{"title":"Hierarchical Fuzzy Control Design and Stability Analysis for Steering-Control Based Vehicles","authors":"Jifei Xu, W. Norris","doi":"10.1145/3351917.3351961","DOIUrl":"https://doi.org/10.1145/3351917.3351961","url":null,"abstract":"This paper discusses a model-free control design for a class of vehicle systems. A fuzzy logic steering control (FLSC) is designed for trajectory tracking of a wide class of vehicles. The FLSC system utilizes the hierarchical character of the system to reduce the rule base size, thus reducing its complexity. The stability analysis of this control system is addressed. The Lyapunov direct method is utilized to derive stability criteria to guarantee the convergence of the trajectory error, based on our proposed Lyapunov function. Satisfying the criteria guarantees the vehicle to converge to the desired linguistic zero error region. Simulations are given with a skid-steer and Ackermann vehicle model to demonstrate the FLSC's capability to track the desired trajectory and converge to the linguistic zero error region. Our approach can be used for trajectory tracking problems on a wide range of vehicles. It enables straightforward tuning of the controller's behavior.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121299235","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}
Hao Zhang, Rong Li, Y. Duan, Jinxia Yao, Jianjun Su, Meng Wang
{"title":"Research of Multi-path Point Tracking Control Method of Submarine Cable Based on Single Neuron Adaptive PID","authors":"Hao Zhang, Rong Li, Y. Duan, Jinxia Yao, Jianjun Su, Meng Wang","doi":"10.1145/3351917.3351960","DOIUrl":"https://doi.org/10.1145/3351917.3351960","url":null,"abstract":"To solve the problem of submarine cable route tracking, a multi way-points tracking control approach was designed based on Single Neuron Adaptive Proportional-Integral-Derivative controller (SNA-PID). Dynamic model of Remotely Operated Vehicle (ROV) was set up and simplified according to its kinetic characteristics and the actual needs of oceanic engineering application. Three SNA-PID controllers were used to control ROV's heading, surge velocity and sway velocity. And the LOS (line of sight) was utilized to guide ROV motion to track predefined way-points.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122221614","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}
Lingyun Jiang, Kai Qiao, Ruoxi Qin, Jian Chen, Haibing Bu, Bin Yan
{"title":"Unsupervised Adversarial Perturbation Eliminating via Disentangled Representations","authors":"Lingyun Jiang, Kai Qiao, Ruoxi Qin, Jian Chen, Haibing Bu, Bin Yan","doi":"10.1145/3351917.3351987","DOIUrl":"https://doi.org/10.1145/3351917.3351987","url":null,"abstract":"Although deep neural networks (DNNs) could achieve state-of-the-art performance while recognizing images, they often vulnerable to adversarial examples where input intended to be added the small magnitude perturbations may mislead them to incorrect results. It is worth researching on defending against adversarial examples due to the potential security threats. In this paper, we propose an unsupervised method for eliminating adversarial perturbation based on disentangled representations. To achieve adversarial defense, we propose extracting the content and perturbation features of adversarial examples by content encoders and perturbation encoders. Meanwhile, to handle the unpaired training data, we introduce a cross-cycle consistency loss based on disentangled representations and a perturbation branch. We also add an adversarial loss on recovered images to make DNNs predict right. Qualitative results show that our method can eliminate adversarial perturbation without paired training data. We perform extensive experiments on two public datasets MNIST and CIFAR10, which is shown the efficiency of resisting adversarial examples.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126693879","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}
{"title":"Head Design and Optimization of An Emotionally Interactive Robot for the Treatment of Autism","authors":"Feng Wu, Sheng-zhao Lin, Xiangfei Cao, Huixin Zhong, Jia-ming Zhang","doi":"10.1145/3351917.3351992","DOIUrl":"https://doi.org/10.1145/3351917.3351992","url":null,"abstract":"Emotionally interactive robots with facial expressions have various applications, such as research, education, companion, entertainment, and so on. Apart from this, robots with facial expressions demonstrate unique therapeutic effects via eye contact, facial expression recognition and presentation, especially in the early intervention for autistic children. The present study focuses on the head design of a humanoid robot with facial expressions and demonstrates strong attraction of the emotional robotic head presented in the 20th China Hi-Tech Fair. Feedback of the general public's acceptance of the robotic head during the High-tech Fair, was combined with the special needs in treatment of autism, to optimize the design of a second generation of the robotic head. As a result, the mechanical structures of the key components of the head, including the shell of the head, the eyes, the neck, the tongue, achieved better performance, and fewer motors were used to generate more and reliable facial expressions. TPE material which is environmentally friendly and bio-compatible was used in making a more human-like skin covering the robotic head. The facial expressions of the big six basic emotions presented by the robotic head has been tested by the Face++ software, and the recognition accuracy of some facial expressions exceeded 96%. The contributions of the present study are threefold, first of all, it shows that limited number of motors can generate reliable facial expressions of the basic emotions; second, TPE material is suitable for making human-like skin covering the robotic head; third, it shows the potential of our robotic head to be a practical and clinical rehabilitation platform of training autistic patients to recognize and imitate facial expressions of emotions.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"4161 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127560436","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}
{"title":"System Design of Ultrasonic 2D Hand Gesture Trajectory Capture Using Variable Gain","authors":"Ronghua He, Zhili Long, Xiaobing Zhang, Yuyang Yuan","doi":"10.1145/3351917.3351978","DOIUrl":"https://doi.org/10.1145/3351917.3351978","url":null,"abstract":"This paper presents a technique for two dimensional (2D) hand gesture trajectory capture system which can be applied to the interaction of intelligent equipment. Firstly, the sensing principle and hardware are described. In the processing of gesture trajectory, an automatic calibration algorithm based on cross correlation operation is proposed to resolve the interference from environment; the dynamic threshold and variable gain methods are developed to extract distance and the finger positioning model is established basing on the geometric relation. Finally, we obtain the hand gesture trajectory with our hardware in real time and demonstrate the effectiveness of the system.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130001137","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}
{"title":"Weighted LS-SVMR-Based System Identification with Outliers","authors":"Congjun Ma, Haipeng Wang, T. Zhao, S. Dian","doi":"10.1145/3351917.3351940","DOIUrl":"https://doi.org/10.1145/3351917.3351940","url":null,"abstract":"Plenty of methods applied in system identification, while those based on data-driven are increasingly popular. Usually we ignore the absence of outliers among the system to be modeled, but it is unreachable in reality. To improve the precision of identification towards system with outliers, advantageous approaches with robustness are needed. This study analyzes the superiority of weighted Least Square Support Vector Machine Regression (LS-SVMR) in the field of system identification under random outliers, and compare it with LS-SVMR mainly.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128751137","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}
{"title":"The Calibration of Industrial Robot Through Compensation of The Nonlinear Residual Errors","authors":"Gang Zhao, Pengfei Zhang, W. Xiao","doi":"10.1145/3351917.3351969","DOIUrl":"https://doi.org/10.1145/3351917.3351969","url":null,"abstract":"In this paper, the nonlinear positioning errors of a serial industrial robot with six degrees of freedom(6-DOF) are studied using measurements from a FARO laser tracker. An experiment is designed to rotate each robot joint respectively both in forward and reverse directions with different external payloads on the end-effector. The mirror ball fixed on robot links is measured during rotating each joint to obtain the joint coordinates. Then, the positioning errors of each joint are calculated in terms of different movement directions and different external payloads. In addition, the nonlinear residual errors are obtained by subtracting the parametric parts from the total errors. According to experimental results and analysis of robot structures, the gear backlash and joint stiffness are regarded as the main sources of the nonlinear residual errors. Finally, two different compensation strategies are proposed by identifying the nonlinear error parameters and optimizing robot motion path respectively.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115482261","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}
{"title":"Sound Source Localization and Speech Enhancement Algorithm Based on Fixed Beamforming","authors":"Fuchun Liu, Yang Yang, Q. Lin","doi":"10.1145/3351917.3351932","DOIUrl":"https://doi.org/10.1145/3351917.3351932","url":null,"abstract":"In voice-based human-computer interaction, various environmental noise may interfere with the normal transmission of information. Noises may typically lead to performance degradation and efficiency reduction of the voice interaction system. Aiming for reliable sound source localization and effective speech enhancement, we researched those algorithms in scenario of voice-based human-computer interaction with indoor intelligent robots, carried out analysis and implementation. In this paper, we analyzed the localization algorithms based on steered-response power, improved, implemented, and tested on it for its stability in practical application. The results indicated the good performance of the algorithm we proposed under the condition that no strong directional noise interferes with the target signal. Reliable two-dimensional sound localization information can be provided, ensuring real-time performance of the system. We also implemented the speech enhancement algorithm based on fixed beamforming, using the sound localization information provided by the two-dimensional sound localization algorithm. The results showed that the algorithm has a certain inhibitory effect on non-correlative noise on the premise of reliable sound source localization and undistorted signal of speech.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131653397","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}
{"title":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","authors":"","doi":"10.1145/3351917","DOIUrl":"https://doi.org/10.1145/3351917","url":null,"abstract":"","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122038630","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}