Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435656
Dingwei Wu, Kaifang Wan, Xiao-guang Gao, Zijian Hu
When agents in a multiagent system implement motion planning in complex and dynamic environments, model-based planning algorithms have poor adaptability, while intelligent algorithms, such as MADDPG, encounter difficulty in converging when training multiple agents, and the resulting control model has poor stability and robustness. To address the above challenges, this paper proposes a mixed experience multiagent deep deterministic policy gradient algorithm referred to as ME-MADDPG. The algorithm increases the high-quality experience obtained by artificial potential field method and uses dynamic probability to sample from different replay buffers. Simulation experiments have proven that compared to MADDPG, ME-MADDPG greatly improves convergence speed, convergence effect and stability and that ME-MADDPG can efficiently provide shorter and more convenient paths for multiagent systems.
{"title":"Multiagent Motion Planning Based on Deep Reinforcement Learning in Complex Environments","authors":"Dingwei Wu, Kaifang Wan, Xiao-guang Gao, Zijian Hu","doi":"10.1109/ICCRE51898.2021.9435656","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435656","url":null,"abstract":"When agents in a multiagent system implement motion planning in complex and dynamic environments, model-based planning algorithms have poor adaptability, while intelligent algorithms, such as MADDPG, encounter difficulty in converging when training multiple agents, and the resulting control model has poor stability and robustness. To address the above challenges, this paper proposes a mixed experience multiagent deep deterministic policy gradient algorithm referred to as ME-MADDPG. The algorithm increases the high-quality experience obtained by artificial potential field method and uses dynamic probability to sample from different replay buffers. Simulation experiments have proven that compared to MADDPG, ME-MADDPG greatly improves convergence speed, convergence effect and stability and that ME-MADDPG can efficiently provide shorter and more convenient paths for multiagent systems.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115396543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435712
W. Szeto, F. Wong, Edmond Wing Fung Yau, Sze Yi Mak, K. B. Chuah
A Synchronised “Trio-Robots Cutting System” with “DRY” Lubrication Technology for Post 3D-Metal Laser Sintered Biomedical Product is being developed. The multi-robot machining cell consists of three 6 degree-of-freedom industrial robots serving respectively as cutting robot, holding robot and cooling robot. The novelty of this robotic system is the innovative built-in reference datum setting that enables subsequent downstream robotic manufacturing system and process design to be completed in a single set-up. This innovative idea/concept is patent pending. This paper reports the conceptual development of the said manufacturing system, with the use of kinematic modelling of the three 6 DOF robots for the Machining System.
{"title":"Kinematic Modelling of a Tri Robot Machining Cell","authors":"W. Szeto, F. Wong, Edmond Wing Fung Yau, Sze Yi Mak, K. B. Chuah","doi":"10.1109/ICCRE51898.2021.9435712","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435712","url":null,"abstract":"A Synchronised “Trio-Robots Cutting System” with “DRY” Lubrication Technology for Post 3D-Metal Laser Sintered Biomedical Product is being developed. The multi-robot machining cell consists of three 6 degree-of-freedom industrial robots serving respectively as cutting robot, holding robot and cooling robot. The novelty of this robotic system is the innovative built-in reference datum setting that enables subsequent downstream robotic manufacturing system and process design to be completed in a single set-up. This innovative idea/concept is patent pending. This paper reports the conceptual development of the said manufacturing system, with the use of kinematic modelling of the three 6 DOF robots for the Machining System.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124951483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435653
Yunxiu Zhang, Qifeng Zhang, Aiqun Zhang, Yingzhe Sun, Zhen He
It is extremely difficult and expensive to operate a traditional remotely operated vehicle (ROV) in the deep-sea. In this paper, a novel small-scale deep-sea resident ROV, called Rover ROV, is designed to conduct regional fine-sounding operations. The Rover ROV does not require a complicated Launch and Recovery System (LARS) equipped on a surface vessel, instead, the Rover ROV can be placed on a deep-sea lander and diving to the seafloor together. To ensure sufficient energy for the Rover ROV and meanwhile reduce the complexity of the conventional Tether Management System (TMS), a combined energy supply scheme based on floating charging technology is proposed. This power supply solution avoids relying solely on strong cables to provide power. To validating the maneuverability of the self-developed resident ROV and the effectiveness of the combined energy supply solution, Field experiments have been conducted in the South China Sea area with a depth of 3000 m. The results show that the developed small-scale resident ROV system can be operated in deep-sea high-power scenario, which verifies the higher reliability and longtime working capability of the proposed system.
{"title":"Development and Experiments of a Novel Deep-sea Resident ROV","authors":"Yunxiu Zhang, Qifeng Zhang, Aiqun Zhang, Yingzhe Sun, Zhen He","doi":"10.1109/ICCRE51898.2021.9435653","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435653","url":null,"abstract":"It is extremely difficult and expensive to operate a traditional remotely operated vehicle (ROV) in the deep-sea. In this paper, a novel small-scale deep-sea resident ROV, called Rover ROV, is designed to conduct regional fine-sounding operations. The Rover ROV does not require a complicated Launch and Recovery System (LARS) equipped on a surface vessel, instead, the Rover ROV can be placed on a deep-sea lander and diving to the seafloor together. To ensure sufficient energy for the Rover ROV and meanwhile reduce the complexity of the conventional Tether Management System (TMS), a combined energy supply scheme based on floating charging technology is proposed. This power supply solution avoids relying solely on strong cables to provide power. To validating the maneuverability of the self-developed resident ROV and the effectiveness of the combined energy supply solution, Field experiments have been conducted in the South China Sea area with a depth of 3000 m. The results show that the developed small-scale resident ROV system can be operated in deep-sea high-power scenario, which verifies the higher reliability and longtime working capability of the proposed system.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129743708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435725
G. Xue, Zhongyu Ding, Qiang Zhang, Yang Liu, Yancai Hu, Zewen Tao
In order to solve the trajectory tracking control problem of underwater dredging operation of tracked robot, considering that the center of mass does not coincide with the geometric center of the robot, the kinematics and dynamics motion model is established. The kinematics and dynamics controller are designed based on Backstepping method, and the global stability of the controller is proved by Lyapunov stability theory. The effectiveness of the designed controller is proved by simulation.
{"title":"Trajectory Tracking Control of Tracked Underwater Dredging Robot","authors":"G. Xue, Zhongyu Ding, Qiang Zhang, Yang Liu, Yancai Hu, Zewen Tao","doi":"10.1109/ICCRE51898.2021.9435725","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435725","url":null,"abstract":"In order to solve the trajectory tracking control problem of underwater dredging operation of tracked robot, considering that the center of mass does not coincide with the geometric center of the robot, the kinematics and dynamics motion model is established. The kinematics and dynamics controller are designed based on Backstepping method, and the global stability of the controller is proved by Lyapunov stability theory. The effectiveness of the designed controller is proved by simulation.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131284971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435654
Niven Jun Liang Sie, S. Srigrarom, Sunan Huang
This paper reports the field test validations of the recently proposed vision-based real-time multi-camera setups for detecting, tracking and 3D localizing multiple aerial targets (mainly drones). We also propose the additional concurrent camera pose estimation when the camera poses are not known beforehand. This extra step can be used alongside (in parallel) with the drone tracking and localizing process. We conducted flight tests using 2 drones flying in 2 specific scenarios, and used 3 cameras to observe, detect, track and locate the positions of both drones in global frame. The efficacy of our technique is measured by the accuracy of the temporal and spatial positions of the observed drones, against the drones’ own GPS recordings. Our initial results show reasonable accuracy, i.e. ±1m at 50m, as such, the proposed vision-based methods can be used for drone detection and tracking.
{"title":"Field Test Validations of Vision-based Multi-camera Multi-drone Tracking and 3D Localizing with Concurrent Camera Pose Estimation","authors":"Niven Jun Liang Sie, S. Srigrarom, Sunan Huang","doi":"10.1109/ICCRE51898.2021.9435654","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435654","url":null,"abstract":"This paper reports the field test validations of the recently proposed vision-based real-time multi-camera setups for detecting, tracking and 3D localizing multiple aerial targets (mainly drones). We also propose the additional concurrent camera pose estimation when the camera poses are not known beforehand. This extra step can be used alongside (in parallel) with the drone tracking and localizing process. We conducted flight tests using 2 drones flying in 2 specific scenarios, and used 3 cameras to observe, detect, track and locate the positions of both drones in global frame. The efficacy of our technique is measured by the accuracy of the temporal and spatial positions of the observed drones, against the drones’ own GPS recordings. Our initial results show reasonable accuracy, i.e. ±1m at 50m, as such, the proposed vision-based methods can be used for drone detection and tracking.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132652647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435727
Dong Zhang, Xiaolin Yan, Rixing Li, Zhongyi Guo
The current quadruped robots are designed based on the quadruped animals in the natural world, and use complex control algorithms to realize the movement and walking of the quadruped robots, which cause problems such as difficult design of bionic robots and high production costs. In order to solve the above-mentioned problems, this paper will design a four-legged sports robot that can walk quickly, turn and cross obstacles at low cost and simple control. First, establish a simplified threedimensional model of the quadruped motion robot designed and a three-dimensional model of the specific mechanical structure in SOLIDWORKS to ensure the rationality of the mechanism design. Secondly, import the simplified model into ADAMS for kinematics simulation, complete the setting and definition of the parameters of the quadruped robot model, and verify the feasibility of the mechanical structure scheme. Then, according to the complex mechanical structure environment, some key design parts are imported into ANASY for structural finite element analysis to verify whether the stiffness and strength of the key parts of the mechanism meet the design requirements. Finally, a real quadruped robot was built in combination with theoretical design and put into operation in a real environment. The simulation results were compared to verify the feasibility and rationality of the quadruped robot program as a whole.
{"title":"Design of an Unconventional Bionic Quadruped Robot with Low-degree-freedom of Movement","authors":"Dong Zhang, Xiaolin Yan, Rixing Li, Zhongyi Guo","doi":"10.1109/ICCRE51898.2021.9435727","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435727","url":null,"abstract":"The current quadruped robots are designed based on the quadruped animals in the natural world, and use complex control algorithms to realize the movement and walking of the quadruped robots, which cause problems such as difficult design of bionic robots and high production costs. In order to solve the above-mentioned problems, this paper will design a four-legged sports robot that can walk quickly, turn and cross obstacles at low cost and simple control. First, establish a simplified threedimensional model of the quadruped motion robot designed and a three-dimensional model of the specific mechanical structure in SOLIDWORKS to ensure the rationality of the mechanism design. Secondly, import the simplified model into ADAMS for kinematics simulation, complete the setting and definition of the parameters of the quadruped robot model, and verify the feasibility of the mechanical structure scheme. Then, according to the complex mechanical structure environment, some key design parts are imported into ANASY for structural finite element analysis to verify whether the stiffness and strength of the key parts of the mechanism meet the design requirements. Finally, a real quadruped robot was built in combination with theoretical design and put into operation in a real environment. The simulation results were compared to verify the feasibility and rationality of the quadruped robot program as a whole.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115523647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435699
Yousheng Yang, Z. Cui, Hong-li Xue, Mohammed AL-Bedwi
In view of the difficulties in cleaning the bio-fouling on the surface of underwater marine engineering equipment, a systematic solution based on the advantages of water hydraulic technology—a water hydraulic rotary actuator (WHRA) —is proposed. Its composition and working principles are introduced. The system is composed of a DC motor, bidirectional water hydraulic pump, water hydraulic motor, relief valve, pilot check valve. By adjusting the speed and direction of the DC motor, the output flow of the hydraulic pump, the direction and the speed of the water hydraulic motor can be controlled. This paper addresses the effects of workload and DC motor rotation direction on WHRA. Simulations have been carried out to study input flow, inlet pressure, and output speed of the executive part of WHRA—water hydraulic motor—under different conditions. It is concluded from the results that the actuator has a good capacity of resisting disturbance and the actuator works well under normal conditions with the startup time is 0.3s, the steadystate error is 0.01 rpm. The research provides a fundamental basis for the development of high-performance water hydraulic rotary actuator.
{"title":"Research of a Water Hydraulic Rotary Actuator","authors":"Yousheng Yang, Z. Cui, Hong-li Xue, Mohammed AL-Bedwi","doi":"10.1109/ICCRE51898.2021.9435699","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435699","url":null,"abstract":"In view of the difficulties in cleaning the bio-fouling on the surface of underwater marine engineering equipment, a systematic solution based on the advantages of water hydraulic technology—a water hydraulic rotary actuator (WHRA) —is proposed. Its composition and working principles are introduced. The system is composed of a DC motor, bidirectional water hydraulic pump, water hydraulic motor, relief valve, pilot check valve. By adjusting the speed and direction of the DC motor, the output flow of the hydraulic pump, the direction and the speed of the water hydraulic motor can be controlled. This paper addresses the effects of workload and DC motor rotation direction on WHRA. Simulations have been carried out to study input flow, inlet pressure, and output speed of the executive part of WHRA—water hydraulic motor—under different conditions. It is concluded from the results that the actuator has a good capacity of resisting disturbance and the actuator works well under normal conditions with the startup time is 0.3s, the steadystate error is 0.01 rpm. The research provides a fundamental basis for the development of high-performance water hydraulic rotary actuator.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124861318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435729
Huiqiao Ren, K. Fujisawa
This research engages in generating trajectories with continuous curvature and applying blending cases. Clothoid spline has an important property that its curvature is linear related to its arclength, this property can provide a curvature (G2) continuity to the interpolation operation. But it is rarely used in the trajectory plan because its shape is hard to control to avoid obstacles. This paper uses a collision-free corridor to limit the trajectory generation to avoid obstacles. In a transformable system, using line segments to connect with Clothoid spiral segments, the computation complexity could be greatly reduced by setting the starting conditions equal to zero. With the computation, a unique solution to the spiral segment is found. The computation process and the corresponding algorithm are elaborated in this paper.
{"title":"Obstacle Avoidable G2-continuous Trajectory Generated with Clothoid Spline Solution","authors":"Huiqiao Ren, K. Fujisawa","doi":"10.1109/ICCRE51898.2021.9435729","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435729","url":null,"abstract":"This research engages in generating trajectories with continuous curvature and applying blending cases. Clothoid spline has an important property that its curvature is linear related to its arclength, this property can provide a curvature (G2) continuity to the interpolation operation. But it is rarely used in the trajectory plan because its shape is hard to control to avoid obstacles. This paper uses a collision-free corridor to limit the trajectory generation to avoid obstacles. In a transformable system, using line segments to connect with Clothoid spiral segments, the computation complexity could be greatly reduced by setting the starting conditions equal to zero. With the computation, a unique solution to the spiral segment is found. The computation process and the corresponding algorithm are elaborated in this paper.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121843560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435710
Jose Luis Ordoñez Avila, Marcial Gustavo Ordoñez Avila, M. E. Perdomo
Climate change is affecting all ecosystems in the world, robotics applications are focusing on monitoring ecosystems effects. Coral reef in Honduras is an important resource that needs to be preserved. This study shows the development of a robot for monitoring coral reef, simplifying some challenges of underwater mechanical robot design. The robot development implements VDI 2206 model into cycles the lab design and the prototype integration. Because of different force estimations, simulations and field test the robot accomplish its task. PWM outputs control the force thrust. Internal sensors for leaks and temperature assure the robot functions. The vision system detect motion to take videos and photos every 2 minutes. Sea water temperature, videos, and photos are stored in a minicomputer. The flow simulation assures robot mechanical design to accomplish its task. The control should be improve adding a mathematical model for the robot displacement underwater.
{"title":"Design of an Underwater Robot for Coral Reef Monitoring in Honduras","authors":"Jose Luis Ordoñez Avila, Marcial Gustavo Ordoñez Avila, M. E. Perdomo","doi":"10.1109/ICCRE51898.2021.9435710","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435710","url":null,"abstract":"Climate change is affecting all ecosystems in the world, robotics applications are focusing on monitoring ecosystems effects. Coral reef in Honduras is an important resource that needs to be preserved. This study shows the development of a robot for monitoring coral reef, simplifying some challenges of underwater mechanical robot design. The robot development implements VDI 2206 model into cycles the lab design and the prototype integration. Because of different force estimations, simulations and field test the robot accomplish its task. PWM outputs control the force thrust. Internal sensors for leaks and temperature assure the robot functions. The vision system detect motion to take videos and photos every 2 minutes. Sea water temperature, videos, and photos are stored in a minicomputer. The flow simulation assures robot mechanical design to accomplish its task. The control should be improve adding a mathematical model for the robot displacement underwater.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130642032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435706
Ruiqi Ruan, Xiao-qin Liu, Xing Wu
Recognizing the motion of the multi-joint industrial robot from the measurement signal is helpful to link the test signal with the motion joint and improve the accuracy of state evaluation. A motion recognition method for multi-joint industrial robots based on end-arm vibration and Back Propagation (BP) neural network is proposed in this paper. A three-axis vibration sensor is installed on the last joint of the multi-joint industrial robot to obtain the vibration signals and then segment the acquired signal according to the length of time and extract the features, establish a feature matrix, train the network model through a single joint motion feature matrix, and finally identify the action corresponding to each small segment of the signal in the multi-joint motion of the robot through the model. The experimental results show that the proposed motion recognition method based on end-arm vibration and BP neural network has high practical value in action state recognition of multi-joint industrial robots.
{"title":"Action Recognition Method for Multi-joint Industrial Robots Based on End-arm Vibration and BP Neural Network","authors":"Ruiqi Ruan, Xiao-qin Liu, Xing Wu","doi":"10.1109/ICCRE51898.2021.9435706","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435706","url":null,"abstract":"Recognizing the motion of the multi-joint industrial robot from the measurement signal is helpful to link the test signal with the motion joint and improve the accuracy of state evaluation. A motion recognition method for multi-joint industrial robots based on end-arm vibration and Back Propagation (BP) neural network is proposed in this paper. A three-axis vibration sensor is installed on the last joint of the multi-joint industrial robot to obtain the vibration signals and then segment the acquired signal according to the length of time and extract the features, establish a feature matrix, train the network model through a single joint motion feature matrix, and finally identify the action corresponding to each small segment of the signal in the multi-joint motion of the robot through the model. The experimental results show that the proposed motion recognition method based on end-arm vibration and BP neural network has high practical value in action state recognition of multi-joint industrial robots.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116800134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：