In this paper, a hybrid method based on deep learning is proposed to visually classify terrains encountered by mobile robots. Considering the limited computing resource on mobile robots and the requirement for high classification accuracy, the proposed hybrid method combines a convolutional neural network with a support vector machine to keep a high classification accuracy while improve work efficiency. The key idea is that the convolutional neural network is used to finish a multi-class classification and simultaneously the support vector machine is used to make a two-class classification. The two-class classification performed by the support vector machine is aimed at one kind of terrain that users are mostly concerned with. Results of the two classifications will be consolidated to get the final classification result. The convolutional neural network used in this method is modified for the on-board usage of mobile robots. In order to enhance efficiency, the convolutional neural network has a simple architecture. The convolutional neural network and the support vector machine are trained and tested by using RGB images of six kinds of common terrains. Experimental results demonstrate that this method can help robots classify terrains accurately and efficiently. Therefore, the proposed method has a significant potential for being applied to the on-board usage of mobile robots.
The cable-driven soft arm is mostly made of soft material; it is difficult to control because of the material characteristics, so the traditional robot arm modeling and control methods cannot be directly applied to the soft robot arm. In this paper, we combine the data-driven modeling method with the reinforcement learning control method to realize the position control task of robotic soft arm, the method of control strategy based on deep Q learning. In order to solve slow convergence and unstable effect in the process of simulation and migration when deep reinforcement learning is applied to the actual robot control task, a control strategy learning method is designed, which is based on the experimental data, to establish a simulation environment for control strategy training, and then applied to the real environment. Finally, it is proved by experiment that the method can effectively complete the control of the soft robot arm, which has better robustness than the traditional method.
Научно-технический вестник информационных технологий, механики и оптики, АннотацияИсследована задача синтеза траекторного управления движением мобильного робота в нестационарном внешнем окружении, в частности, при наличии в рабочем пространстве робота внешних подвижных объектов, с использованием методов дифференциальной геометрии и методов стабилизации инвариантных многообразий в пространстве выходов объекта управления. Для построения алгоритма управления рассмотрена относительная динамика объекта управления и внешнего подвижного объекта, и применяются методы дифференциально-геометрического преобразования исходной модели к задачно-ориентированной системе координат, формулирующей исходную задачу в терминах продольного движения, ортогонального и углового отклонений, для которой строятся пропорционально-дифференциальные алгоритмы управления с прямой компенсацией нелинейностей. Основные результаты представлены задачно-ориентированной моделью пространственного движения и соответствующими нелинейными алгоритмами управления. Для иллюстрации работоспособности предлагаемого метода приведен пример моделирования движения твердого тела вдоль прямолинейной траектории при наличии в рабочем пространстве внешнего подвижного объекта, движущегося по прямолинейной траектории, пересекающей желаемую траекторию движения объекта управления. В примере реализован обход внешнего движущегося объекта по круговой траектории и возврат на исходную желаемую траекторию. Ключевые слова траекторное управление, преобразование координат, управление движением Благодарности Работа выполнена при поддержке: гранта Президента Российской Федерации №14.Y3116.9281-НШ; Российского фонда фундаментальных исследований (грант 17-58-53129); гранта Государственного фонда естественных наук Китая (грант 61611530709 и 61503108). Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2017, vol. 17, no. 5, pp. 790-797 (in Russian). doi: 10.17586/2226-1494-2017 Abstract The paper deals with the trajectory control synthesis of a mobile robot movement in a nonstationary external environment, in particular, in the presence of external mobile objects in the robot working space, by differential geometry methods and stabilization methods for invariant manifolds in the space of control object outputs. For control algorithm development, the relative dynamics of the control object and the external mobile object is considered and the methods of differential-geometric transformation of the initial model to the task-oriented coordinates are formulated. The latter formulates the initial problem in terms of longitudinal motion, orthogonal and angular deviations, and the proportional differential control algorithms are TRAJECTORY CONTROL FOR A ROBOT MOTION IN PRESENSE OF MOVING OBSTACLES
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.