{"title":"The GFPA Finger: Parallel-Adaption Merged Robot Finger based on Gear-Flexible Belt Mechanism","authors":"Yixin Wang, R. He, Wenzeng Zhang","doi":"10.1109/ICARM49381.2020.9195344","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195344","url":null,"abstract":"This paper proposes a novel design of an underactuated finger that integrating the advantages of two most frequently used grasping method: parallel-pinching method and self-adaptive method. The finger has an underactuated mechanism using gears, tension spring and flexible belt, GFPA finger. The designed gear transmission and flexible belt-tension spring in the fingers could let the finger grasping object in a merged movement of parallel pinching and self-adaptive, which not only has the advantages of parallel-pinching to grasp the shape of the plate, but also has the advantages of adaptive way to adapt to the shape of the object. Due to the special structure including gear mechanism and tension spring-flexible belt mechanism, the finger could firstly rotate the proximal phalanx while keep the distal phalanx in a parallel motion through the meshed series gear. The distal phalanx will rotate to envelope the object only after the proximal phalanx contact with the object. The GFPA finger has important application prospects in the field of humanoid, aeronautics and Astronautics, etc.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121098609","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":"Sliding Mode Control of Uncertain Discrete-Time Nonlinear Systems Based on Disturbance Observer","authors":"Shuyi Shao, Mou Chen, Xiaohui Yan, Qi-jun Zhao","doi":"10.1109/ICARM49381.2020.9195270","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195270","url":null,"abstract":"This paper designs a discrete-time sliding mode (DTSM) controller for a class of uncertain discrete-time nonlinear systems (DTNSs) subject to bounded time-varying disturbances. By making use of the neural network (NN), the problem of system uncertainties is tackled. The time-varying disturbances are processed based on a designed NN-based discrete-time disturbance observer (DTDO). By taking advantage of the NN and DTDO, a DTSM control approach is developed, and all signals are proven to be bounded for the entire closed-loop system under the designed DTSM controller. Finally, a cart-inverted pendulum system is employed to statement the availability of the proposed control technology.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127436701","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":"Dynamic Modeling for Dielectric Elastomer Actuators Based on LSTM Deep Neural Network","authors":"Huai Xiao, Jundong Wu, Wenjun Ye, Yawu Wang","doi":"10.1109/ICARM49381.2020.9195369","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195369","url":null,"abstract":"This paper proposes a dynamic model for dielectric elastomer actuators (DEAs) based on the long-short term memory (LSTM) deep neural network. The fabrication of the DEA and the framework of the experimental platform are introduced firstly. The behaviors of the DEA are analyzed through several sets of experiments, which shows the DEA has obvious memory behavior (i.e., the hysteresis behavior and creep behavior), where the hysteresis behavior is a symmetry and rate-dependence. Considering that the traditional neural network is difficult to describe the memory property, the LSTM deep neural network is constructed as the dynamic model of the DEA. Then, such neural network is trained according to the experimental data. Finally, the comparation results of the experimental data and the model output verify the effectiveness as well as the generalization ability of the dynamic model.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128712447","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}
Weijun Wang, Songtao Cai, Chaoyang Ma, Wenjie Li, Jian Liu
{"title":"Multi-objective Optimization Design of An Inchworm Climbing Robot","authors":"Weijun Wang, Songtao Cai, Chaoyang Ma, Wenjie Li, Jian Liu","doi":"10.1109/ICARM49381.2020.9195306","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195306","url":null,"abstract":"An optimal design of an inchworm climbing robot is addressed in this paper. Toward a mobile robot, generally speaking, the greater the power, the faster the moving speed. However, high power brings high weight while high weight reduces the speed. In other words, the weight and the moving speed of a climbing robot are two conflicting objectives in the design. A modular robot is proposed in this paper. Five modular motors and two sets of suction cups are leading parts of the robot. High power modules can increase the robot moving speed while adding weight. Large suction cups can increase adsorption force while increasing adsorption time and reducing moving speed. A multi-objective optimization design problem is formulated and the designer can select the final solution from the Pareto solutions. Firstly, a modular inchworm climbing robot is described. Then, a method using a multi-objective optimization is proposed to determine the optimal design variables. Finally, the CAD model of the selected solution and the prototype of this robot is presented and discussed.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409202","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":"Improved Safety-First A-Star Algorithm for Autonomous Vehicles","authors":"Junwei Yu, Jing Hou, Guang Chen","doi":"10.1109/ICARM49381.2020.9195318","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195318","url":null,"abstract":"The research focus of this paper is to improve the traditional A-star algorithm to meet the needs of autonomous vehicles for path safety and smoothness. First, the improved algorithm considers the factor of obstacle distance in the heuristic function. This allows the algorithm to strike a balance between path length and path security, as well as avoiding searching for redundant nodes that are too close to obstacles. Besides, the expansion mode of the 8-connection of the traditional A-star algorithm is improved to the 20-connection, so that the sharpness of turning at the corner can be greatly reduced. And because there is enough safety distance between the planned path and obstacles, the path smoothing can be performed to meet the vehicle dynamics. The improved safety-first A-star algorithm is compared with the traditional A-star algorithm in various scenes. The experimental results prove that the security of the improved safety-first A-star algorithm is greatly enhanced.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123493152","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}
Zhuangzhuang Zhang, Q. Cao, Xiaoxiao Zhu, Yiqi Yang, N. Luan
{"title":"External Force Estimation on a Robotic Surgical Instrument","authors":"Zhuangzhuang Zhang, Q. Cao, Xiaoxiao Zhu, Yiqi Yang, N. Luan","doi":"10.1109/ICARM49381.2020.9195324","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195324","url":null,"abstract":"In this paper, a novel force/torque estimation algorithm for the in-house developed instrument in the robotic-assisted arthroscopic surgery system is proposed. This surgical robot system consists of two parts with 7 degree-of-freedom (DOF) Franka Emika robot for providing 4-DOF Remote Centre of Motion (RCM) about the incision-trocar and an instrument performing bone grinding. The method utilizes Neural Networks (NN) in the Cartesian space to estimate external forces acting on the instrument. The instrument is a rigid-link mechanism attached to the end of the Franka robot by a 6-DOF wrist force sensor. With this proposed method it is possible to obtain force and torque estimation in Cartesian space for any rigid-link wrist mechanism under RCM constraints. Several experiments are performed on an actual robotic system prototype and results show the efficacy of the proposed method.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132374375","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":"Gaze Teleoperation of a Surgical Robot Endoscope for Minimal Invasive Surgery","authors":"Randolph Odekhe, Q. Cao, S. Jing","doi":"10.1109/ICARM49381.2020.9195348","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195348","url":null,"abstract":"This paper presents an innovative approach for controlling an endoscope during robot assisted minimally invasive surgery through the gaze of the surgeon. This system incorporates an eye tracking device which captures the 2D gaze fixation of the surgeon. An event detection algorithm is used in discriminating the fixations and these are sent as UDP to an Arduino microcontroller device where it is used to control two servo motors. The endoscope is attached to the two servos which generates it motion in two different planes which corresponds to the target gaze coordinates of the endoscope fixation point. Experimental results show the effectiveness and robustness of the gaze-based system in intuitively controlling the endoscope.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130213809","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":"Sharp Processing of Blur Image Based on Generative Adversarial Network","authors":"Jinqing Fan, Lan Wu, Chenglin Wen","doi":"10.1109/ICARM49381.2020.9195305","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195305","url":null,"abstract":"Aiming at the very challenging problem of motion blur caused by camera shake, object movement, etc. the traditional method using blur kernel estimation easily leads to estimation errors and makes the image restoration effect poor. We propose a deep convolutional neural network solution to restore blurred images. It is based on DeblurGAN to directly obtain deblurred images from end-to-end motion blurred images. and improves the residual network to effectively restore the detailed information of the image, Finally, through the training and testing of the deep convolution neural network model, it is proved that the method can achieve state-of-the-art performance in several commonly used indexes.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"362 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134093376","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":"Trajectory Prediction Based on Planning Method Considering Collision Risk","authors":"Ya Wu, Jing Hou, Guang Chen, Alois Knoll","doi":"10.1109/ICARM49381.2020.9195282","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195282","url":null,"abstract":"Anticipating the trajectory of Autonomous Vehicles (AV) plays an important role in improving its driving safety. With the rapid development of learning-based method in recent years, the long short-term memory (LSTM) network for sequential data has achieved great success in trajectory forecasting. However, the previous LSTM only considered forward time cues and did not reason on motion intent of rational agents. In this paper, we use planning-based methods follow a sense-reason-predict scheme in which agents reason about intentions and possible ways to the goal. In addition, the collision risk is considered, and the most appropriate future trajectory will be selected with the current state of the agent. We have compared our method against two baselines in highD dataset. Our experimental results show that the planning-based method improves prediction accuracy compared with the baselines.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130856690","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":"Pole-based Localization for Autonomous Vehicles in Urban Scenarios Using Local Grid Map-based Method","authors":"Fan Lu, Guang Chen, Jinhu Dong, Xiaoding Yuan, Shangding Gu, Alois Knoll","doi":"10.1109/ICARM49381.2020.9195330","DOIUrl":"https://doi.org/10.1109/ICARM49381.2020.9195330","url":null,"abstract":"Self-localization is a key component of autonomous vehicles in urban scenarios. In this work, we proposed a localization system which is based on pole-like objects such as trees and street lamps. Pole-like objects are extracted from 3D LiDAR point cloud using a cluster-based method. Based on the pole detection results, we propose a new map representation which consists of numerous local grid maps. In order to tackle the data association problem caused by the ambiguity of pole-like landmarks, the detected poles are directly transformed to the local grid map to define a cost function without pole-to-pole matching. The subsequent non-linear optimization method is utilized to minimize the cost function and generate the vehicle pose. We evaluate our localization system on our self-collected dataset. And the proposed system achieves a root mean square error of less than 18 cm for position and less than 0.52 ° for yaw.","PeriodicalId":189668,"journal":{"name":"2020 5th International Conference on Advanced Robotics and Mechatronics (ICARM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128830796","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}