在未知环境中基于模糊逻辑的移动机器人行为控制

本文介绍了一种在未知环境中基于模糊逻辑的移动机器人行为控制方法．传统的行为控制方法存在两个弱点：①行为不易描述;②多个行为之间的冲突和竞争难以协调．这篇文章的主要思想是将模糊逻辑控制与行为控制相结合致使这两个问题得到有效的解决．仿真实验结果表明：所提的方法通过多个行为如避障边沿行走和目标导向的融合,能够有效地对机器人在复杂和未知环境中导航．另外,该方法还适用于多传感器的融合与集成．     

基于红外传感皮肤的多关节机器人自主运动方法研究

本文研究了障碍环境下多关节机器人自主实时避碰运动理论、技术与方法. 研制的新型红外传感皮肤, 可以为多关节机器人提供所需要的周围环境信息. 针对非结构化环境下的多关节机器人实时避障问题, 提出了一种未知环境下的机器人模糊路径实时规划新方法. 实验结果表明: 基于研制的红外传感皮肤和模糊运动规划算法, 多关节机器人可以在未知或时变环境下自主工作.     

满足复杂要求的机器人最优巡回控制系统设计与实现

本文结合线性时序逻辑理论与模糊控制方法,设计并实现了一种满足复杂任务需求的移动机器人巡回控制系统,它既能够针对复杂时序任务进行路径规划,又能够对机器人进行模糊控制实现路径跟踪.首先,基于线性时序逻辑理论,确定能够满足复杂巡回任务需求的全局最优路径.接着,根据所获得的最优路径,采用模糊控制方法设计轨迹跟踪控制器,使其通过实时位姿反馈对机器人进行路径跟踪控制.仿真结果验证了移动机器人巡回控制系统的有效性.最后,基于E-Puck移动机器人构建了能够满足复杂任务需求的移动机器人巡回控制实验系统.基于所提出的最优巡回路径规划算法和模糊控制器设计方法,通过图像处理、数据通信、算法加载等软件模块的实现完成了满足复杂任务需求的移动机器人巡回控制.     

关节式移动机器人在斜面上基于模糊逻辑的运动控制

本文针对关节式移动机器人在斜面上运动时稳定性和安全性的要求对其进行动力学分析 ,利用传感器融合技术对机器人进行局部定位 ,提出了它的基于模糊逻辑的控制策略 .实验证明这种方法是可行的和有效的     

Obstacle Avoidance Using the Human Operator Experience for a Mobile Robot

In this paper, a neuro-fuzzy technique has been used to steer a mobile robot. The neuro-fuzzy approach provides a good way to capture the information given by a human. In this manner, it has been possible to obtain the rules and membership functions automatically whereas a fuzzy approach needs to make a prior definition of the rules and membership functions. In order to apply the neuro-fuzzy strategy, two mobile robots have been developed. However, in this paper only the smallest one has been considered. Similar results are obtained for the biggest one. The results of the approach are satisfactory, avoiding the obstacles when the mobile robot is steered to the target.     

An Intelligent Controller Improving the Drive System of a Head Platform

In this paper a new approach for steering a binocular head is presented. This approach is based on extracting the expert’s knowledge in order to improve the behaviour of the classical control strategies. This is carried out without inserting new elements in the system. Neuro–Fuzzy techniques have been chosen in order to reach this target. As a result a more friendly robotic system is achieved.     

Path planning for a manipulator with constraints on orientation

This paper discusses the work undertaken at the U.K. National Advanced Robotics Research Centre in the area of path planning. Experiments have been undertaken with the Best First Planner (BFP) and Random Path Planner (RPP) algorithms developed at Stanford University by Barraquand and Latombe. These look particularly suitable for solving a wide range of motion planning problems and for providing the basic mechanism for path planning in an advanced robotic architecture. From this basic mechanism higher level functional primitives have been developed to enable paths to be planned with a pre-defined orientation of the end effector at the goal location or maintaining an orientation throughout the whole path. These functions are achieved through placing additional constraints on the search through configuration space and modifying the workspace potential.     

On Intelligent Robot Motion Planning via Learning

Automatic motion planning is one of the basic modules that are needed to increase robot intelligence and usability. Unfortunately, the inherent complexity of motion planning has rendered traditional search algorithms incapable of solving every problem in real time. To circumvent this difficulty, we explore the alternative of allowing human operators to participate in the problem solving process. By having the human operator teach during difficult motion planning episodes, the robot should be able to learn and improve its own motion planning capability and gradually reduce its reliance on the human operator. In this paper, we present such a learning framework in which both human and robot can cooperate to achieve real-time automatic motion planning. To enable a deeper understanding of the framework in terms of performance, we present it as a simple learning algorithm and provide theoretical analysis of its behavior. In particular, we characterize the situations in which learning is useful, and provide quantitative bounds to predict the necessary training time and the maximum achievable speedup in planning time.     

Motion Planning for Drift-Free Nonholonomic Systems under a Discrete Levels Control Constraint

We solve the Motion Planning Problem for nonholonomic systems without drift when their inputs are restricted to take values in a prescribed discrete levels set of finite cardinality. In particular, we propose algorithms that produce the proper sequence of input levels as well as the corresponding switching times providing exact steering when the system is nilpotent or feedback nilpotentizable. For a general drift-free system, i.e. for a drift-free system that is neither nilpotent nor feedback nilpotentizable another algorithm provides approximate steering within a permissible error. Finally, we apply the proposed algorithms in motion planning for a car-like mobile robot.     

Real-World Robotics: Learning to Plan for Robust Execution

In executing classical plans in the real world, small discrepancies between a planner's internal representations and the real world are unavoidable. These can conspire to cause real-world failures even though the planner is sound and, therefore, proves that a sequence of actions achieves the goal. Permissive planning, a machine learning extension to classical planning, is one response to this difficulty. This paper describes the permissive planning approach and presents GRASPER, a permissive planning robotic system that learns to robustly pick up novel objects.     

A Simple Robust Sliding-Mode Fuzzy-Logic Controller of the Diagonal Type

This paper derives and analyzes a new robust fuzzy-logic sliding-mode controller of the diagonal type, which does not need the prior design of the rule base. The basic objective of the controller is to keep the system on the sliding surface so as to ensure the asympotic stability of the closed-loop system. The control law consists of two rules: (i) IF sign(e(t)(t)) < 0 THEN maintain the control action, and (ii) IF sign(e(t)(t)) > 0 THEN change the control action, where e(t) = x(t) – x^d(t) is the system state error, and the control action can be either an increase or decrease of the control signal, which is realized through the use of fuzzy rules. The proposed controller, which does not need the prior knowledge of the system model and the prior design of the membership functions" shape, was tested, by simulation, on linear and nonlinear systems. The performance was in all cases excellent (very fast trajectory tracking, no chattering) . Of course, as in traditional control, there was a trade-off between the rise-time and the overshoot of the system response.     

无线传感器网络的模糊功率控制技术

无线传感器网络节点通过撒播造成节点分布不均,分簇后导致分簇疏密不均,影响了网络性能,需要对簇头进行功率控制使网络结构更加优化.但这是一个难以确定其准确数学模型的过程,因此提出了一种采用模糊技术调整簇头功率以改变拓扑结构的方案.最后进行了仿真,实验结果证明通过分簇大小控制以后,网络的生存时间和通信量都有增加.     

Hybrid Controller for Adaptive Link Control of Industrial Robots

This paper presents a new adaptation mechanism for a cascaded positioncontroller. The cascaded position controller consists of P.I.D. controllersthe parameters of which are changed by a fuzzy logic adaptation mechanism.The proposed fuzzy logic adaptation mechanism is tested using thesix-degree-of-freedom-robot RV 15, manufactured by Reis Robotics. Using thefuzzy logic adaptation mechanism, the cartesian position error of the toolcenter point can be significantly reduced by 50 %. Anotherenhancement of the dynamic behaviour, which can be achieved by the fuzzylogic adaptation mechanism, is to lessen the influence of different loads onthe cartesian position error.