Purpose This paper aims to illustrate the growing role of robots in the electronics industries. Design/methodology/approach Following a short introduction, this paper discusses robotic applications and products in three sectors of the electronics industry: semiconductor processing, printed circuit manufacture and electronic product assembly. Finally, conclusions are drawn. Findings The major application in semiconductor manufacture is the handling of silicon wafers during both front- and back-end processes and products include cleanroom certified multi-axis robotic arms, some mounted on mobile platforms, and automated guided vehicles. Applications in printed circuit board production include component handling and insertion, soldering, inspection, testing and packing. These exploit Cartesian, SCARA and six-axis articulated robots and cobots play an important role where automated and manual processes operate in close proximity. Electronic product assembly applications include part handling, soldering, bonding and sealing, screw driving, test and inspection and packaging. Cobots offer the benefits of a small footprint which allows deployment in the often limited space and use in proximity to humans. As yet, robotic assembly of complex electronic products such as smartphones and computers has not been realised for technical reasons. Originality/value This study provides a detailed review of robotic products and applications in three key sectors of the electronics industries.
{"title":"The role of robots in the electronics industry","authors":"R. Bogue","doi":"10.1108/ir-04-2023-0082","DOIUrl":"https://doi.org/10.1108/ir-04-2023-0082","url":null,"abstract":"\u0000Purpose\u0000This paper aims to illustrate the growing role of robots in the electronics industries.\u0000\u0000\u0000Design/methodology/approach\u0000Following a short introduction, this paper discusses robotic applications and products in three sectors of the electronics industry: semiconductor processing, printed circuit manufacture and electronic product assembly. Finally, conclusions are drawn.\u0000\u0000\u0000Findings\u0000The major application in semiconductor manufacture is the handling of silicon wafers during both front- and back-end processes and products include cleanroom certified multi-axis robotic arms, some mounted on mobile platforms, and automated guided vehicles. Applications in printed circuit board production include component handling and insertion, soldering, inspection, testing and packing. These exploit Cartesian, SCARA and six-axis articulated robots and cobots play an important role where automated and manual processes operate in close proximity. Electronic product assembly applications include part handling, soldering, bonding and sealing, screw driving, test and inspection and packaging. Cobots offer the benefits of a small footprint which allows deployment in the often limited space and use in proximity to humans. As yet, robotic assembly of complex electronic products such as smartphones and computers has not been realised for technical reasons.\u0000\u0000\u0000Originality/value\u0000This study provides a detailed review of robotic products and applications in three key sectors of the electronics industries.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79731158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose This paper aims to address the issue of model discontinuity typically encountered in traditional Denavit-Hartenberg (DH) models. To achieve this, we propose the use of a local Product of Exponentials (POE) approach. Additionally, a modified calibration model is presented which takes into account both kinematic errors and high-order joint-dependent kinematic errors. Both kinematic errors and high-order joint-dependent kinematic errors are analyzed to modify the model. Design/methodology/approach Robot positioning accuracy is critically important in high-speed and heavy-load manufacturing applications. One essential problem encountered in calibration of series robot is that the traditional methods only consider fitting kinematic errors, while ignoring joint-dependent kinematic errors. Findings Laguerre polynomials are chosen to fitting kinematic errors and high-order joint-dependent kinematic errors which can avoid the Runge phenomenon of curve fitting to a great extent. Levenberg–Marquard algorithm, which is insensitive to overparameterization and can effectively deal with redundant parameters, is used to quickly calibrate the modified model. Experiments on an EFFORT ER50 robot are implemented to validate the efficiency of the proposed method; compared with the Chebyshev polynomial calibration methods, the positioning accuracy is improved from 0.2301 to 0.2224 mm. Originality/value The results demonstrate the substantial improvement in the absolute positioning accuracy achieved by the proposed calibration methods on an industrial serial robot.
{"title":"Modeling and calibration of high-order joint-dependent kinematic errors of serial robot based on local POE","authors":"Yujie Zhang, Jing Cui, Yang Li, Zhongyi Chu","doi":"10.1108/ir-11-2022-0284","DOIUrl":"https://doi.org/10.1108/ir-11-2022-0284","url":null,"abstract":"\u0000Purpose\u0000This paper aims to address the issue of model discontinuity typically encountered in traditional Denavit-Hartenberg (DH) models. To achieve this, we propose the use of a local Product of Exponentials (POE) approach. Additionally, a modified calibration model is presented which takes into account both kinematic errors and high-order joint-dependent kinematic errors. Both kinematic errors and high-order joint-dependent kinematic errors are analyzed to modify the model.\u0000\u0000\u0000Design/methodology/approach\u0000Robot positioning accuracy is critically important in high-speed and heavy-load manufacturing applications. One essential problem encountered in calibration of series robot is that the traditional methods only consider fitting kinematic errors, while ignoring joint-dependent kinematic errors.\u0000\u0000\u0000Findings\u0000Laguerre polynomials are chosen to fitting kinematic errors and high-order joint-dependent kinematic errors which can avoid the Runge phenomenon of curve fitting to a great extent. Levenberg–Marquard algorithm, which is insensitive to overparameterization and can effectively deal with redundant parameters, is used to quickly calibrate the modified model. Experiments on an EFFORT ER50 robot are implemented to validate the efficiency of the proposed method; compared with the Chebyshev polynomial calibration methods, the positioning accuracy is improved from 0.2301 to 0.2224 mm.\u0000\u0000\u0000Originality/value\u0000The results demonstrate the substantial improvement in the absolute positioning accuracy achieved by the proposed calibration methods on an industrial serial robot.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87279205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shijie Dai, S. Li, Wenbin Ji, Ruiqin Wang, Shuyuan Liu
Purpose Considering the response lag and viscous slip oscillation of the system caused by cylinder piston friction during automatic polishing of aero-engine blades by a robotic pneumatic end-effector, the purpose of this study is to propose a constant force control method with adaptive friction compensation. Design/methodology/approach First, the mathematical model of the pneumatic end-effector is established based on the continuous LuGre model, and the static parameters of the LuGre model are identified to verify the necessity of friction compensation. Second, aiming at the problems of difficult identification of dynamic parameters and unmeasurable internal states in the LuGre model, the parameter adaptive law and friction state observer are designed to estimate these parameters online. Finally, an adaptive friction compensation backstepping controller is designed to improve the response speed and polishing force control accuracy of the system. Findings Simulation and experimental results show that, compared with proportion integration differentiation, extended state observer-based active disturbance rejection controller and integral sliding mode controller, the proposed method can quickly and effectively suppress the polishing force fluctuation caused by nonlinear friction and significantly improve the blade quality. Originality/value The pneumatic force control method combining backstepping control with the friction adaptive compensation based on LuGre friction model is studied, which effectively suppresses the fluctuation of normal polishing force.
{"title":"Adaptive friction compensation control of robotic pneumatic end-effector based on LuGre model","authors":"Shijie Dai, S. Li, Wenbin Ji, Ruiqin Wang, Shuyuan Liu","doi":"10.1108/ir-01-2023-0010","DOIUrl":"https://doi.org/10.1108/ir-01-2023-0010","url":null,"abstract":"\u0000Purpose\u0000Considering the response lag and viscous slip oscillation of the system caused by cylinder piston friction during automatic polishing of aero-engine blades by a robotic pneumatic end-effector, the purpose of this study is to propose a constant force control method with adaptive friction compensation.\u0000\u0000\u0000Design/methodology/approach\u0000First, the mathematical model of the pneumatic end-effector is established based on the continuous LuGre model, and the static parameters of the LuGre model are identified to verify the necessity of friction compensation. Second, aiming at the problems of difficult identification of dynamic parameters and unmeasurable internal states in the LuGre model, the parameter adaptive law and friction state observer are designed to estimate these parameters online. Finally, an adaptive friction compensation backstepping controller is designed to improve the response speed and polishing force control accuracy of the system.\u0000\u0000\u0000Findings\u0000Simulation and experimental results show that, compared with proportion integration differentiation, extended state observer-based active disturbance rejection controller and integral sliding mode controller, the proposed method can quickly and effectively suppress the polishing force fluctuation caused by nonlinear friction and significantly improve the blade quality.\u0000\u0000\u0000Originality/value\u0000The pneumatic force control method combining backstepping control with the friction adaptive compensation based on LuGre friction model is studied, which effectively suppresses the fluctuation of normal polishing force.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73096869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose This paper aims to propose a learning exponential jerk trajectory planning to suppress the residual vibrations of industrial robots. Design/methodology/approach Based on finite impulse response filter technology, a step signal with a proper amplitude first passes through two linear filters and then performs exponential filter shaping to obtain an exponential jerk trajectory and cancel oscillation modal. An iterative learning strategy designed by gradient descent principle is used to adjust the parameters of exponential filter online and achieve the maximum vibration suppression effect. Findings By building a SCARA robot experiment platform, a series of contrast experiments are conducted. The results show that the proposed method can effectively suppress residual vibration compared to zero vibration shaper and zero vibration and derivative shaper. Originality/value The idea of the adopted iterative leaning strategy is simple and reduces the computing power of the controller. A cheap acceleration sensor is available because it just needs to measure vibration energy to feedback. Therefore, the proposed method can be applied to production practice.
{"title":"A learning trajectory planning for vibration suppression of industrial robot","authors":"Yanbiao Zou, Tao Liu, Tie Zhang, Hubo Chu","doi":"10.1108/ir-02-2023-0013","DOIUrl":"https://doi.org/10.1108/ir-02-2023-0013","url":null,"abstract":"\u0000Purpose\u0000This paper aims to propose a learning exponential jerk trajectory planning to suppress the residual vibrations of industrial robots.\u0000\u0000\u0000Design/methodology/approach\u0000Based on finite impulse response filter technology, a step signal with a proper amplitude first passes through two linear filters and then performs exponential filter shaping to obtain an exponential jerk trajectory and cancel oscillation modal. An iterative learning strategy designed by gradient descent principle is used to adjust the parameters of exponential filter online and achieve the maximum vibration suppression effect.\u0000\u0000\u0000Findings\u0000By building a SCARA robot experiment platform, a series of contrast experiments are conducted. The results show that the proposed method can effectively suppress residual vibration compared to zero vibration shaper and zero vibration and derivative shaper.\u0000\u0000\u0000Originality/value\u0000The idea of the adopted iterative leaning strategy is simple and reduces the computing power of the controller. A cheap acceleration sensor is available because it just needs to measure vibration energy to feedback. Therefore, the proposed method can be applied to production practice.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75235100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Zhou, Shufeng Tang, Yubin Liu, Jie Zhao, Zaiyong Sun
Purpose This study aims to the complex and unpredictable terrain environment of the Qinghai-Tibet Plateau scientific research station, such as cement road, wetland, gravel desert, snowfield, ice surface, grassland, slimy ground, steep slope, step, etc., a reconfigurable walking mechanism based on two movement modes of wheel and triangular crawler was proposed. Design/methodology/approach By analyzing the deformation mechanism of the walking mechanism, a reconfigurable wheel-crawler-integrated walking mechanism and the configuration scheme are designed. The analysis of the kinematics and mechanical properties of the swing arm system and the deformation mechanism of the walking mechanism. Findings The reconfigurable wheel-crawler-integrated walking mechanism can be switched between the wheel and triangular crawler modes by driving the deformation mechanism. Through the numerical simulation of its movement process, and the trial production and experiment of the prototype, indicates the validity of the reconfigurable wheel-crawler-integrated walking mechanism design. Originality/value The work of this paper provides a reconfigurable wheel-crawler-integrated-walking mechanism, which can be used by robots in the Qinghai-Tibet Plateau scientific research station. It has excellent reconfigurability and can effectively improve the robot’s adaptability to complex terrain.
{"title":"Reconfigurable wheel-crawler-integrated walking mechanism design and kinetic analysis","authors":"P. Zhou, Shufeng Tang, Yubin Liu, Jie Zhao, Zaiyong Sun","doi":"10.1108/ir-08-2022-0208","DOIUrl":"https://doi.org/10.1108/ir-08-2022-0208","url":null,"abstract":"\u0000Purpose\u0000This study aims to the complex and unpredictable terrain environment of the Qinghai-Tibet Plateau scientific research station, such as cement road, wetland, gravel desert, snowfield, ice surface, grassland, slimy ground, steep slope, step, etc., a reconfigurable walking mechanism based on two movement modes of wheel and triangular crawler was proposed.\u0000\u0000\u0000Design/methodology/approach\u0000By analyzing the deformation mechanism of the walking mechanism, a reconfigurable wheel-crawler-integrated walking mechanism and the configuration scheme are designed. The analysis of the kinematics and mechanical properties of the swing arm system and the deformation mechanism of the walking mechanism.\u0000\u0000\u0000Findings\u0000The reconfigurable wheel-crawler-integrated walking mechanism can be switched between the wheel and triangular crawler modes by driving the deformation mechanism. Through the numerical simulation of its movement process, and the trial production and experiment of the prototype, indicates the validity of the reconfigurable wheel-crawler-integrated walking mechanism design.\u0000\u0000\u0000Originality/value\u0000The work of this paper provides a reconfigurable wheel-crawler-integrated-walking mechanism, which can be used by robots in the Qinghai-Tibet Plateau scientific research station. It has excellent reconfigurability and can effectively improve the robot’s adaptability to complex terrain.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74038879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose Omnidirectional mobile robots with a special type of wheel structure can realize flexible motion with all three degrees of freedom in a plane. But the driving method brings large disturbance, which affects motion accuracy and stability. This study aims to improve the motion control accuracy of the omnidirectional mobile platform with MY3 wheels (MY3-OMR), a new fuzzy active disturbance rejection control (FADRC) method with adaptivity is proposed. Design/methodology/approach Based on the basic mechanical structure and drive characteristics of MY3-OMR, the dynamics model of the system is established. The linear active disturbance rejection control (LADRC) system is designed to reduce the interference of nonlinear factors in this dynamics model. A fuzzy controller is introduced to realize the online adjustment of the parameters of the LADRC, which further improves the anti-disturbance performance of the system. Findings The control method proposed in this paper is compared and analyzed with other methods by simulation and experiment. Results show that the proposed method has better tracking and robustness, which effectively improves the control accuracy of trajectory tracking of MY3-OMR. Originality/value A FADRC method with adaptivity is proposed by combining fuzzy control and LADRC. The motion accuracy and anti-interference ability of the MY3-OMR are improved by this control method, which lays a foundation for the subsequent application of MY3-OMR.
{"title":"Fuzzy active disturbance rejection control method for an omnidirectional mobile robot with MY3 wheel","authors":"C. Ye, Jingru Shao, Yong Liu, Su-Yang Yu","doi":"10.1108/ir-10-2022-0264","DOIUrl":"https://doi.org/10.1108/ir-10-2022-0264","url":null,"abstract":"\u0000Purpose\u0000Omnidirectional mobile robots with a special type of wheel structure can realize flexible motion with all three degrees of freedom in a plane. But the driving method brings large disturbance, which affects motion accuracy and stability. This study aims to improve the motion control accuracy of the omnidirectional mobile platform with MY3 wheels (MY3-OMR), a new fuzzy active disturbance rejection control (FADRC) method with adaptivity is proposed.\u0000\u0000\u0000Design/methodology/approach\u0000Based on the basic mechanical structure and drive characteristics of MY3-OMR, the dynamics model of the system is established. The linear active disturbance rejection control (LADRC) system is designed to reduce the interference of nonlinear factors in this dynamics model. A fuzzy controller is introduced to realize the online adjustment of the parameters of the LADRC, which further improves the anti-disturbance performance of the system.\u0000\u0000\u0000Findings\u0000The control method proposed in this paper is compared and analyzed with other methods by simulation and experiment. Results show that the proposed method has better tracking and robustness, which effectively improves the control accuracy of trajectory tracking of MY3-OMR.\u0000\u0000\u0000Originality/value\u0000A FADRC method with adaptivity is proposed by combining fuzzy control and LADRC. The motion accuracy and anti-interference ability of the MY3-OMR are improved by this control method, which lays a foundation for the subsequent application of MY3-OMR.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84792301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xinyang Fan, Xin Shu, Baoxu Tu, C. Liu, F. Ni, Zainan Jiang
Purpose In the current teleoperation system of humanoid robots, the control between arms and the control between the waist and arms are individual and lack coordinated motion. This paper aims to solve the above problem and proposes a teleoperation control approach for a humanoid robot based on waist–arm coordination (WAC). Design/methodology/approach The teleoperation approach based on WAC comprises dual-arm coordination (DAC) and WAC. The DAC method realizes the coordinated motion of both arms through one hand by establishing a mapping relationship between a single hand controller and the manipulated object; the WAC method realizes the coordinated motion of both arms and waist by calculating the inverse kinematic input of robotic arms based on the desired velocity of the waist and the end of both arms. An integrated teleoperation control framework provides interfaces for the above methods, and users can switch control modes online to adapt to different tasks. Findings After conducting experiments on the dual-arm humanoid robot through the teleoperation control framework, it was found that the DAC method can save 27.2% of the operation time and reduce 99.9% of the posture change of the manipulated object compared with the commonly used individual control. The WAC method can accomplish a task that cannot be done by individual control. The experiments proved the improvement of both methods in terms of operation efficiency, operation stability and operation capability compared with individual control. Originality/value The DAC method better maintains the constraints of both arms and the manipulated object. The WAC method better maintains the constraints of the manipulated object itself. Meanwhile, the teleoperation framework integrates the proposed methods and enriches the teleoperation modes and control means.
{"title":"A humanoid robot teleoperation approach based on waist-arm coordination","authors":"Xinyang Fan, Xin Shu, Baoxu Tu, C. Liu, F. Ni, Zainan Jiang","doi":"10.1108/ir-12-2022-0306","DOIUrl":"https://doi.org/10.1108/ir-12-2022-0306","url":null,"abstract":"\u0000Purpose\u0000In the current teleoperation system of humanoid robots, the control between arms and the control between the waist and arms are individual and lack coordinated motion. This paper aims to solve the above problem and proposes a teleoperation control approach for a humanoid robot based on waist–arm coordination (WAC).\u0000\u0000\u0000Design/methodology/approach\u0000The teleoperation approach based on WAC comprises dual-arm coordination (DAC) and WAC. The DAC method realizes the coordinated motion of both arms through one hand by establishing a mapping relationship between a single hand controller and the manipulated object; the WAC method realizes the coordinated motion of both arms and waist by calculating the inverse kinematic input of robotic arms based on the desired velocity of the waist and the end of both arms. An integrated teleoperation control framework provides interfaces for the above methods, and users can switch control modes online to adapt to different tasks.\u0000\u0000\u0000Findings\u0000After conducting experiments on the dual-arm humanoid robot through the teleoperation control framework, it was found that the DAC method can save 27.2% of the operation time and reduce 99.9% of the posture change of the manipulated object compared with the commonly used individual control. The WAC method can accomplish a task that cannot be done by individual control. The experiments proved the improvement of both methods in terms of operation efficiency, operation stability and operation capability compared with individual control.\u0000\u0000\u0000Originality/value\u0000The DAC method better maintains the constraints of both arms and the manipulated object. The WAC method better maintains the constraints of the manipulated object itself. Meanwhile, the teleoperation framework integrates the proposed methods and enriches the teleoperation modes and control means.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86837107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
X. Yan, Jie Huang, Keyan He, Huajie Hong, Dasheng Xu
Purpose Robots equipped with LiDAR sensors can continuously perform efficient actions for mapping tasks to gradually build maps. However, with the complexity and scale of the environment increasing, the computation cost is extremely steep. This study aims to propose a hybrid autonomous exploration method that makes full use of LiDAR data, shortens the computation time in the decision-making process and improves efficiency. The experiment proves that this method is feasible. Design/methodology/approach This study improves the mapping update module and proposes a full-mapping approach that fully exploits the LiDAR data. Under the same hardware configuration conditions, the scope of the mapping is expanded, and the information obtained is increased. In addition, a decision-making module based on reinforcement learning method is proposed, which can select the optimal or near-optimal perceptual action by the learned policy. The decision-making module can shorten the computation time of the decision-making process and improve the efficiency of decision-making. Findings The result shows that the hybrid autonomous exploration method offers good performance, which combines the learn-based policy with traditional frontier-based policy. Originality/value This study proposes a hybrid autonomous exploration method, which combines the learn-based policy with traditional frontier-based policy. Extensive experiment including real robots is conducted to evaluate the performance of the approach and proves that this method is feasible.
{"title":"Autonomous exploration through deep reinforcement learning","authors":"X. Yan, Jie Huang, Keyan He, Huajie Hong, Dasheng Xu","doi":"10.1108/ir-12-2022-0299","DOIUrl":"https://doi.org/10.1108/ir-12-2022-0299","url":null,"abstract":"\u0000Purpose\u0000Robots equipped with LiDAR sensors can continuously perform efficient actions for mapping tasks to gradually build maps. However, with the complexity and scale of the environment increasing, the computation cost is extremely steep. This study aims to propose a hybrid autonomous exploration method that makes full use of LiDAR data, shortens the computation time in the decision-making process and improves efficiency. The experiment proves that this method is feasible.\u0000\u0000\u0000Design/methodology/approach\u0000This study improves the mapping update module and proposes a full-mapping approach that fully exploits the LiDAR data. Under the same hardware configuration conditions, the scope of the mapping is expanded, and the information obtained is increased. In addition, a decision-making module based on reinforcement learning method is proposed, which can select the optimal or near-optimal perceptual action by the learned policy. The decision-making module can shorten the computation time of the decision-making process and improve the efficiency of decision-making.\u0000\u0000\u0000Findings\u0000The result shows that the hybrid autonomous exploration method offers good performance, which combines the learn-based policy with traditional frontier-based policy.\u0000\u0000\u0000Originality/value\u0000This study proposes a hybrid autonomous exploration method, which combines the learn-based policy with traditional frontier-based policy. Extensive experiment including real robots is conducted to evaluate the performance of the approach and proves that this method is feasible.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90368281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose Simultaneous localization and map building (SLAM), as a state estimation problem, is a prerequisite for solving the problem of autonomous vehicle motion in unknown environments. Existing algorithms are based on laser or visual odometry; however, the lidar sensing range is small, the amount of data features is small, the camera is vulnerable to external conditions and the localization and map building cannot be performed stably and accurately using a single sensor. This paper aims to propose a laser three dimensions tightly coupled map building method that incorporates visual information, and uses laser point cloud information and image information to complement each other to improve the overall performance of the algorithm. Design/methodology/approach The visual feature points are first matched at the front end of the method, and the mismatched point pairs are removed using the bidirectional random sample consensus (RANSAC) algorithm. The laser point cloud is then used to obtain its depth information, while the two types of feature points are fed into the pose estimation module for a tightly coupled local bundle adjustment solution using a heuristic simulated annealing algorithm. Finally, the visual bag-of-words model is fused in the laser point cloud information to establish a threshold to construct a loopback framework to further reduce the cumulative drift error of the system over time. Findings Experiments on publicly available data sets show that the proposed method in this paper can match its real trajectory well. For various scenes, the map can be constructed by using the complementary laser and vision sensors, with high accuracy and robustness. At the same time, the method is verified in a real environment using an autonomous walking acquisition platform, and the system loaded with the method can run well for a long time and take into account the environmental adaptability of multiple scenes. Originality/value A multi-sensor data tight coupling method is proposed to fuse laser and vision information for optimal solution of the positional attitude. A bidirectional RANSAC algorithm is used for the removal of visual mismatched point pairs. Further, oriented fast and rotated brief feature points are used to build a bag-of-words model and construct a real-time loopback framework to reduce error accumulation. According to the experimental validation results, the accuracy and robustness of the single-sensor SLAM algorithm can be improved.
{"title":"Laser 3D tightly coupled mapping method based on visual information","authors":"Sixing Liu, Yan Chai, Rui Yuan, H. Miao","doi":"10.1108/ir-02-2023-0016","DOIUrl":"https://doi.org/10.1108/ir-02-2023-0016","url":null,"abstract":"\u0000Purpose\u0000Simultaneous localization and map building (SLAM), as a state estimation problem, is a prerequisite for solving the problem of autonomous vehicle motion in unknown environments. Existing algorithms are based on laser or visual odometry; however, the lidar sensing range is small, the amount of data features is small, the camera is vulnerable to external conditions and the localization and map building cannot be performed stably and accurately using a single sensor. This paper aims to propose a laser three dimensions tightly coupled map building method that incorporates visual information, and uses laser point cloud information and image information to complement each other to improve the overall performance of the algorithm.\u0000\u0000\u0000Design/methodology/approach\u0000The visual feature points are first matched at the front end of the method, and the mismatched point pairs are removed using the bidirectional random sample consensus (RANSAC) algorithm. The laser point cloud is then used to obtain its depth information, while the two types of feature points are fed into the pose estimation module for a tightly coupled local bundle adjustment solution using a heuristic simulated annealing algorithm. Finally, the visual bag-of-words model is fused in the laser point cloud information to establish a threshold to construct a loopback framework to further reduce the cumulative drift error of the system over time.\u0000\u0000\u0000Findings\u0000Experiments on publicly available data sets show that the proposed method in this paper can match its real trajectory well. For various scenes, the map can be constructed by using the complementary laser and vision sensors, with high accuracy and robustness. At the same time, the method is verified in a real environment using an autonomous walking acquisition platform, and the system loaded with the method can run well for a long time and take into account the environmental adaptability of multiple scenes.\u0000\u0000\u0000Originality/value\u0000A multi-sensor data tight coupling method is proposed to fuse laser and vision information for optimal solution of the positional attitude. A bidirectional RANSAC algorithm is used for the removal of visual mismatched point pairs. Further, oriented fast and rotated brief feature points are used to build a bag-of-words model and construct a real-time loopback framework to reduce error accumulation. According to the experimental validation results, the accuracy and robustness of the single-sensor SLAM algorithm can be improved.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75333969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purpose This paper aims to illustrate the growing role of drones in applications involving physical tasks. Design/methodology/approach Following a short introduction, this first provides a brief introduction to drone technology. It then describes and discusses products and applications involving physical tasks in agricultural and forestry, maritime rescue, firefighting and product delivery. Finally, brief conclusions are drawn. Findings Excluding military applications, drones were initially used primarily for image acquisition. Numerous different designs have since been developed with greatly varying wing configurations, payloads, flight duration, power sources and other features which are increasingly being used to conduct physical tasks. In the applications considered here drones are applying agrochemicals and dispersing crop and tree seeds; saving lives by deploying lifeboats and buoyancy aids; extinguishing fires in high-rise buildings and forests; and delivering groceries, food, mail, medicines and humanitarian aid, often in and to remote locations. Originality/value This study provides a detailed insight into selection of applications in which drones conduct physical tasks.
{"title":"Beyond imaging: drones for physical applications","authors":"R. Bogue","doi":"10.1108/ir-03-2023-0037","DOIUrl":"https://doi.org/10.1108/ir-03-2023-0037","url":null,"abstract":"\u0000Purpose\u0000This paper aims to illustrate the growing role of drones in applications involving physical tasks.\u0000\u0000\u0000Design/methodology/approach\u0000Following a short introduction, this first provides a brief introduction to drone technology. It then describes and discusses products and applications involving physical tasks in agricultural and forestry, maritime rescue, firefighting and product delivery. Finally, brief conclusions are drawn.\u0000\u0000\u0000Findings\u0000Excluding military applications, drones were initially used primarily for image acquisition. Numerous different designs have since been developed with greatly varying wing configurations, payloads, flight duration, power sources and other features which are increasingly being used to conduct physical tasks. In the applications considered here drones are applying agrochemicals and dispersing crop and tree seeds; saving lives by deploying lifeboats and buoyancy aids; extinguishing fires in high-rise buildings and forests; and delivering groceries, food, mail, medicines and humanitarian aid, often in and to remote locations.\u0000\u0000\u0000Originality/value\u0000This study provides a detailed insight into selection of applications in which drones conduct physical tasks.\u0000","PeriodicalId":54987,"journal":{"name":"Industrial Robot-The International Journal of Robotics Research and Application","volume":null,"pages":null},"PeriodicalIF":1.8,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78882303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：