Pub Date : 2015-12-01DOI: 10.1109/ROBIO.2015.7418974
Bai Li, Zhijiang Shao
Trajectory planning is a critical aspect in driving an autonomous tractor-trailer vehicle. This study considers trajectory planning as a minimal-time optimal control problem that incorporates the kinematics, mechanical/physical constraints, environmental requirements and an optimization criterion. This formulation benefits in the ability to directly handle time-dependent requirements. A gradient-based numerical solver is adopted to tackle the formulated optimal control problem. An incremental strategy is proposed to enhance the global optimization ability of that solver and to help find satisfactory solutions in challenging cases. Specifically, when an optimal solution is found, we doubt whether that is merely a local optimum and then still expect to make evolution; when optimal solutions are not easy to obtain, we expect at least one feasible solution first, which is taken as a preliminary guess to assist the subsequent optimization process. Both procedures proceed alternatively until no progress can be made any further. Some intricate simulation results are well beyond manual operation ability. Moreover, our overall proposal, as a unified and open framework, can deal with a wide variety of user-specified requirements.
{"title":"An incremental strategy for tractor-trailer vehicle global trajectory optimization in the presence of obstacles","authors":"Bai Li, Zhijiang Shao","doi":"10.1109/ROBIO.2015.7418974","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418974","url":null,"abstract":"Trajectory planning is a critical aspect in driving an autonomous tractor-trailer vehicle. This study considers trajectory planning as a minimal-time optimal control problem that incorporates the kinematics, mechanical/physical constraints, environmental requirements and an optimization criterion. This formulation benefits in the ability to directly handle time-dependent requirements. A gradient-based numerical solver is adopted to tackle the formulated optimal control problem. An incremental strategy is proposed to enhance the global optimization ability of that solver and to help find satisfactory solutions in challenging cases. Specifically, when an optimal solution is found, we doubt whether that is merely a local optimum and then still expect to make evolution; when optimal solutions are not easy to obtain, we expect at least one feasible solution first, which is taken as a preliminary guess to assist the subsequent optimization process. Both procedures proceed alternatively until no progress can be made any further. Some intricate simulation results are well beyond manual operation ability. Moreover, our overall proposal, as a unified and open framework, can deal with a wide variety of user-specified requirements.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"360 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132257098","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418960
Lixing Jiang, Huimin Lu, Vo Duc My, A. Koch, A. Zell
Superpixels aim to group homogenous pixels by a series of characteristics in an image. They decimate redundancy that may be utilized later by more computationally expensive algorithms. The most popular algorithms obtain superpixels based on an energy function on a graph. However, these graph-based methods have a high computational time consumption. This study presents a fast and high quality over-segmentation method by a watershed transform based on computing the dissimilarity of pixels among RGB(D) cues and gradient maps. Specifically, we first capture a gradient map based on an image to enhance and explain directional variations in the image scene. A distance function then measures the similarity among adjacent pixels, which is calculated according to RGB(D) values. A fast marker-controlled watershed (MCW) algorithm traverses the entire image based on the distance function. Finally, we acquire all watersheds consisting of superpixel contours. Experimental results compare state-of-the-art algorithms and highlight the effectiveness of the proposed method. As an application, the proposed superpixel algorithm can be used in applications aiming for real-time, like mobile robot saliency detection and segmentation.
{"title":"Superpixel segmentation based gradient maps on RGB-D dataset","authors":"Lixing Jiang, Huimin Lu, Vo Duc My, A. Koch, A. Zell","doi":"10.1109/ROBIO.2015.7418960","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418960","url":null,"abstract":"Superpixels aim to group homogenous pixels by a series of characteristics in an image. They decimate redundancy that may be utilized later by more computationally expensive algorithms. The most popular algorithms obtain superpixels based on an energy function on a graph. However, these graph-based methods have a high computational time consumption. This study presents a fast and high quality over-segmentation method by a watershed transform based on computing the dissimilarity of pixels among RGB(D) cues and gradient maps. Specifically, we first capture a gradient map based on an image to enhance and explain directional variations in the image scene. A distance function then measures the similarity among adjacent pixels, which is calculated according to RGB(D) values. A fast marker-controlled watershed (MCW) algorithm traverses the entire image based on the distance function. Finally, we acquire all watersheds consisting of superpixel contours. Experimental results compare state-of-the-art algorithms and highlight the effectiveness of the proposed method. As an application, the proposed superpixel algorithm can be used in applications aiming for real-time, like mobile robot saliency detection and segmentation.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131649318","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418870
Xuan Xiao, Go Fukuda, F. Asano
This paper presents mathematical analyses of steady walking states in underactuated limit cycle walking. We introduce an underactuated rimless wheel with a torso to analyze target steady walking states. Then the formula of boundary conditions are derived and the properties of the steady gaits are analyzed. The transition function of state error is derived from the properties of the steady gaits, and an optimal steady walking state is generated. In addition, we generate the target steady walking speed on the underactuated rimless wheel model and verify our results using numerical simulations. As a conclusion, optimal steady states can be discovered and generated based on the mathematical analysis of dynamic walking states.
{"title":"Mathematical analysis of steady walking states in underactuated limit cycle walking","authors":"Xuan Xiao, Go Fukuda, F. Asano","doi":"10.1109/ROBIO.2015.7418870","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418870","url":null,"abstract":"This paper presents mathematical analyses of steady walking states in underactuated limit cycle walking. We introduce an underactuated rimless wheel with a torso to analyze target steady walking states. Then the formula of boundary conditions are derived and the properties of the steady gaits are analyzed. The transition function of state error is derived from the properties of the steady gaits, and an optimal steady walking state is generated. In addition, we generate the target steady walking speed on the underactuated rimless wheel model and verify our results using numerical simulations. As a conclusion, optimal steady states can be discovered and generated based on the mathematical analysis of dynamic walking states.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"424 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126715429","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418924
Yanhong He, Huihuan Qian, Shuaijun Li, N. Cui, Yangsheng Xu
In this paper, a fast charging system (FCS) is designed for service robots. In this design, batteries are used to due to its energy density, whereas supercapacitors (SCs) are used to enhance the power density. DC-DC converter controls the FCS. The main advantage of the design of fast charging system is that, the SCs are charged with a large current fast and then discharge to the batteries with small current slowly. This feature is beneficial for batteries' long-life and store more energy for service robots which have been in great demand for multiple purposes, such as elderly care, child education etc. Some experimental and testing results are presented to validate the design of FCS for service robots.
{"title":"Design of a fast charging system for service robots","authors":"Yanhong He, Huihuan Qian, Shuaijun Li, N. Cui, Yangsheng Xu","doi":"10.1109/ROBIO.2015.7418924","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418924","url":null,"abstract":"In this paper, a fast charging system (FCS) is designed for service robots. In this design, batteries are used to due to its energy density, whereas supercapacitors (SCs) are used to enhance the power density. DC-DC converter controls the FCS. The main advantage of the design of fast charging system is that, the SCs are charged with a large current fast and then discharge to the batteries with small current slowly. This feature is beneficial for batteries' long-life and store more energy for service robots which have been in great demand for multiple purposes, such as elderly care, child education etc. Some experimental and testing results are presented to validate the design of FCS for service robots.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123466508","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418831
Yazhe Tang, Shaorong Xie, F. Lin, Jianyu Yang, Youfu Li
Catadioptric omnidirectional images suffer from serious distortions because of quadratic mirrors involved. For that reason, most of visual features developed on the basis of the perspective model are difficult to achieve a satisfactory performance when directly applied to the omnidirectional image. To accurately calculate the deformed target neighborhood, this paper employs equivalent projection approach to effectively formulate the distortion of omnidirectional camera. On the basis of equivalent projection, this paper presents a distortion invariant multi-feature fusion method for robust feature representation in omnidirectional image. Given the Gaussian Mixture Model (GMM), multiple features can be integrated into a whole probability framework. In other words, GMM transforms the problem of features matching into the multi-channel clustering. The fragment-based tracking framework can robustly handle the partial occlusion relying on an adaptive weight metric mechanism. Finally, a series of experiments will be presented to validate the performance of the proposed algorithm.
{"title":"Equivalent projection based distortion invariant visual tracking for omnidirectional vision","authors":"Yazhe Tang, Shaorong Xie, F. Lin, Jianyu Yang, Youfu Li","doi":"10.1109/ROBIO.2015.7418831","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418831","url":null,"abstract":"Catadioptric omnidirectional images suffer from serious distortions because of quadratic mirrors involved. For that reason, most of visual features developed on the basis of the perspective model are difficult to achieve a satisfactory performance when directly applied to the omnidirectional image. To accurately calculate the deformed target neighborhood, this paper employs equivalent projection approach to effectively formulate the distortion of omnidirectional camera. On the basis of equivalent projection, this paper presents a distortion invariant multi-feature fusion method for robust feature representation in omnidirectional image. Given the Gaussian Mixture Model (GMM), multiple features can be integrated into a whole probability framework. In other words, GMM transforms the problem of features matching into the multi-channel clustering. The fragment-based tracking framework can robustly handle the partial occlusion relying on an adaptive weight metric mechanism. Finally, a series of experiments will be presented to validate the performance of the proposed algorithm.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121430773","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7419738
Xiang Chen, Y. Qiao
Nowadays, people are increasingly concerned about the safety of traffic systems. Road segmentation and recognition is a fundamental problem in perceiving traffic environments and serve as the basis for self-driving cars. In this paper, inspired by an iterative deep analysis thinking, we propose a novel method which is able to learning powerful features step by step, and solve the optimal precision by balancing local and global information to conduct pixel-level classification for road segmentation. Firstly, we introduce an iterative deep analysis thinking which shows that how to design a strong and robustness deep model from failure experience. Secondly, we choose a powerful global features learning network as basis to create a novel framework for our task. Meanwhile, we employ the patch and multi-scale pyramid as input to enhance local features learning. We conduct experiments on three datasets from KITTI Vision Benchmark, namely UU, UM, UMM. The experimental results demonstrate that our proposed method obtains comparable performance with state-of-the-art methods on these datasets.
{"title":"Road segmentation via iterative deep analysis","authors":"Xiang Chen, Y. Qiao","doi":"10.1109/ROBIO.2015.7419738","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7419738","url":null,"abstract":"Nowadays, people are increasingly concerned about the safety of traffic systems. Road segmentation and recognition is a fundamental problem in perceiving traffic environments and serve as the basis for self-driving cars. In this paper, inspired by an iterative deep analysis thinking, we propose a novel method which is able to learning powerful features step by step, and solve the optimal precision by balancing local and global information to conduct pixel-level classification for road segmentation. Firstly, we introduce an iterative deep analysis thinking which shows that how to design a strong and robustness deep model from failure experience. Secondly, we choose a powerful global features learning network as basis to create a novel framework for our task. Meanwhile, we employ the patch and multi-scale pyramid as input to enhance local features learning. We conduct experiments on three datasets from KITTI Vision Benchmark, namely UU, UM, UMM. The experimental results demonstrate that our proposed method obtains comparable performance with state-of-the-art methods on these datasets.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126305772","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418834
Yueen Hou, Ping Ye, Wei Zeng
Visual tracking is important in the field of robotic controlling. However, developing a object tracker, which is robust in complex scenarios, is still a challenging work. In the paper, we propose a novel structural local sparse representation based residual error consistent ranking tracker. In the particle filter framework, candidate targets are linearly combined by a local sparse dictionary. By exploiting temporal consistency, the proposed algorithm develops a residual error consistency term to constraint the objective function of sparse representation. The alignment-pooling algorithm is used to obtain pooled features which contain similarity information of candidates. For further robustness, we develop residual error scores to evaluate the likelihood of candidates belonging to targets. For different natures of the residual error scores and pooled features, a ranking mechanism is proposed to fuse them. Furthermore, the dictionary updating scheme, which combines incremental subspace learning and sparse representation together, uses ranking results of predicted targets to decide which of the predicted targets are collected for dictionary updating. Finally, the proposed tracker performs favorably against 6 state-of-the-art trackers on 6 challenging video sequences.
{"title":"Temporal consistency object tracker with ranking mechanism","authors":"Yueen Hou, Ping Ye, Wei Zeng","doi":"10.1109/ROBIO.2015.7418834","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418834","url":null,"abstract":"Visual tracking is important in the field of robotic controlling. However, developing a object tracker, which is robust in complex scenarios, is still a challenging work. In the paper, we propose a novel structural local sparse representation based residual error consistent ranking tracker. In the particle filter framework, candidate targets are linearly combined by a local sparse dictionary. By exploiting temporal consistency, the proposed algorithm develops a residual error consistency term to constraint the objective function of sparse representation. The alignment-pooling algorithm is used to obtain pooled features which contain similarity information of candidates. For further robustness, we develop residual error scores to evaluate the likelihood of candidates belonging to targets. For different natures of the residual error scores and pooled features, a ranking mechanism is proposed to fuse them. Furthermore, the dictionary updating scheme, which combines incremental subspace learning and sparse representation together, uses ranking results of predicted targets to decide which of the predicted targets are collected for dictionary updating. Finally, the proposed tracker performs favorably against 6 state-of-the-art trackers on 6 challenging video sequences.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"73 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126106767","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7419040
Kazuki Igeta, A. Namiki
In this study, we propose a novel air-hockey robot that can select the optimal actions according to the behavior of an opponent human player. The attack behavior of the robot is optimized during an air hockey game by recognizing the motions of the puck and the human hand. First, we explain how to calculate the attack position. Second, we explain the algorithm for decision making using an attack value based on the puck and the position of the human hand. The attack value is calculated by considering the physical constraints of both the attack and defense sides. Then, we show experimental data and explain the reason for robot behaviors based on the calculated attack value.
{"title":"A decision-making algorithm for an air-hockey robot that decides actions depending on its opponent player's motions","authors":"Kazuki Igeta, A. Namiki","doi":"10.1109/ROBIO.2015.7419040","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7419040","url":null,"abstract":"In this study, we propose a novel air-hockey robot that can select the optimal actions according to the behavior of an opponent human player. The attack behavior of the robot is optimized during an air hockey game by recognizing the motions of the puck and the human hand. First, we explain how to calculate the attack position. Second, we explain the algorithm for decision making using an attack value based on the puck and the position of the human hand. The attack value is calculated by considering the physical constraints of both the attack and defense sides. Then, we show experimental data and explain the reason for robot behaviors based on the calculated attack value.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114154601","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418798
Ismail Kuru, J. Coy, F. Ferrer, T. Lenarz, H. Maier, T. Lüth
The tympanoplasty-III is a widely used method to heal the conductive hearing loss by reconstructing the ossicular chain with passive middle ear prostheses. One of the major challenges during this procedure is to determine the correct prosthesis length intraoperatively, which specifies the tension on the tissues. A suboptimal tension on the tissues may decrease the sound conduction, cause prosthesis luxation and even injure the tympanic membrane or inner ear. Furthermore, the tissue deformations after the operation and variations in the ambient pressure may cause the same problems even if the prosthesis length was set correctly during the operation. However, the state of the art prostheses can only be adjusted during the operation and they cannot adapt themselves after the operation. In this paper, we present a new middle ear prosthesis that can adapt its length to changes occurring after the operation such as tissue swelling or unbalanced middle ear pressure.
{"title":"A new postoperative adjustable prosthesis for ossicular chain reconstructions","authors":"Ismail Kuru, J. Coy, F. Ferrer, T. Lenarz, H. Maier, T. Lüth","doi":"10.1109/ROBIO.2015.7418798","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418798","url":null,"abstract":"The tympanoplasty-III is a widely used method to heal the conductive hearing loss by reconstructing the ossicular chain with passive middle ear prostheses. One of the major challenges during this procedure is to determine the correct prosthesis length intraoperatively, which specifies the tension on the tissues. A suboptimal tension on the tissues may decrease the sound conduction, cause prosthesis luxation and even injure the tympanic membrane or inner ear. Furthermore, the tissue deformations after the operation and variations in the ambient pressure may cause the same problems even if the prosthesis length was set correctly during the operation. However, the state of the art prostheses can only be adjusted during the operation and they cannot adapt themselves after the operation. In this paper, we present a new middle ear prosthesis that can adapt its length to changes occurring after the operation such as tissue swelling or unbalanced middle ear pressure.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"33 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120999407","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 : 2015-12-01DOI: 10.1109/ROBIO.2015.7418925
F. Xiao, Yongsheng Gao, Shengxin Wang, Jie Zhao
In this paper, a new prediction algorithm combining multiple linear regression with autoregressive model and Kalman filter (MLRAR-KF) is proposed to predict the elbow joint angle. The MLRAR model updating weights with Kalman filter is shown to be able to predict joint motion with high accuracy and well robustness. In comparison to existing prediction algorithms, MLRAR-KF can predict joint angle with higher accuracy and better robustness. A data acquisition system was used to collect sEMG and elbow joint angle signals of human upper limb. The experimental results demonstrate the benefits of MLRAR-KF prediction algorithm. Comparison of computational complexity about some existing prediction methods and MLRAR-KF is conducted to analyze the real-time performance.
{"title":"Prediction of joint angle by combining multiple linear regression with autoregressive (AR) model and Kalman filter","authors":"F. Xiao, Yongsheng Gao, Shengxin Wang, Jie Zhao","doi":"10.1109/ROBIO.2015.7418925","DOIUrl":"https://doi.org/10.1109/ROBIO.2015.7418925","url":null,"abstract":"In this paper, a new prediction algorithm combining multiple linear regression with autoregressive model and Kalman filter (MLRAR-KF) is proposed to predict the elbow joint angle. The MLRAR model updating weights with Kalman filter is shown to be able to predict joint motion with high accuracy and well robustness. In comparison to existing prediction algorithms, MLRAR-KF can predict joint angle with higher accuracy and better robustness. A data acquisition system was used to collect sEMG and elbow joint angle signals of human upper limb. The experimental results demonstrate the benefits of MLRAR-KF prediction algorithm. Comparison of computational complexity about some existing prediction methods and MLRAR-KF is conducted to analyze the real-time performance.","PeriodicalId":325536,"journal":{"name":"2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116240732","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：