Adaptive task-space regulation of rigid-link flexible-joint robots with uncertain kinematics

In this paper, an adaptive control scheme is proposed for the regulation problem of rigid-link flexible-joint (RLFJ) robots with uncertain kinematics. Existing research works in literature on RLFJ robot control assume exact knowledge of the kinematics of robot, and no result that can deal with kinematics uncertainty in RLFJ robot has been proposed so far. This paper presents the first study addressing this problem. The adaptive control scheme proposed can deal with the kinematics uncertainty and uncertainties in both link and actuator dynamics of the RLFJ robot system. A nonlinear observer is designed to avoid the use of acceleration due to the fourth-order overall dynamics. Asymptotic stability of the closed-loop system is shown and sufficient conditions are presented to guarantee the stability. Simulation results are provided to illustrate the effectiveness of the proposed control method.     

Impact dynamics of flexible-joint robots

In this paper the dynamic analysis of a flexible-joint robot colliding with its environments is presented. The system considered here is an n-rigidlink manipulator driven by n DC-motors through n revolute flexible-joints. The flexibility of each flexible joint is modelled as a linearly elastic torsional spring. 2n generalized coordinates are introduced to identify the configuration of the robot. The concept of impulse potential energy is introduced, and the generalized impulse-momentum equations along with the equation involving coefficient of restitution are used to establish the complete mathematic model for dealing with the case of a flexible-joint manipulator colliding with its environments (such as the ground, another manipulator, and so on). Solving for this mathematic model, one can obtain the jump discontinuities in system generalized velocities and the impulses at the impact points explicitly. To validate the algorithm presented in this paper, the dynamic simulation of a robot involving impact with its environments is given as an example.     

Improving performance of robots using human-inspired approaches: a survey

Realizing high performance of ordinary robots is one of the core problems in robotic research. Improving the performance of ordinary robots usually relies on the collaborative development of multiple research fields, resulting in high costs and difficulty to complete some high-precision tasks. As a comparison,humans can realize extraordinary overall performance under the condition of limited computational-energy consumption and low absolute precision in sensing and controlling each body unit. Th...     

Trajectory tracking control of flexible-joint robots

Inverse dynamics control of flexible-joint robots is addressed. It is shown that, in a flexible-joint robot, the acceleration level inverse dynamic equations are singular because the control torques do not have an instantaneous effect on the end-effector accelerations due to the elastic media. Implicit numerical integration methods that account for the higher order derivative information are utilized for solving the singular set of differential equations. The trajectory tracking control law presented linearizes and decouples the system and yields an asymptotically stable fourth order error dynamics for each end-effector degree of freedom. A 3R spatial robot with all joints flexible is simulated to illustrate the performance of the proposed algorithm.     

Design of global tracking controllers for flexible-joint robots

An approach to design control laws for trajectory tracking of robots having flexible joints is presented. An application to the adaptive control is also given with reference to a single-link robot with one revolute elastic joint whose parameters are unknown.     

Position and force tracking control of rigid-link electrically-driven robots

This paper introduces a framework for the design of tracking controllers for rigid-link electrically-driven (RLED) robot manipulators operating under constrained and unconstrained conditions. We present an intuitive nonlinear control strategy that can easily be reformulated for robots performing high precision tasks. The main emphasis is placed on the development of controllers that incorporate both motion in freespace and under constrained conditions. Another novelty is the combined treatment of force control and compensation for actuator dynamics. Based on models of the robot dynamics and environmental constraints, a reduced order dynamic model is obtained for the mechanical subsystem with respect to a set of constraint variables. A design procedure for tracking controllers is then formulated for the reduced order manipulator dynamics and the DC actuator dynamics. This paper concentrates on the theoretical aspects of the problem and, hence, is based on exact knowledge of the entire system. However, we have illustrated recently in [1] that this assumption can be generously relaxed in the design of a robust controller following a similar procedure as discussed in this paper.     

Fractional-order dynamics and adaptive dynamic surface control of flexible-joint robots

This paper establishes a novel fractional-order model for n-links flexible-joint (FJ) robots and proposes an adaptive dynamic surface control (DSC) scheme to address the tracking control problem. The fractional-order FJ model is built by fractional-order viscoelastic dynamics model to have a more concise form. An adaptive DSC strategy is proposed to address the tracking control problem based on backstepping method. By selecting the appropriate orders for fractional filters, the controller could solve the “explosion of complexity” problem. The unknown nonlinearities of FJ robot systems are approximated by Radial basis function (RBF) neural networks (NNs). Based on the Lyapunov stability theory, the bounds of all signals in the closed-loop system are achieved. The simulation results confirm the effectiveness of the presented control scheme.     

Robust tracking control for a class of electrically driven flexible-joint robots without velocity measurements

This article addresses the motion tracking control for a class of flexible-joint robotic manipulators actuated by brushed direct current motors. This class of electrically driven flexible-joint robots is perturbed by time-varying parametric uncertainties and external disturbances. A novel observer-based robust dynamic feedback tracking controller without velocity measurements will be developed such that the resulting closed-loop system is locally stable, all the states and signals are bounded and the trajectory tracking errors can be made as small as possible. Only the measurements of link position and armature current are required for feedback and so the number of sensors in the practical implementation of the developed control scheme can be greatly reduced. The observer structure is of reduced order in the sense that the observer is constructed only to estimate the velocity signals and whose dimension is half of the dimension of flexible-joint robots. Especially, for the set-point regulation problem, the developed controller is simplified to a linear time-invariant controller. Consequently, the robust tracking control scheme developed in this study can be extended to handle a broader class of uncertain electrically driven flexible-joint robots and the developed robust control schemes possess the properties of computational simplicity and easy implementation. Finally, simulation results are presented to demonstrate the effectiveness of the proposed control algorithms.     

Robust tracking control for a class of flexible-joint time-delay robots using only position measurements

In this paper, robust tracking control is investigated for a class of uncertain flexible-joint robots with time delays and time-varying perturbations. By employing the Lyapunov--Krasovskii functional technique and backstepping design technique, a novel robust tracking control scheme using only position measurements is developed such that all the states and signals of the closed-loop flexible-joint time-delay robot system remain bounded and the tracking error can asymptotically converge to a small neighbourhood around the origin. By appropriately choosing the weighting gains in the Lyapunov–Krasovskii functionals, the circular phenomenon in the controller design is overcome. Due to suitably designing the velocity observer and the virtual control input, the link-side dynamics does not need to be incorporated into the actuator-side tracking error dynamics, and so the complexity in the backstepping design is avoided. Consequently, we can easily construct the Lyapunov–Krasovskii functionals, and, in turn, the robust tracking control scheme developed here is a linear time-varying controller and can be simply implemented. Simulation examples are provided to verify the effectiveness of the proposed control algorithm.     

Distributed adaptive containment control of networked flexible-joint robots using neural networks

This study presents a distributed adaptive containment control approach for a group of uncertain flexible-joint (FJ) robots with multiple dynamic leaders under a directed communication graph. The leaders are neighbors of only a subset of the followers. The derivatives of the leaders are unknown, namely, the position information of the leaders is only available for implementing the proposed control approach. The local adaptive dynamic surface containment controller for each follower is designed using only neighbors’ information to guarantee that all followers converge to the dynamic convex hull spanned by the dynamic leaders. The function approximation technique using neural networks is employed to estimate the model uncertainties of each follower. It is proved that the containment control errors converge to an adjustable neighborhood of the origin regardless of model uncertainties and the lack of shared communication information. Simulation results for FJ manipulators are provided to illustrate the effectiveness of the proposed adaptive containment control scheme.     

Control of truck-trailer mobile robots: a survey

Mobile robots with trailers and its control is one of the most challenging problems in service robotics. Since, these kinds of robots can accomplish the given task in a faster and cheaper way than an individual robot, they find applications in many areas. However, the backward movement of a truck-trailer mobile robot is more complex as the complete system is highly non-linear and unstable. The practical advantages of this system in the transportation industry have led to significant research in this area. Various studies have been conducted in this area for exploring more on the subject of non-linear control. This paper presents a survey on the various control strategies developed in the backward motion of mobile robot with trailers. The existing studies in this field are analyzed to identify unsolved problems.     

Text-to-picture tools,systems, and approaches: a survey

Multimedia Tools and Applications - Text-to-picture systems attempt to facilitate high-level, user-friendly communication between humans and computers while promoting understanding of natural...     

Adaptive dynamic surface control of flexible-joint robots using self-recurrent wavelet neural networks.

A new method for the robust control of flexible-joint (FJ) robots with model uncertainties in both robot dynamics and actuator dynamics is proposed. The proposed control system is a combination of the adaptive dynamic surface control (DSC) technique and the self-recurrent wavelet neural network (SRWNN). The adaptive DSC technique provides the ability to overcome the "explosion of complexity" problem in backstepping controllers. The SRWNNs are used to observe the arbitrary model uncertainties of FJ robots, and all their weights are trained online. From the Lyapunov stability analysis, their adaptation laws are induced, and the uniformly ultimately boundedness of all signals in a closed-loop adaptive system is proved. Finally, simulation results for a three-link FJ robot are utilized to validate the good position tracking performance and robustness against payload uncertainties and external disturbances of the proposed control system.     

Adaptive Jacobian tracking control of rigid-link electrically driven robots based on visual task-space information

This paper studies stable adaptive tracking control of rigid-link electrically driven robot manipulators in the presence of uncertainties in kinematics, manipulator dynamics, and actuator dynamics. A new task-space control method using visual task-space information is proposed to overcome the uncertainties adaptively. Accelerations measurements are avoided in the control voltage inputs by constructing observers to specify desired armature currents. Simulation results illustrate the performance of the proposed control method.     

Creativity: a survey of AI approaches

In this paper we critically survey the AI programs that have been developed to exhibit some aspect of creative behaviour. We describe five necessary characteristics of models of creativity, and we apply these characteristics to help assess the programs surveyed. These characteristic features also provide a basis for a new theory of creative behavior: an emergent memory model. The survey is concluded with an assessment of an implementation of this latest theory.

相似文献   

具有参数不确定性的轮式移动机器人自适应backstepping控制

针对参数不确定的轮式移动机器人的轨迹跟踪问题,设计自适应跟踪控制器.基于移动机器人的动力学模型,采用backstepping积分方法,通过逐步递推选择适当的Lyapunov函数,设计基于状态反馈的自适应控制器,并进行了相应的稳定性分析.与传统PID控制进行仿真对比,结果表明提出的自适应控制策略能较好地补偿系统参数摄动的影响,提高了移动机器人的轨迹跟踪性能和鲁棒性.     

A partial state feedback controller for tajectory tracking of rigid-link fiexible-joint robot using an observed backstepping approach

This article presents a partial state feedback controller for a rigid-link flexible-joint (RLFJ) robot using an observed integrator backstepping approach. The robot controller requires only link position and actuator position measurements, and eliminates the need for measuring link velocity and actuator velocity. The controller uses two exact knowledge, second-order nonlinear observers to estimate the link and actuator velocities. The overall control system achieves a semiglobal exponential stability result for the link position and velocity tracking errors as well as the velocity observation errors. A stability proof and simulation results for the proposed partial state feedback controller are included in the article. © 1995 John Wiley & Sons, Inc.     

Emotion in reinforcement learning agents and robots: a survey

This article provides the first survey of computational models of emotion in reinforcement learning (RL) agents. The survey focuses on agent/robot emotions, and mostly ignores human user emotions. Emotions are recognized as functional in decision-making by influencing motivation and action selection. Therefore, computational emotion models are usually grounded in the agent’s decision making architecture, of which RL is an important subclass. Studying emotions in RL-based agents is useful for three research fields. For machine learning (ML) researchers, emotion models may improve learning efficiency. For the interactive ML and human–robot interaction community, emotions can communicate state and enhance user investment. Lastly, it allows affective modelling researchers to investigate their emotion theories in a successful AI agent class. This survey provides background on emotion theory and RL. It systematically addresses (1) from what underlying dimensions (e.g. homeostasis, appraisal) emotions can be derived and how these can be modelled in RL-agents, (2) what types of emotions have been derived from these dimensions, and (3) how these emotions may either influence the learning efficiency of the agent or be useful as social signals. We also systematically compare evaluation criteria, and draw connections to important RL sub-domains like (intrinsic) motivation and model-based RL. In short, this survey provides both a practical overview for engineers wanting to implement emotions in their RL agents, and identifies challenges and directions for future emotion-RL research.     

机器人增量学习研究综述

机器人的应用场景正在不断更新换代,数据量也在日益增长.传统的机器学习方法难以适应动态的环境,而增量学习技术能够模拟人类的学习过程,使机器人能利用旧知识来加快新任务的学习,在不遗忘旧技能的前提下学习新的技能.目前对于机器人增量学习的相关研究仍然较少,对此,主要介绍机器人增量学习研究进展.首先,对增量学习进行简介;其次,从参数和模型的角度出发,将当前机器人增量学习主流方法分为变参数方法、变模型方法、混合方法3类,分别对每一类进行论述,并给出相应的增量学习技术在机器人领域中的应用实例;然后,对机器人增量学习中常用的数据集和评价指标进行介绍;最后,对增量学习未来的发展趋势进行展望.