bionic robot [J] . Transactions of the Chinese Society for Agricultural Machinery ,2019,50(4) ;401 -412. (in Chinese)
CHEN Jiupeng, LI Chunlei, SAN Hongjun,et al. Model based gait transition control for quadruped robots [ J ]. Transactions of the Chinese Society for Agricultural Machinery,2024,55(3) ;431 -440,451. (in Chinese)
YAN Xu. Research on remote condition monitoring and fault diagnosis system of quadruped robot joints[ D] . Guilin; Guilin University of Technology,2022. (in Chinese)
ZHAO D, YANG J, OKOYE M 0, et al. Walking assist robot; a novel non-contact abnormal gait recognition approach based on extended set membership filter [J] . IEEE Access, 2019, 7; 76741 -76753.
KERTESZ C, TURUNE M. Body state recognition for a quadruped mobile robot [C] / 2018 IEEE 22nd International Conference on Intelligent Engineering Systems (INES). IEEE, 2018; 323 -328.
WU Y, FU Z, EEI J. Fault diagnosis for industrial robots based on a combined approach of manifold learning, treelet transform and Naive Bayes [J ]. Review of Scientific Instruments, 2020, 91(1); 015116.
LIU Wei, LIU Wang, CAO Dahu, et al. Robot grinding chatter monitoring based on improved EMD and GA - BPNN [J ]. Journal of Vibration and Shock, 2024, 43(9) ; 131 - 138. (in Chinese)
LI Bing, ZHANG Yongde, YUAN Lipeng, et al. Predictive control of plantar force and motion stability of hydraulic quadruped robot[ J . China Mechanical Engineering, 2021 , 32(5); 523 -532. (in Chinese)
YANG T, ZHANG W, YU Z, et al. Falling prediction and recovery control for a humanoid robot [ С] / Proceedings of the 2018 IEEE - HAS 18th International Conference on Humanoid Robots (Humanoids) , 2018; 1073 - 1079.
XI Ao, MUDIYANSELAGE T, TAO Dacheng, et al. Balance control of a biped robot on a rotating platform based on efficient reinforcement learning [J] . IEEE/CAA Journal of Automatica Sinica, 2019, 6(4) : 938 -951.
LI Zhibin, ZHOU Chengxu, CSTANO J, el al. Fall prediction of legged robots based on energy state and its implication of balance augmentation: a study on the humanoid [ C] //Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICR A) ,2015 :5094 -5100.
MUMMOLO C, MANGIALARDI L, KIM J H. Numerical estimation of balanced and falling states for constrained legged systems [J]. Journal of Nonlinear Science, 2017, 27(4) ;1291 - 1323.
ATKESON C, BAIDU B, BANERJEE N, et al. No falls, no resets; reliable humanoid behavior in the DARPA robotics challenge [ C]// 2015 IEEE - RAS 15th International Conference on Humanoid Robots (Humanoids) , 2015: 623 -630.
D1 Pei, HASEGAWA Y, NAKAGAWA S, et al. Fall detection and prevention control using walking-aid cane robot [ J]. IEEE/ASM E Transactions on Mechatronics, 2015, 21(2) ; 625 -637.
HUANG J, DI P, WAKITA K, et al. Study of fall detection using intelligent cane based on sensor fusion С //2008 International Symposium on Micro-nanomeehatronics and Human Science, 2008: 495 -5(X).
SUBBURAMAN R, KANOULAS D, MURATORE L, et al. Human inspired fall prediction method for humanoid robots [ J]. Robotics and Autonomous Systems, 2019, 121; 103257.
B1 Sheng, LIU Haoxi, MIN Huaqing, et al. Fall detection and control of humanoid robots based on multi-sensor information fusion [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45 (1): 95 - 101. (in Chinese)
KORMUSHEV P, UGURLU B, COLASANTO L, et al. The anatomy of a fall: automated real-time analysis of raw force sensor data from bipedal walking robots and humans [С] //Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012; 3706 -3713.
LEE D W, JUN K, NAHEEM K, et al. Deep neural network-based double-check method for fall detection using IMU - L sensor and RGB camera data J]. IEEE Access, 2021, 9: 48064 -48079.
Refbacks
- There are currently no refbacks.
