Distributed adaptive fuzzy iterative learning control of coordination problems for higher order multi-agent systems

In this paper, the adaptive fuzzy iterative learning control scheme is proposed for coordination problems of Mth order (M ≥ 2) distributed multi-agent systems. Every follower agent has a higher order integrator with unknown nonlinear dynamics and input disturbance. The dynamics of the leader are a higher order nonlinear systems and only available to a portion of the follower agents. With distributed initial state learning, the unified distributed protocols combined time-domain and iteration-domain adaptive laws guarantee that the follower agents track the leader uniformly on [0, T]. Then, the proposed algorithm extends to achieve the formation control. A numerical example and a multiple robotic system are provided to demonstrate the performance of the proposed approach.     

移动机器人的队形控制及其主动避障

在这篇论文中, 我们利用一个统一的算法框架来解决移动机器人的队形控制和主动避障问题, 使得编队中的从机器人在避开障碍物的同时, 能够与被跟踪的主机器人保持期望的相对距离或相对方位. 在现有的关于主—从跟踪编队控制的文献中, 为了实现对主机器人快速准确的跟踪, 从机器人在跟踪控制时需要主机器人在惯性坐标系下的绝对运动速度作为队形跟踪控制器的输入. 然而, 在一些环境中, 主机器人的绝对运动状态很难获得. 这里, 我们将利用主—从机器人之间的相对速度来建立机器人编队系统的运动学模型. 基于这个模型的编队控制方法将不再需要测量主机器人的绝对运动速度. 进一步地, 上述的建模和控制方法被扩展为一个移动机器人的动态避障方法, 该方法利用机器人与障碍物之间相对运动状态作为避障控制器的信息输入. 利用由三个非完整移动机器人组成的多机器人系统, 验证了所提出编队控制方法的有效性.     

Distributed adaptive flocking of robotic fish system with a leader of bounded unknown input

A distributed leader-follower flocking problem of multiple robotic fish governed by extended second-order unicycles is studied in this paper. The multi-agent system consists of only one leader with pre-appointed and bounded speeds. A distributed flocking algorithm on the basis of the combination of consensus and attractive/repulsive functions is investigated, in which adaptive strategy is adopted to compute the weight of the velocity coupling strengths. The proposed control algorithm enables followers to asymptotically track the leader’s varying velocities and approach the equilibrium distances with their neighbors. Furthermore, the arbitrarily-shaped formation flocking problem of the system can also be solved by adding the information of a desired formation topology to the potential function term. Finally, simulations are carried out to verify the effectiveness of the proposed theoretical results.     

基于二阶运动学模型的移动机器人主从跟踪系统的鲁棒控制

In this paper, we study the problem of modeling and controlling leader-follower formation of mobile robots. First, a novel kinematics model for leader-follower robot formation is formulated based on the relative motion states between the robots and the local motion of the follower robot. Using this model, the relative centripetal and Coriolis accelerations between robots are computed directly by measuring the relative and local motion sensors, and utilized to linearize the nonlinear system equations. A formation controller, consisting of a feedback linearization part and a sliding mode compensator, is designed to stabilize the overall system including the internal dynamics. The control gains are determined by solving a robustness inequality and assumed to satisfy a cooperative protocol that guarantees the stability of the zero dynamics of the formation system. The proposed controller generates the commanded acceleration for the follower robot and makes the formation control system robust to the effect of unmeasured acceleration of the leader robot. Furthermore, a robust adaptive controller is developed to deal with parametric uncertainty in the system. Simulation and experimental results have demonstrated the effectiveness of the proposed control method.     

Symmetry position/force hybrid control for cooperative object transportation using multiple humanoid robots

A symmetry position/force hybrid control framework for cooperative object transportation tasks with multiple humanoid robots is proposed in this paper. In a leader-follower type cooperation, follower robots plan their biped gaits based on the forces generated at their hands after a leader robot moves. Therefore, if the leader robot moves fast (rapidly pulls or pushes the carried object), some of the follower humanoid robots may lose their balance and fall down. The symmetry type cooperation discussed in this paper solves this problem because it enables all humanoid robots to move synchronously. The proposed framework is verified by dynamic simulations.     

电驱移动机器人多变量固定时间连续编队控制

针对扰动下电驱动非完整移动机器人固定时间编队控制问题,通过引入包含驱动器动力学的领航者-跟随者状态空间动力学模型,分两步对编队控制器进行了设计。对领航者跟随者编队运动学模型进行了多变量固定时间控制设计。在动力学层面,为实现扰动下的速度跟踪,通过辅助输入设计了一种跟随者机器人多变量超螺旋固定时间连续电压控制器。所提算法使机器人编队克服了跟随者机器人所受干扰,确保了跟随者机器人与领航者在固定时间达到期望队形,跟随者在固定时间内跟随期望速度,设计的连续控制消除了开关控制的抖振现象。通过参数设计提前给定系统收敛的固定时间,与系统初始状态无关。基于Lyapunov方法进行了系统稳定性分析。通过仿真对算法进行了验证。     

Distributed leader‐follower flocking control

This paper presents a fuzzy based leader‐follower flocking system. To maintain the distance between robots, we use a fuzzy logic controller to design a “force function” which is related to the relative distance between neighbours. The “force function” is used to control velocity of robots. To prove stability of the flocking system, we build a Hamilton function which is kinetic energy of the flocking system. Utilizing the LaSalle's invariance principle, we prove that the system is stable. Specially, we develop a flocking controller in local form. By using the local controller, the robots in the flocking system only need to know local information (relative distances and relative angles between neighbours). To evaluate performance of the flocking system, we simulate the flocking system tracking trajectories with different shapes. The local flocking algorithm is tested with three Pioneer robots. We use the SICK laser scanner to measure the relative distances and relative angles between neighbours. Copyright © 2009 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

基于二阶一致性算法的多仿生机器鱼分布式编队控制

针对动态领航者按照自身动力学模型运动, 多个跟随者机器鱼以其为编队参考点, 根据编队要求形成队形并整体跟随领航者运动的问题, 提出一种多仿生机器鱼分布式编队控制方案. 首先, 基于二阶一致性算法给出各跟随者机器鱼估计领航者位姿信息的分布式算法;其次,给出以领航者为参考点的多仿生机器鱼编队描述方法,进而各机器鱼根据编队要求以所估得的参考点信息实时确定其在编队中的期望位姿; 再次, 各跟随者机器鱼以期望速度和角速度以及所估得的领航者位姿信息为输入, 利用模糊控制器确定其速度档位和方向档位, 实现编队的形成与保持. 仿真和实验结果均表明, 所提分布式编队控制方法是有效的, 仿生机器鱼群体能够较快形成期望队形并跟随领航者游动.     

Flocking for multi-agent systems with optimally rigid topology based on information weighted Kalman consensus filter

This paper investigates the leader-follower flocking problem of multi-agent systems. The leader with input noise is estimated by a proposed continuous-time information weighted Kalman consensus filter (IWKCF) for agents. A novel distributed flocking algorithm based on the IWKCF is further presented to make agents achieve flocking to the leader. It is shown that the proposed flocking algorithm based on the continuous-time IWKCF is asymptotically stable. Applying the topology optimization scheme, the communication complexity of system topologies of multi-agent systems is effectively reduced. Finally, simulations are provided to demonstrate the effectiveness of the proposed results.     

改进遗传算法与领航跟随法的机器人编队方法

针对传统遗传算法在求解机器人路径规划问题时存在的收敛速度慢、路径不平滑问题,对其进行了改进,在适应度函数中加入了路径平滑度因素,选择操作时平滑度较好的路径更容易被选中。在种群选择时将最优个体直接复制到下一代,有效地保留了父代优良基因。在领航机器人规划路径阶段,使用改进的遗传算法为领航机器人规划出一条安全无碰撞且平滑度较好的最优路径。在跟随机器人跟随阶段,使用领航跟随法控制每一个跟随机器人使其与领航者保持特定的距离与角度,从而形成设定的队形。最后通过MATLAB软件建立栅格地图进行仿真,验证了该算法的可行性,与传统遗传算法相比,改进遗传算法收敛速度更快,且路径更加平滑。     

A new approach of formation navigation derived from multi-robots cooperative online FastSLAM

A new formation navigation approach derived from multi-robots cooperative online FastSLAM is proposed. In this approach,the leader and follower robots are defined.The posteriori estimation of the leader robot state is treated as a relative reference for all follower robots to correct their state priori estimations.The control volume of individual follower will be achieved from the results of the corrected estimation.All robots are observed as landmarks with known associations by the others and are considered in their landmarks updating.By the method,the errors of the robot posterior estimations are reduced and the formation is well kept.The simulation and physical experiment results show that the multi-robots relative localization accuracy is improved and the formation navigation control is more stable and efficient than normal leader-following strategy.The algorithm is easy in implementation.     

动态环境中的多机器人协同搬运

在多机器人协同搬运过程中,针对传统的强化学习算法仅使用数值分析却忽略了推理环节的问题,将多机器人的独立强化学习与“信念-愿望-意向”（BDI）模型相结合,使得多机器人系统拥有了逻辑推理能力,并且,采用距离最近原则将离障碍物最近的机器人作为主机器人,并指挥从机器人运动,提出随多机器人系统位置及最近障碍物位置变化的评价函数,同时将其与基于强化学习的行为权重结合运用,在多机器人通过与环境不断交互中,使行为权重逐渐趋向最佳。仿真实验表明,该方法可行,能够成功实现协同搬运过程。     

Nonsingular Terminal Sliding Mode Control of Robot Manipulators Using Fuzzy Wavelet Networks

This paper presents an adaptive nonsingular terminal sliding mode (NTSM) tracking control design for robotic systems using fuzzy wavelet networks. Compared with linear hyperplane-based sliding control, terminal sliding mode controller can provide faster convergence and higher precision control. Therefore, a terminal sliding controller combined with the fuzzy wavelet network, which can accurately approximate unknown dynamics of robotic systems by using an adaptive learning algorithm, is an attractive control approach for robots. In addition, the proposed learning algorithm can on-line tune parameters of dilation and translation of fuzzy wavelet basis functions and hidden-to-output weights. Therefore, a robust control law is used to eliminate uncertainties including the inevitable approximation errors resulted from the finite number of fuzzy wavelet basis functions. The proposed controller requires no prior knowledge about the dynamics of the robot and no off-line learning phase. Moreover, both tracking performance and stability of the closed-loop robotic system can be guaranteed by Lyapunov theory. Finally, the effectiveness of the fuzzy wavelet network-based control approach is illustrated through comparative simulations on a six-link robot manipulator     

Observer-based leader-following tracking control under both fixed and switching topologies

This paper studies the tracking problem for a class of leader-follower multi-agent systems moving on the plane using observerbased cooperative control strategies. In our set-up, only a subset of the followers can obtain some relative information on the leader. We assume that the control input of the leader is not known to any of the followers while the system matrix is broadcast to all the followers. To track such a leader, an observer-based decentralized feedback controller is designed for each follower and detailed analysis for the convergence is presented for both fixed and switching interaction topologies between agents with the method of common Lyapunov function. We can also generalize the result to the higher dimension case for fixed topology and some special system matrices of the leader for switching topology.     

基于多源信息融合的协作机器人演示编程及优化方法

为解决现有机器人装配学习过程复杂且对编程技术要求高等问题,提出一种基于前臂表面肌电信号和惯性多源信息融合的隐式交互方式来实现机器人演示编程.在通过演示学习获得演示人的装配经验的基础上,为提高对装配对象和环境变化的自适应能力,提出了一种多工深度确定性策略梯度算法（M-DDPG）来修正装配参数,在演示编程的基础上,进行强化学习确保机器人稳定执行任务.在演示编程实验中,提出一种改进的PCNN（并行卷积神经网络）,称作1维PCNN（1D-PCNN）,即通过1维的卷积与池化过程自动提取惯性信息与肌电信息特征,增强了手势识别的泛化性和准确率;在演示再现实验中,采用高斯混合模型（GMM）对演示数据进行统计编码,利用高斯混合回归（GMR）方法实现机器人轨迹动作再现,消除噪声点.最后,基于Primesense Carmine摄像机采用帧差法与多特征图核相关滤波算法（MKCF）的融合跟踪算法分别获取X轴与Y轴方向的环境变化,采用2个相同的网络结构并行进行连续过程的深度强化学习.在轴孔相对位置变化的情况下,机械臂能根据强化学习得到的泛化策略模型自动对机械臂末端位置进行调整,实现轴孔装配的演示学习.     

Robust fuzzy tracking control for robotic manipulators

In this paper, a stable adaptive fuzzy-based tracking control is developed for robot systems with parameter uncertainties and external disturbance. First, a fuzzy logic system is introduced to approximate the unknown robotic dynamics by using adaptive algorithm. Next, the effect of system uncertainties and external disturbance is removed by employing an integral sliding mode control algorithm. Consequently, a hybrid fuzzy adaptive robust controller is developed such that the resulting closed-loop robot system is stable and the trajectory tracking performance is guaranteed. The proposed controller is appropriate for the robust tracking of robotic systems with system uncertainties. The validity of the control scheme is shown by computer simulation of a two-link robotic manipulator.     

深度强化学习中稀疏奖励问题研究综述

强化学习作为机器学习的重要分支,是在与环境交互中寻找最优策略的一类方法。强化学习近年来与深度学习进行了广泛结合,形成了深度强化学习的研究领域。作为一种崭新的机器学习方法,深度强化学习同时具有感知复杂输入和求解最优策略的能力,可以应用于机器人控制等复杂决策问题。稀疏奖励问题是深度强化学习在解决任务中面临的核心问题,在实际应用中广泛存在。解决稀疏奖励问题有利于提升样本的利用效率,提高最优策略的水平,推动深度强化学习在实际任务中的广泛应用。文中首先对深度强化学习的核心算法进行阐述;然后介绍稀疏奖励问题的5种解决方案,包括奖励设计与学习、经验回放机制、探索与利用、多目标学习和辅助任务等;最后对相关研究工作进行总结和展望。     

Observer-Based Adaptive Controller Design of Flexible Manipulators Using Time-Delay Neuro-Fuzzy Networks

In this paper, a dynamical time-delay neuro-fuzzy controller is proposed for the adaptive control of a flexible manipulator. It is assumed that the robotic manipulator has only joint angle position measurements. A linear observer is used to estimate the robot joint angle velocity. For a perfect tracking control of the robot, the output redefinition approach is used in the adaptive controller design using time-delay neuro-fuzzy networks. The time-delay neuro-fuzzy networks with the rule representation of the TSK type fuzzy system have better learning ability for complex dynamics as compared with existing neural networks. The novel control structure and learning algorithm are given, and a simulation for the trajectory tracking of a flexible manipulator illustrates the control performance of the proposed control approach.     

Conflict-Aware Safe Reinforcement Learning: A Meta-Cognitive Learning Framework

In this paper,a data-driven conflict-aware safe reinforcement learning(CAS-RL)algorithm is presented for control of autonomous systems.Existing safe RL results with predefined performance functions and safe sets can only provide safety and performance guarantees for a single environment or circumstance.By contrast,the presented CAS-RL algorithm provides safety and performance guarantees across a variety of circumstances that the system might encounter.This is achieved by utilizing a bilevel learning control architecture:A higher metacognitive layer leverages a data-driven receding-horizon attentional controller(RHAC)to adapt relative attention to different system’s safety and performance requirements,and,a lower-layer RL controller designs control actuation signals for the system.The presented RHAC makes its meta decisions based on the reaction curve of the lower-layer RL controller using a metamodel or knowledge.More specifically,it leverages a prediction meta-model(PMM)which spans the space of all future meta trajectories using a given finite number of past meta trajectories.RHAC will adapt the system’s aspiration towards performance metrics(e.g.,performance weights)as well as safety boundaries to resolve conflicts that arise as mission scenarios develop.This will guarantee safety and feasibility(i.e.,performance boundness)of the lower-layer RL-based control solution.It is shown that the interplay between the RHAC and the lower-layer RL controller is a bilevel optimization problem for which the leader(RHAC)operates at a lower rate than the follower(RL-based controller)and its solution guarantees feasibility and safety of the control solution.The effectiveness of the proposed framework is verified through a simulation example.     

Stable adaptive controller design of robotic manipulators via neuro‐fuzzy dynamic inversion

In this paper, a stable adaptive control approach is developed for the trajectory tracking of a robotic manipulator via neuro‐fuzzy (NF) dynamic inversion, an inverse model constructed by the dynamic neuro‐fuzzy (DNF) model with desired dynamics. The robot neuro‐fuzzy model is initially built in the Takagi‐Sugeno (TS) fuzzy framework with both structure and parameters identified through input/output (I/O) data from the robot control process, and then employed to dynamically approximate the whole robot dynamics rather than its nonlinear components as is done by static neural networks (NNs) through parameter learning algorithm. Since the NF dynamic inversion comprises a cluster of reference trajectories connecting the initial state to the desired state of the robot, the dynamic performance in the initial control stage of robot trajectory tracking can be guaranteed by choosing the optimum reference trajectory. Furthermore, the assumption that the robot states should be on a compact set can be excluded by NF dynamic inversion design. The system stability and the convergence of tracking errors are guaranteed by Lyapunov stability theory, and the learning algorithm for the DNF system is obtained thereby. Finally, the viability and effectiveness of the proposed control approach are illustrated through comparing with the dynamic NN (DNN) based control approach. © 2005 Wiley Periodicals, Inc.