Pub Date : 2021-04-16DOI: 10.1109/ICCRE51898.2021.9435722
B. Xie, S. Dai
For Stewart platform, high-quality kinematic motion signal plays an vital role in assessing flight training fidelity and providing feedback for trajectory following. In addition to relying on numerically solving forward kinematic problem from measurement of six leg displacement sensors to obtain kinematic motion, some researchers began to employ sensor fusion scheme through deploying inertial measurement unit (IMU) on upper moving platform. In this paper, we will construct Extended Kalman Filtering (EKF) and Unscented Kalman Filtering (UKF) on Lie group to address this fusion problem. This fusion problem is slightly different from Simultaneous Localization and Mapping (SLAM) or Visual Inertial Odometry (VIO) in that six linear displacement sensors are tightly coupled with IMU sensors while those sensors in SLAM or VIO problem still provides partial measurement of motion state. Numerical simulation experiment shows that both Lie group-based EKF (EKF-LG) and UKF (UKF-LG) which satisfy group affine property behave better than conventional Kalman filtering in consistency and accuracy.
{"title":"A Comparative Study of Extended Kalman Filtering and Unscented Kalman Filtering on Lie Group for Stewart Platform State Estimation","authors":"B. Xie, S. Dai","doi":"10.1109/ICCRE51898.2021.9435722","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435722","url":null,"abstract":"For Stewart platform, high-quality kinematic motion signal plays an vital role in assessing flight training fidelity and providing feedback for trajectory following. In addition to relying on numerically solving forward kinematic problem from measurement of six leg displacement sensors to obtain kinematic motion, some researchers began to employ sensor fusion scheme through deploying inertial measurement unit (IMU) on upper moving platform. In this paper, we will construct Extended Kalman Filtering (EKF) and Unscented Kalman Filtering (UKF) on Lie group to address this fusion problem. This fusion problem is slightly different from Simultaneous Localization and Mapping (SLAM) or Visual Inertial Odometry (VIO) in that six linear displacement sensors are tightly coupled with IMU sensors while those sensors in SLAM or VIO problem still provides partial measurement of motion state. Numerical simulation experiment shows that both Lie group-based EKF (EKF-LG) and UKF (UKF-LG) which satisfy group affine property behave better than conventional Kalman filtering in consistency and accuracy.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"1 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":"134510312","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/ICCRE51898.2021.9435731
Ming Xu, Bo Liu, Jun Zhou, Zelin Zhou, Zhenjie Weng
This paper addresses the trajectory tracking problem for soccer robots which can be simplified as two-wheeled robots. The kinematics analysis of the soccer robot is performed and a kinematics model is established. Due to the under-actuation of the robot and constraints of both the field and the soccer robot itself, Model Predictive Control (MPC) is applied in trajectory tracking control. The MPC strategy can be transformed to a constrained quadratic programming (QP) problem and the optimal control sequences for trajectory tracking is obtained by solving the QP problem online. Simulation experiments are designed to verify the control performance of the MPC controller.
{"title":"Trajectory Tracking of Wheeled Soccer Robots Based on Model Predictive Control","authors":"Ming Xu, Bo Liu, Jun Zhou, Zelin Zhou, Zhenjie Weng","doi":"10.1109/ICCRE51898.2021.9435731","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435731","url":null,"abstract":"This paper addresses the trajectory tracking problem for soccer robots which can be simplified as two-wheeled robots. The kinematics analysis of the soccer robot is performed and a kinematics model is established. Due to the under-actuation of the robot and constraints of both the field and the soccer robot itself, Model Predictive Control (MPC) is applied in trajectory tracking control. The MPC strategy can be transformed to a constrained quadratic programming (QP) problem and the optimal control sequences for trajectory tracking is obtained by solving the QP problem online. Simulation experiments are designed to verify the control performance of the MPC controller.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"18 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":"124168304","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/ICCRE51898.2021.9435659
Guo Qiang, Miao Yufeng, Xie Liudan, Zhang Xufeng, Luo Penghao
With the continuous application of location technology, ultra-wide band (UWB) location as a typical representation of indoor location technology is developing rapidly. It possesses many excellent features and performs well in UWB/INS integrated navigation system. Therefore, this paper investigates the UWB/INS integrated navigation method with fuzzy Kalman filtering algorithm in the case of existing large fluctuation caused by non-line-of-sight (NLOS) factors to meet the requirements on high location accuracy of electrical apparatuses in the complex indoor environment.This paper presents the fuzzy Kalman filtering algorithm by theoretical derivation and algorithm flow chart, and then carries out related simulation experiments to show and analyze the comparison results of the original algorithm and the modified one by using fuzzy control. The comparison of error curves indicates that the improved algorithm can effectively deal with the non-line-of-sight interference, and make sure the location data smoother and more reliable. This method is helpful to improve the location of electrical apparatuses.
{"title":"UWB/INS Location via Fuzzy Kalman Filtering for Electrical Apparatuses in Complex Indoor Environment","authors":"Guo Qiang, Miao Yufeng, Xie Liudan, Zhang Xufeng, Luo Penghao","doi":"10.1109/ICCRE51898.2021.9435659","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435659","url":null,"abstract":"With the continuous application of location technology, ultra-wide band (UWB) location as a typical representation of indoor location technology is developing rapidly. It possesses many excellent features and performs well in UWB/INS integrated navigation system. Therefore, this paper investigates the UWB/INS integrated navigation method with fuzzy Kalman filtering algorithm in the case of existing large fluctuation caused by non-line-of-sight (NLOS) factors to meet the requirements on high location accuracy of electrical apparatuses in the complex indoor environment.This paper presents the fuzzy Kalman filtering algorithm by theoretical derivation and algorithm flow chart, and then carries out related simulation experiments to show and analyze the comparison results of the original algorithm and the modified one by using fuzzy control. The comparison of error curves indicates that the improved algorithm can effectively deal with the non-line-of-sight interference, and make sure the location data smoother and more reliable. This method is helpful to improve the location of electrical apparatuses.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"50 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":"127495018","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/ICCRE51898.2021.9435719
Shanlin Zhong, Jinhan Zhang, Xiangli Nie
Creating robots with similar behavior and appearance to humans has been a long-term dream for roboticists. However, the highly redundant characteristic of the muscle system brings tremendous difficulty for the control and manufacture of the musculoskeletal robot. In this paper, we propose a heuristic pruning-based recurrent neural network method with group sparse regularization to reduce redundancy of muscles in musculoskeletal model, which can maintain the motion accuracy of musculoskeletal robots without activating the redundant muscles. Experiments on an upper extremity musculoskeletal model validate the effectiveness of the proposed method.
{"title":"Redundancy Reduction of Musculoskeletal Model for Robots with Group Sparse Neural Network","authors":"Shanlin Zhong, Jinhan Zhang, Xiangli Nie","doi":"10.1109/ICCRE51898.2021.9435719","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435719","url":null,"abstract":"Creating robots with similar behavior and appearance to humans has been a long-term dream for roboticists. However, the highly redundant characteristic of the muscle system brings tremendous difficulty for the control and manufacture of the musculoskeletal robot. In this paper, we propose a heuristic pruning-based recurrent neural network method with group sparse regularization to reduce redundancy of muscles in musculoskeletal model, which can maintain the motion accuracy of musculoskeletal robots without activating the redundant muscles. Experiments on an upper extremity musculoskeletal model validate the effectiveness of the proposed method.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"1 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":"130860764","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/ICCRE51898.2021.9435702
Jing Zhang, B. Yin, Xianpeng Xiao, Houyi Yang
Due to illumination variation under different lighting conditions, texture-less objects have posed significant challenges to visual object localization algorithms for robot grasping. We propose a method to determine the 6D pose of both textured and texture-less objects from a single RGB-D image with a Kinect. First, we apply hierarchical clustering strategy to pre-process the point cloud of a scene. Then, we achieve the 3D object detection by comparing the diameter between clustering point cloud and object model. Last, the rough pose of object is estimated through Hough voting and the estimation result is refined by ICP (Iterative Closest Point). Experimental results show that the accumulation error between the model and the corresponding point in the scene is less than 6mm and the attitude error is less than 1$.5^{mathrm{o}}$. The average detection accuracy rate of the proposed method reaches 97%, which can satisfy the grasping requirements of the manipulator. We also demonstrate that our approach has good performance in dynamic lighting conditions.
{"title":"3D Detection and 6D Pose Estimation of Texture-Less Objects for Robot Grasping","authors":"Jing Zhang, B. Yin, Xianpeng Xiao, Houyi Yang","doi":"10.1109/ICCRE51898.2021.9435702","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435702","url":null,"abstract":"Due to illumination variation under different lighting conditions, texture-less objects have posed significant challenges to visual object localization algorithms for robot grasping. We propose a method to determine the 6D pose of both textured and texture-less objects from a single RGB-D image with a Kinect. First, we apply hierarchical clustering strategy to pre-process the point cloud of a scene. Then, we achieve the 3D object detection by comparing the diameter between clustering point cloud and object model. Last, the rough pose of object is estimated through Hough voting and the estimation result is refined by ICP (Iterative Closest Point). Experimental results show that the accumulation error between the model and the corresponding point in the scene is less than 6mm and the attitude error is less than 1$.5^{mathrm{o}}$. The average detection accuracy rate of the proposed method reaches 97%, which can satisfy the grasping requirements of the manipulator. We also demonstrate that our approach has good performance in dynamic lighting conditions.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"1 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":"129751706","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/ICCRE51898.2021.9435665
Jie Zhou, Jun Liu
In the sensorless control of high-frequency signal injection permanent magnet synchronous motor, rotor position information can be obtained from high frequency response current, So extracting high frequency current is a crucial part. Aiming at the shortcomings of traditional methods of extracting high-frequency currents such as large errors and delays, an improved method is proposed to introduce the equal ripple Chebyshev best approximation finite impulse response filter into the signal extraction. The benefits of this filter include linear phase and maximum error minimization of passband and stopband. High-frequency current can be extracted effectively, the extraction error is minimized, and the interference of harmonic current generated by the inverter is also suppressed. In this paper, a high-frequency square wave is injected into a permanent magnet synchronous motor, and the simulation results showed the effectiveness and superiority of the proposed method.
{"title":"An Improved High Frequency Square Wave Injection Permanent Magnet Synchronous Motor sensorless Control","authors":"Jie Zhou, Jun Liu","doi":"10.1109/ICCRE51898.2021.9435665","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435665","url":null,"abstract":"In the sensorless control of high-frequency signal injection permanent magnet synchronous motor, rotor position information can be obtained from high frequency response current, So extracting high frequency current is a crucial part. Aiming at the shortcomings of traditional methods of extracting high-frequency currents such as large errors and delays, an improved method is proposed to introduce the equal ripple Chebyshev best approximation finite impulse response filter into the signal extraction. The benefits of this filter include linear phase and maximum error minimization of passband and stopband. High-frequency current can be extracted effectively, the extraction error is minimized, and the interference of harmonic current generated by the inverter is also suppressed. In this paper, a high-frequency square wave is injected into a permanent magnet synchronous motor, and the simulation results showed the effectiveness and superiority of the proposed method.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"11 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":"132554753","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/ICCRE51898.2021.9435680
S. Wang, Hongfeng Li
In order to study the influence of different eccentricity on the electromagnetic vibration of permanent magnet synchronous motor (PMSM), this paper takes a 48-slot 8-pole interior PMSM for electric vehicle as an example, establishes an analytical analysis model of radial electromagnetic force, and analyzes the variation laws of spatial order and time frequency of electromagnetic force under static and dynamic eccentric respectively. The differences between the effects of static and dynamic eccentricity on the electromagnetic vibration of the motor under different eccentricities are compared. The results show that with the increase of eccentricity, both static and dynamic eccentricity will aggravate the electromagnetic vibration of the motor. Static eccentricity will aggravate the electromagnetic vibration corresponding to the original vibration frequencies, but will not produce the new vibration frequencies. While dynamic eccentricity has little effect on the electromagnetic vibration at the original vibration frequencies, but introduces some new vibration frequencies, and the new frequencies are more likely to cause motor resonance.
{"title":"Analysis of Electromagnetic Vibration of Permanent Magnet Synchronous Motor under Static and Dynamic Eccentricity Fault","authors":"S. Wang, Hongfeng Li","doi":"10.1109/ICCRE51898.2021.9435680","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435680","url":null,"abstract":"In order to study the influence of different eccentricity on the electromagnetic vibration of permanent magnet synchronous motor (PMSM), this paper takes a 48-slot 8-pole interior PMSM for electric vehicle as an example, establishes an analytical analysis model of radial electromagnetic force, and analyzes the variation laws of spatial order and time frequency of electromagnetic force under static and dynamic eccentric respectively. The differences between the effects of static and dynamic eccentricity on the electromagnetic vibration of the motor under different eccentricities are compared. The results show that with the increase of eccentricity, both static and dynamic eccentricity will aggravate the electromagnetic vibration of the motor. Static eccentricity will aggravate the electromagnetic vibration corresponding to the original vibration frequencies, but will not produce the new vibration frequencies. While dynamic eccentricity has little effect on the electromagnetic vibration at the original vibration frequencies, but introduces some new vibration frequencies, and the new frequencies are more likely to cause motor resonance.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"10 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":"125285374","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/ICCRE51898.2021.9435700
Dongxu Zhou, Ruiqing Jia, Haifeng Yao
With the rapid changes in application scenarios, the robotic arm’s motion planning function is playing an increasingly important role. The traditional demonstration motion planning method of the robotic arm cannot be carried out quickly. The use of reinforcement learning algorithms to solve motion planning problems is a new research trend that has emerged in recent years. However, reinforcement learning algorithms are difficult to converge quickly in some complex tasks. This leads to inefficient and difficult training problems in actual training. This paper proposes a robotic arm motion planning method based on curriculum reinforcement learning. This method adopts the concept of obstacle effective sphere to simplify obstacles in the environment. According to the reinforcement learning agent’s real-time motion planning ability, the size of the effective sphere radius of the obstacle is adaptively adjusted so that the agent can train in an environment that matches its ability. The agent can first be trained in a simple environment and then gradually transition to a complete obstacle environment. The experiment in a virtual environment shows that this method can successfully perform motion planning. Comparing this method with the training effect of using only the PPO algorithm shows that this algorithm can effectively improve the efficiency of reinforcement learning training and reduce algorithm convergence difficulty.
{"title":"Robotic Arm Motion Planning Based on Curriculum Reinforcement Learning","authors":"Dongxu Zhou, Ruiqing Jia, Haifeng Yao","doi":"10.1109/ICCRE51898.2021.9435700","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435700","url":null,"abstract":"With the rapid changes in application scenarios, the robotic arm’s motion planning function is playing an increasingly important role. The traditional demonstration motion planning method of the robotic arm cannot be carried out quickly. The use of reinforcement learning algorithms to solve motion planning problems is a new research trend that has emerged in recent years. However, reinforcement learning algorithms are difficult to converge quickly in some complex tasks. This leads to inefficient and difficult training problems in actual training. This paper proposes a robotic arm motion planning method based on curriculum reinforcement learning. This method adopts the concept of obstacle effective sphere to simplify obstacles in the environment. According to the reinforcement learning agent’s real-time motion planning ability, the size of the effective sphere radius of the obstacle is adaptively adjusted so that the agent can train in an environment that matches its ability. The agent can first be trained in a simple environment and then gradually transition to a complete obstacle environment. The experiment in a virtual environment shows that this method can successfully perform motion planning. Comparing this method with the training effect of using only the PPO algorithm shows that this algorithm can effectively improve the efficiency of reinforcement learning training and reduce algorithm convergence difficulty.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"2 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":"126790527","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/ICCRE51898.2021.9435695
Jiapei Xu, Ruiming Qian
To study the adsorption performance of the split-type four-wheel wall-climbing robot working on the wall of the cylindrical tank, it is necessary to investigate the orientation of the robot and the position of the contact point between the wheel and the wall. This paper analyzes the contact situation between the wall and the wheels of a split-type four-wheel wall-climbing robot. The orientation of the left and right sides of the car body is then obtained. The orientation is described by a coordinate transformation matrix. Using the spatial geometric relationship and MATLAB, the orientation angle of the car body and the position of the four-wheel contact points relative to the angle of the left body attitude are obtained. The results provide a theoretical basis for designing the structure and size of the magnetic wheel.
{"title":"Research on Position and orientation of Wheel-wall Contact for Four-Wheel Wall-Climbing Robot Working on Cylindrical Tank","authors":"Jiapei Xu, Ruiming Qian","doi":"10.1109/ICCRE51898.2021.9435695","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435695","url":null,"abstract":"To study the adsorption performance of the split-type four-wheel wall-climbing robot working on the wall of the cylindrical tank, it is necessary to investigate the orientation of the robot and the position of the contact point between the wheel and the wall. This paper analyzes the contact situation between the wall and the wheels of a split-type four-wheel wall-climbing robot. The orientation of the left and right sides of the car body is then obtained. The orientation is described by a coordinate transformation matrix. Using the spatial geometric relationship and MATLAB, the orientation angle of the car body and the position of the four-wheel contact points relative to the angle of the left body attitude are obtained. The results provide a theoretical basis for designing the structure and size of the magnetic wheel.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"1 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":"126186458","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/ICCRE51898.2021.9435678
Xiao Wen, Zhen-Gang Zhao
In recent years, the service robot has been developed rapidly, which has brought a lot of convenience for industries and human life. It is of great significance to study service robot. Mission planning is the key component of robot, which is used to solve the sequential decision problem of robot. Because of the highly dynamic and uncertain working environment of service robot, how to model and deal with these complex environments is very important for agents to complete mission planning correctly and efficiently. In this paper, a multimission planning method based on L-HMM and utility function description considering path cost for service robot are proposed, high-dimensional partially observable states of agents are abstractly classified into three-dimensional states, combined with HMM model based on Bayesian network. L-HMM not only reasonably models the stochastic process of agent, but also avoids the dimension explosion problem in the process of model solving. In addition, in the iterative process of utility function, considering the impact of path cost on planning effect prevents the agent from planning irrationally and inefficiently due to the encapsulation of navigation nodes. Finally, humanoid robot NAO is used to verify the effect of the theory proposed, multi-mission experiments show the planning results are excellent and highefficient.
{"title":"Multi-Mission Planning of Service Robot Based on L-HMM","authors":"Xiao Wen, Zhen-Gang Zhao","doi":"10.1109/ICCRE51898.2021.9435678","DOIUrl":"https://doi.org/10.1109/ICCRE51898.2021.9435678","url":null,"abstract":"In recent years, the service robot has been developed rapidly, which has brought a lot of convenience for industries and human life. It is of great significance to study service robot. Mission planning is the key component of robot, which is used to solve the sequential decision problem of robot. Because of the highly dynamic and uncertain working environment of service robot, how to model and deal with these complex environments is very important for agents to complete mission planning correctly and efficiently. In this paper, a multimission planning method based on L-HMM and utility function description considering path cost for service robot are proposed, high-dimensional partially observable states of agents are abstractly classified into three-dimensional states, combined with HMM model based on Bayesian network. L-HMM not only reasonably models the stochastic process of agent, but also avoids the dimension explosion problem in the process of model solving. In addition, in the iterative process of utility function, considering the impact of path cost on planning effect prevents the agent from planning irrationally and inefficiently due to the encapsulation of navigation nodes. Finally, humanoid robot NAO is used to verify the effect of the theory proposed, multi-mission experiments show the planning results are excellent and highefficient.","PeriodicalId":382619,"journal":{"name":"2021 6th International Conference on Control and Robotics Engineering (ICCRE)","volume":"1 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":"116872506","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：