Proceedings of the 2019 3rd International Conference on Automation, Control and Robots最新文献

{"title":"Method of Industrial Automated Optical-Electronic Control of Granulometric Composition of Mineral Fertilizers","authors":"D. Yunovidov, V. Shabalov, V. Sokolov","doi":"10.1145/3365265.3365268","DOIUrl":"https://doi.org/10.1145/3365265.3365268","url":null,"abstract":"The article describes the solution of the operational control problem of particle size composition of industrially produced mineral fertilizers by the optical-electronic method. The device and algorithm for automated online control in industrial conditions is proposed. This scheme consists of three independent parts: the system of sampling from the conveyor belt, the system of sampling in the field of analysis (feeder) and the block of optical-electronic detection of granules. The peculiarities of the proposed scheme include online control of the fraction of granules (granulometric composition, which was calibrated by mass or optical distribution) and several abilities (to analyze the shape and color of granules; to work in industrial conditions and to transfer data into the factory information system - \"PISystem\"). Sampling from the conveyor belt is carried out by a robotic rotary system. The transfer of the sample to the analysis area was performed by the linear vibrations of the sample feed system. The integrated computer controls the entire sampling and feeding scheme. Furthermore, the algorithm for calculating parameters of granules was developed. It consists of obtaining an optical-electronic image (three-dimensional Red-Green-Blue matrix of pixel intensities), image pre-processing (smoothing, binaryization and morphology), calculation of closed contours, approximation of the found contours by ellipses and calculation of ellipse parameters (long and short axis, axis ratios, average color). All stages of receiving and processing of the information are automated and implemented on programming language Python 3.7. Statistical indicators of the proposed method are calculated and the results are compared with the laboratory techniques of granulometric composition analyses. The linear correlation map of different parameters of technological process (calculated granulometric composition, raw material consumption, work of drum dryer-granulator, vibrating screen and crushers) is given.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116962275","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":"A Modular Simulation Platform for Training Robots via Deep Reinforcement Learning and Multibody Dynamics","authors":"S. Benatti, A. Tasora, Dario Fusai, D. Mangoni","doi":"10.1145/3365265.3365274","DOIUrl":"https://doi.org/10.1145/3365265.3365274","url":null,"abstract":"In this work we focus on the role of Multibody Simulation in creating Reinforcement Learning virtual environments for robotic manipulation, showing a versatile, efficient and open source toolchain to create directly from CAD models. Using the Chrono::Solidworks plugin we are able to create robotic environments in the 3D CAD software Solidworks® and later convert them into PyChrono models (PyChrono is an open source Python module for multibody simulation). In addition, we demonstrate how collision detection can be made more efficient by introducing a limited number of contact primitives instead of performing collision detection and evaluation on complex 3D meshes, still reaching a policy able to avoid unwanted collisions. We tested this approach on a 6DOF robot Comau Racer3: the robot, together with a 2 fingers gripper (Hand-E by Robotiq) was modelled using Solidworks®, imported as a PyChrono model and then a NN was trained in simulation to control its motor torques to reach a target position. To demonstrate the versatility of this toolchain we also repeated the same procedure to model and then train the ABB IRB 120 robotic arm.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"PP 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126675672","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":"A Novel Varying Angle Fiber-Reinforced Elastomer as a Soft Pneumatic Bending Actuator","authors":"S. Kandasamy, H. Devaraj, Logan Stuart, A. McDaid, K. Aw","doi":"10.1145/3365265.3365272","DOIUrl":"https://doi.org/10.1145/3365265.3365272","url":null,"abstract":"Soft actuators are inherently compliant, highly dexterous and an extremely lightweight alternative that are progressively replacing traditional electromechanical actuators in a wide range of robotic applications that involves close interaction with humans. This research aims to demonstrate the bending characteristics, and the force response achieved by a soft pneumatic actuator made from a unique fabrication technique; namely continuous fiber reinforcement technique (CFR) to create a fiber braiding, which is significantly simpler than the previous work, which we named as split fiber reinforce technique (SFR). The performances of SFR and CFR were compared. The active layer was a highly elastic material that can stretch up to 900% of its original length without losing its elasticity. Thus, the actuators' angular profiles were improved by a factor of 89% & 92% for the SFR and CFR respectively than that of the benchmark. The CFR actuator in particular was demonstrated to be capable of exerting blocking force of up to 1.63 N at just 30.75% of the input pressure compared to the benchmark actuator, while the SFR was capable of exerting a slightly lower 1.5 N of force beyond which pressurization gave way to lateral expansion. The bending capability and compliance of these varying angle fiber reinforced elastomer-based soft pneumatic actuators shows high potential for implementation in human-centric body powered robotic actuation tasks for rehabilitation and other delicate industrial grasping tasks.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134346527","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":"Serious Game based on Skeleton Shape Matching for Functional Rehabilitation Exercises","authors":"M. Z. Amrani, N. Achour","doi":"10.1145/3365265.3365279","DOIUrl":"https://doi.org/10.1145/3365265.3365279","url":null,"abstract":"Rehabilitation exercises are now presented as games, where the patient performs the exercises by playing video games, this kind of games is designed for a primary purpose other than pure entertainment, they are serious games. We can find in the literature some serious games for functional rehabilitation, but almost all of them are based on video recordings or images, without full body tracking. In this paper, we present an interactive serious game based on full body tracking and using virtual reality techniques. A virtual coach supervises the users and gives instructions to help user performing the rehabilitation exercises correctly. With a group of eight players for a set of six therapeutic exercises, we have reached a high classification accuracy and positive results on the experience questionnaire.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126162172","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":"Low Cost Lower Limb Exoskeleton for Assisting Gait Rehabilitation: Design and Evaluation","authors":"L. I. Minchala, Anthony J. Velasco, Jonathan Blandin, Fabian Astudillo-Salinas, Andrés Vázquez-Rodas","doi":"10.1145/3365265.3365276","DOIUrl":"https://doi.org/10.1145/3365265.3365276","url":null,"abstract":"This paper presents the design and implementation of a low cost, yet robust, three degrees of freedom (DoF) lower limb exoskeleton intended to assist patients in gait rehabilitation. The majority of patients with incomplete spinal cord injuries (SCI) are able to walk after a rehabilitation process. Among the broad options of physical rehabilitation therapies, there is a relatively recent interest in those assisted by robotic exoskeletons, due to features as high precision movements and automated repetitions. In this context, the subsystems of the exoskeleton prototype described throughout this paper are the following: i) a controlled area network (CAN) communications bus with SDO protocol; and, ii) a hierarchical control system consisting of two levels: a trajectory generator of the walk biomechanics implemented in a centralized controller (CC), and distributed controllers (DC) installed at each joint of the exoskeleton. The multiplication mechanical system uses reduction speed boxes based on cycloidal and planetary gears. Experimental results of the prototype operating, with and without carrying weight, show effectiveness of the whole control system for tracking a non-pathological gait biomechanics trajectory.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127890731","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":"Rotational Invariant Object Recognition for Robotic Vision","authors":"C. Vilar, Silvia Krug, B. Thornberg","doi":"10.1145/3365265.3365273","DOIUrl":"https://doi.org/10.1145/3365265.3365273","url":null,"abstract":"Depth cameras have enhanced the environment perception for robotic applications significantly. They allow to measure true distances and thus enable a 3D measurement of the robot surroundings. In order to enable robust robot vision, the objects recognition has to handle rotated data because object can be viewed from different dynamic perspectives when the robot is moving. Therefore, the 3D descriptors used of object recognition for robotic applications have to be rotation invariant and implementable on the embedded system, with limited memory and computing resources. With the popularization of the depth cameras, the Histogram of Gradients (HOG) descriptor has been extended to recognize also 3D volumetric objects (3DVHOG). Unfortunately, both version are not rotation invariant. There are different methods to achieve rotation invariance for 3DVHOG, but they increase significantly the computational cost of the overall data processing. Hence, they are unfeasible to be implemented in a low cost processor for real-time operation. In this paper, we propose an object pose normalization method to achieve 3DVHOG rotation invariance while reducing the number of processing operations as much as possible. Our method is based on Principal Component Analysis (PCA) normalization. We tested our method using the Princeton Modelnet10 dataset.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124680161","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":"Segmentation of Very Sparse and Noisy Point Clouds","authors":"P. Fleischmann, K. Berns","doi":"10.1145/3365265.3365284","DOIUrl":"https://doi.org/10.1145/3365265.3365284","url":null,"abstract":"This paper summarizes an approach to segment 3D point clouds into drivable ground, obstacles, and overhangs. It was developed for outdoor Time-of-Flight cameras which only provide very sparse measurements. The proposed methodology takes advantage of the matrix-like data structure of the CMOS sensor for segmentation in order to increase efficiency. Furthermore, it was tailored to handle typical offhighway characteristics with different slopes and missing measurements and can be adapted to various mounting positions and vehicle properties. First, the algorithm processes the data column-wise using geometric relations. Afterward, the neighborhood of a measurement is considered to improve the initial classification. Finally, overhangs are separated.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"102 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131239288","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":"Obtaining the Data for Formation of 3D Road Scene from the Radar Data","authors":"A. V. Averin, I. A. Kostin, N. V. Panokin","doi":"10.1145/3365265.3365277","DOIUrl":"https://doi.org/10.1145/3365265.3365277","url":null,"abstract":"This paper considers the problems of designing of technical vision systems based on millimeter radar technology. The architecture of the software for simulating the millimeter radar operation using mathematical models that simulate various objects of the road scene is considered. 3D road scenes of various configurations, taking into account the impact of the underlying surface have been studied. The possibility to classify the road obstacles and mobile agents of the road scene has been shown by analyzing the radar data from a car radar. The architecture of a neural network classifier that solves the problem of classification of road objects have been proposed.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130121877","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":"On the Event-based Attack-tolerant Control: A Polytopic Representation","authors":"Souad Bezzaoucha Rebai, H. Voos","doi":"10.1145/3365265.3365281","DOIUrl":"https://doi.org/10.1145/3365265.3365281","url":null,"abstract":"In the present contribution, we present a new event-based control representation. Based on the polytopic approach, more specifically the sector nonlinear transformation, an event-based attack-tolerant control and scheduling co-design strategy is proposed. From the event triggering definition (sample-and-hold strategy), polytopic writing of the eventtriggered feedback control is first presented and then incorporated into the system dynamics for analysis. Our goal is to present a unique model that is able to deal with the co-design problem simultaneously and that can be handled by classical control synthesis tools. The novel representation, including data deception and attack tolerant control is formulated as a BMI optimization problem ensuring both stability and some level performance requirements (L2 attenuation of the cyber-attack).","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121819695","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":"Sampling-based Motion Planning via Control Barrier Functions","authors":"Guang Yang, Bee Vang, Zachary T. Serlin, C. Belta, Roberto Tron","doi":"10.1145/3365265.3365282","DOIUrl":"https://doi.org/10.1145/3365265.3365282","url":null,"abstract":"Robot motion planning is central to real-world autonomous applications, such as self-driving cars, persistence surveillance, and robotic arm manipulation. One challenge in motion planning is generating control signals for nonlinear systems that result in obstacle free paths through dynamic environments. In this paper, we propose Control Barrier Function guided Rapidly-exploring Random Trees (CBF-RRT), a sampling-based motion planning algorithm for continuoustime nonlinear systems in dynamic environments. The algorithm focuses on two objectives: efficiently generating feasible controls that steer the system toward a goal region, and handling environments with dynamical obstacles in continuous time. We formulate the control synthesis problem as a Quadratic Program (QP) that enforces Control Barrier Function (CBF) constraints to achieve obstacle avoidance. Additionally, CBF-RRT does not require nearest neighbor or explicit collision checks during sampling.","PeriodicalId":358714,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Automation, Control and Robots","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128943268","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}