{"title":"Magnetic Microrobot Control Based on a Designed Nonlinear Disturbance Observer","authors":"Qigao Fan, Hao Wang, Xiaoyu Wu, Yueyue Liu","doi":"10.1109/ICARM58088.2023.10218931","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218931","url":null,"abstract":"Medical microrobots show great promise for precision therapy and drug delivery, such as the treatment of chronic total occlusions. However, magnetic medical microrobots are affected by several factors, such as the medium, the geometry of the microrobots, and the imaging procedure. Notably, traditional control approaches make it difficult or even impossible to obtain reliable physical motion performance of the system. Since the microrobots suffers various uncertainties, the dynamics of microrobots in human tissues (blood or body fluids) is highly nonlinear with multiple uncertainties. Therefore, to achieve accurate motion tracking control for microrobots control system, the obstacles mentioned above must be overcome. In this paper, aiming at the motion control problem of magnetically driven microrobots under the conditions of input saturation constraints, unknown disturbances and model uncertainties, an observer-based control scheme is designed, which uses the minimum knowledge of the system to achieve precise control. The proposed controller consists of an observer designed to obtain an unknown nonlinear magnetic driven microrobots system. According to the designed control law, the exponential disturbance tracking is guaranteed. The experimental results show that the proposed method can effectively overcome the interference problem caused by the unknown uncertainties. Besides, the control performance can be guaranteed.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133786528","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}
Lufeng Chen, Qihang Chen, Xuan Tan, Shuang Liu, Xiaojie Xue
{"title":"Development of an Extrusion-based Five-axis 3D Printing System for Manufacturing of Complex Parts","authors":"Lufeng Chen, Qihang Chen, Xuan Tan, Shuang Liu, Xiaojie Xue","doi":"10.1109/ICARM58088.2023.10218892","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218892","url":null,"abstract":"Additive manufacturing (AM) has gained significant attention in academia and industry over recent decades. Two inherent challenges faced by conventional three-axis printing are the staircase effect and the need for support structures for overhangs. The emerging multi-axis AM introduces a novel printing process with a variable build direction, offering potential solutions to mitigate these issues. In this study, we develop an extrusion-based five-axis Fused Deposition Modeling (FDM) AM system, concentrating on the implementation of cutting-edge multi-axis printing strategies. We present a collection of algorithms, encompassing the 3+2-axis printing pipeline and the five-axis sculpture printing, to demonstrate the feasibility and versatility of our system. The findings reveal that our system can achieve support-free printing of intricate components with enhanced surface quality and curved layer sculpting with variable depth, while simultaneously reducing both printing time and material consumption.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130701721","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":"Force Calibration and Prediction of Soft Stretch Sensor Based on Deep Learning","authors":"Luying Feng, Lianghong Gui, Zehao Yan, Linfan Yu, Canjun Yang, Wei Yang","doi":"10.1109/ICARM58088.2023.10218756","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218756","url":null,"abstract":"Soft stretch sensors are increasingly used in wearable devices and flexible exoskeleton. This paper presents a novel sensing-actuation integrated unit for elastic tension transmission and force estimation. The unit consists of a capacitive sensor, four elastic bands, which can provide enough stiffness, and two stretchable paper-cut fabric shielding layers, which can greatly shield the external interference. The mechanical and electrical properties of the unit were tested on a universal material testing machine and then a simulation test platform was designed to generate the sine curve with different travels and stretch rates. A great amount of data with a total of 35 cases were collected to train our models. Results demonstrated mean square error (MSE) less than 0.21 N2, normalized root mean square error (NRMSE) less than 1.7% for the selected calibration model, and MSE less than 0.28 N2, NRMSE less than 2.0% for the selected prediction model. Our unit together with its calibration and prediction methods in this paper holds great promise in applications such as lightweight flexible exoskeletons.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131180671","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}
Mengsi Wang, Zhenlei Chen, Qing Guo, Haoran Zhang, Yao Yan, D. Jiang
{"title":"Lower Limb Joint Torque Estimation by Neural Network and Sparse Gaussian Process with RIO Kernel","authors":"Mengsi Wang, Zhenlei Chen, Qing Guo, Haoran Zhang, Yao Yan, D. Jiang","doi":"10.1109/ICARM58088.2023.10218774","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218774","url":null,"abstract":"In this study, joint torques in the sagittal plane are estimated using joint angles and electromyography (EMG) signals during subjects' walk at 7 different speeds. First, a general inter-subject model is built by backpropagation neural network (BPNN) with data from 12 subjects. Then, to improve the estimation performance of the inter-subject for a new subject, sparse gaussian process (SGP) with residual estimation using input and output (RIO) kernel is used to compensate for the model as a transfer learning method. The obtained intra-subject model has superior performance with a relatively small amount of data in the training process. This article can be referenced when you have limited training data to estimate the torques on a new subject.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131026118","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":"Tactile-Based Object Pose Estimation Employing Extended Kalman Filter","authors":"Qiguang Lin, Chao Yan, Qiang Li, Yonggen Ling, Yu Zheng, Wangwei Lee, Zhaoliang Wan, Bidan Huang, Xiaofeng Liu","doi":"10.1109/ICARM58088.2023.10218914","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218914","url":null,"abstract":"In this paper, we present a new approach to estimate the pose of an object being manipulated by a multi-fingered robotic hand. The method utilizes advanced tactile sensors with high spatial resolution to optimize the estimation of the object's pose using an Extended Kalman Filter (EKF) based approach. We defined and derived the state and measurement equations, as well as evaluated the estimation accuracy in grasping tasks. The approach is able to effectively account for the pose transition caused by tactile pushing, and the mapping from the object's pose to the contact position and normal direction as measured by the tactile sensor. The method was evaluated in multiple grasping experiments in simulation scenarios. Results show that the estimation can converge towards the ground truth in a relatively short period of time, with displacement and rotation errors remaining within acceptable levels. This new method has the potential to improve the accuracy and reliability of robotic grasping and manipulation tasks.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133674080","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":"An Adaptive Grasping Strategy for Dexterous Hands Based on Proximity-Contact Sensing","authors":"Pengwen Xiong, Yifan Yin, Junjie Liao, Yang Xiao","doi":"10.1109/ICARM58088.2023.10218873","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218873","url":null,"abstract":"In this paper, we propose a dexterous hand grasping strategy based on proximity sensing sensors and contact sensors. The strategy does not need make any assumptions about the properties and surface features of objects. This sensing system consists of two parts: a pose detector to construct the surface near dexterous hand and a slip signal detector to calculate the slip amplitude. These two sensing components are integrated to form a new sensor PT-Tip. When grasping an unknown object, the dexterous hand uses proximity sensors to sense the surrounding environment and find a safe grasping point, then the contact sensor is used to measure the grasping contact process. The covariance matrix of feedback information from tactile sensor is calculated to determine whether the object slips or not. The strategy for three-finger grasping experiments is verified on two objects with different shapes.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132092950","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":"SSNet: Learning Self-Similarity for Few-Shot Semantic Segmentation","authors":"Weisheng Lan, Yu Liu","doi":"10.1109/ICARM58088.2023.10218769","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218769","url":null,"abstract":"Few-shot Segmentation(FSS) refers to the task of segmenting newly introduced classes using only a limited number of closely marked examples. In the past, prototype learning based on metric and segmentation based on visual correspondence mostly ignore the matching relationship of query image itself. In this article, we present a novel self-similarity based hyperrelation network (SSNet), which introduces self-similarity generation module (SGM) and self-similarity mask module (SMM) to capture self-similarity information of target classes in query images and help the network better understand the internal similarity of query images. We also replace the feature mask with the input mask to eliminate the interference of background information in the support image. Experiments on the PASCAL-Sishow that SSNet achieves new state-of-the-art (SOTA), with a mIoU score of 64.6% in the 1-shot scenario and 68.1% in the 5-shot scenario, which is 0.62% higher than the SOTA method in the 1-shot scenario. This demonstrates that SSNet can achieve efficient and accurate few-shot segmentation with only a small number of samples.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116207388","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":"Path Planning of Unmanned Underwater Vehicles Based on Deep Reinforcement Learning Algorithm","authors":"Yu Wang, Zhenzhong Chu, Yongli Hu","doi":"10.1109/ICARM58088.2023.10218902","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218902","url":null,"abstract":"This paper implemented path planning for unmanned underwater vehicle (UUV) using deep reinforcement learning (DRL)algorithms with the UUV Simulator. We used three different algorithms, including twin delayed deep deterministic policy gradient (TD3), Soft Actor-Critic (SAC), and Proximal Policy Optimization (PPO). By conducting multiple experiments in a simulation environment and evaluating their results, we found that all three algorithms have good performance and robustness, and each has its own advantages in different test cases. The research results of this paper can provide some reference and guidance for UUV path planning.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121739842","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}
Hongye Wu, Ping Lin, Yue Ma, Bin Li, Qi Liu, Hongqing Li
{"title":"Automated Creation of Topological Structure Models of Parallel Mechanisms for Kinematic Performance Evaluation","authors":"Hongye Wu, Ping Lin, Yue Ma, Bin Li, Qi Liu, Hongqing Li","doi":"10.1109/ICARM58088.2023.10218779","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218779","url":null,"abstract":"Considering the diversity of topological structures of parallel mechanisms (PMs), this paper presents an approach for the automated generation of topological structure models based on CAD technology. In this method, joints and links are treated as fundamental elements in the skeleton model of a mechanical system, leading to the development of a library of fundamental components readily available to compose a variety of limbs and PMs. A connection graph and its data structure are then developed for describing, in a hierarchical manner, the assembly information among the fundamental components. Equipped with the knowledge and information mentioned above, the limbs and PMs can finally be assembled automatically by identifying and imposing the geometrical constraints that have been already embedded in the models. The merit of this method lies in that 3D schematic diagrams (termed topological structure models) of various limbs and PMs can be created in an illustrative manner by properly selecting a set of fundamental components and then setting their connections, leading to the digitalized and visible topological structure models that are readily for kinematic performance evaluation. Combined with the CAD-CAE integration technology for the mechanical structure design and static/dynamic performance evaluation, a digital design and simulation framework can be formulated for the rapid design of parallel robotic equipment.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121838443","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":"Prescribed Performance Control of Mobile Wheeled Inverted Pendulum Systems Under Arbitrary Initial Conditions","authors":"Mengshi Zhang, Yu Cao, Bo Yang, Jian Huang","doi":"10.1109/ICARM58088.2023.10218825","DOIUrl":"https://doi.org/10.1109/ICARM58088.2023.10218825","url":null,"abstract":"Mobile wheeled inverted pendulum (MWIP) is a typical naturally unstable underactuated system and it is very necessary to constrain its transient response to improve the overall safety. Prescribed performance control (PPC) is an effective method, however the system initial conditions are usually required to be known and constraint, otherwise it can lead to singularity problems. In practical systems, it is often difficult to obtain the exact initial state leading to limitations in the application of PPC. To overcome this issue, this paper presented a composite error transformation function to address the problem of initial condition dependence. A continuous bounded function was designed to compress the arbitrary initial error into the predefined bound to avoid singularities. After a set time, it was degraded to an original system error. Based on this composite transformation, a state feedback controller was proposed for the underactuated MWIP system to achieve the constraint outputs. Then, by employing the Lyapunov theorem, it was guaranteed that the closed-loop system would remain stable. Various numerical simulations under different initial conditions were carried out to prove the validity of the proposed controller.","PeriodicalId":220013,"journal":{"name":"2023 International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121857351","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}