This paper presents an advanced control algorithm, which accounts for an additional impact of a castor wheel on a tri-wheel robot's trajectory. It demonstrates how to use the information on the angle of twist in o...
详细信息
This paper presents an advanced control algorithm, which accounts for an additional impact of a castor wheel on a tri-wheel robot's trajectory. It demonstrates how to use the information on the angle of twist in order to limit the errors stemming from odometry. Thanks to applying the proven relationship between the trajectory's curvature and the angle of twist of a castor free wheel, we reduced the driving wheels' rotation errors in the robot's motion along the desired trajectory.
For the diagnosis of large-scale local devices, the traditional centralized fault diagnosis systems are becoming incompetent to meet the requirement of real-time monitoring. This paper proposes the Distributed hierarc...
详细信息
In order to meet the requirements of high reliability and safety of acupuncture robot control system, this paper studies the redundancy strategy for acupuncture robot. The hardware design strategy, heartbeat strategy,...
详细信息
ISBN:
(纸本)9781728140773
In order to meet the requirements of high reliability and safety of acupuncture robot control system, this paper studies the redundancy strategy for acupuncture robot. The hardware design strategy, heartbeat strategy, synchronization strategy and arbitration strategy of the redundant system are discussed in detail, and the effectiveness of the proposed redundancy strategy of acupuncture robot controller is verified by OMNeT++ distributed network simulation platform.
In the previous research study it has been pointed out that employing the approximation of the induced matrix norm can be useful during design of minimum-energy perfect control law for LTI MIMO discrete-time state-spa...
详细信息
In the previous research study it has been pointed out that employing the approximation of the induced matrix norm can be useful during design of minimum-energy perfect control law for LTI MIMO discrete-time state-space plants. It has also been shown that this scenario was related to the case involving the closed-loop control matrix norm being less than unity, which was preserved by proper selection of applied nonunique inverses. This paper focuses on the systems which have been excluded from our past considerations. The methodology of minimum-energy approach for plants with norm greater than one is postulated here and some peculiarities in this matter additionally are given. This innovative method allows to predefine in a simple way a minimum-energy behavior of this intriguing control procedure.
Sensor-based condition monitoring systems are becoming an important part of modern industry. However, the data collected from sensor nodes are usually unreliable and inaccurate. It is very critical to clean the sensor...
详细信息
The paper proposes three Gain-Scheduling (GS) control design approaches dedicated to the position control of electromagnetic actuated clutch systems. The initial nonlinear mathematical model of the plant is simplified...
详细信息
The most popular method for optimizing a certain strategy based on a reward is Reinforcement Learning (RL). Lately, a big challenge for this technique are computer games such as StarCraft II which is a real-time strat...
详细信息
The most popular method for optimizing a certain strategy based on a reward is Reinforcement Learning (RL). Lately, a big challenge for this technique are computer games such as StarCraft II which is a real-time strategy game, created by Blizzard. The main idea of this game is to fight between agents and control objects on the battlefield in order to defeat the enemy. This work concerns creating an autonomous bot using reinforced learning, in particular, the Q-Learning algorithm for playing StarCraft. JamesBot consists of three parts. State Manager processes relevant information from the environment. Decision Manager consists of a table implementation of the Q-Learning algorithm, which assigns actions to states, and the epsilon-greedy strategy, which determines the behavior of the bot. In turn, Action Manager is responsible for executing commands. Testing bots involves fighting the default (simple) agent built into the game. Although JamesBot played better than the default (random) agent, it failed to gain the ability to defeat the opponent. The obtained results, however, are quite promising in terms of the possibilities of further development.
The paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. More...
详细信息
The paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification problem. We compared the parameters and performance of the automatically generated neural structure with the architectures selected manually, reported by the authors in previous papers. The obtained structure achieved comparable results to hand-designed networks, but with much fewer parameters then manually crafted architectures.
Legged motion has significant advantages over traditional locomotion techniques. Research and development on it have been constantly improving over the last couple of decades. Though there are numerous techniques in d...
详细信息
Legged motion has significant advantages over traditional locomotion techniques. Research and development on it have been constantly improving over the last couple of decades. Though there are numerous techniques in developing legged biped motion, none of them is fully satisfactory. The main aspects of legged motion are active balancing, smooth pattern generation and control. These play an important role in legged motion and there are numerous techniques developed to achieve it. The research that is shown in this project is to implement model-based design methodology in developing ZMP stability algorithm. The main area that is been concentrated in the implementation of hardware-in-loop (HIL) simulation using an xPC - target computer. The robot walking gait is generated by developing a Simulink plant model where the joint angles are tested on a virtual simulation platform.
This article briefly summarizes the theory of chaos and its applications. Firstly, we begin by describing chaos as an aperiodic bounded deterministic motion, which is sensitive to initial states and therefore unpredic...
详细信息
暂无评论