Autonomous driving at the handling limit using residual reinforcement learning

While driving a vehicle safely at its handling limit is essential in autonomous vehicles in Level 5 autonomy, it is a very challenging task for current conventional methods. Therefore, this study proposes a novel controller of trajectory planning and motion control for autonomous driving through manifold corners at the handling limit to improve the speed and shorten the lap time of the vehicle. The proposed controller innovatively combines the advantages of conventional model-based control algorithm, model-free reinforcement learning algorithm, and prior expert knowledge, to improve the training efficiency for autonomous driving in extreme conditions. The reward shaping of this algorithm refers to the procedure and experience of race training of professional drivers in real time. After training on track maps that exhibit different levels of difficulty, the proposed controller implemented a superior strategy compared to the original reference trajectory, and can to other tougher maps based on the basic driving knowledge learned from the simpler map, which verifies its superiority and extensibility. We believe this technology can be further applied to daily life to expand the application scenarios and maneuvering envelopes of autonomous vehicles.     

基于改进蚁群优化算法的自动驾驶多车协同运动规划

当前面向多辆自动驾驶汽车的协同运动规划方法能有效保证运行车辆与障碍物及其他车辆之间避免发生碰撞并保持安全距离,但车辆间的在线协同与规划能力仍有待提升。为实现多辆自动驾驶汽车在运动过程中的协同控制,提出一种基于改进蚁群优化算法的多车在线协同规划方法。以空间协同与轨迹代价为优化目标,构造多目标优化函数,确保了多车行驶过程中的协同安全性与轨迹平滑性。将多目标优化函数引入蚁群优化算法的信息素更新过程中,根据自动驾驶车辆数量产生多个种群,使得种群之间相互独立的同时为每辆自动驾驶汽车规划可行路线。最终对蚁群优化算法中的挥发因子进行自适应调整,提升了算法全局搜索能力及收敛速度。实验结果表明,该方法能使多辆自动驾驶汽车在运动过程中保持协同控制并规划出无碰撞路线,相比于基于人工势场和模型预测的协同驾驶方法在复杂道路场景下车辆间的协同效果更好且适应性更强。     

An Optimal Control Strategy for Multi-UAVs Target Tracking and Cooperative Competition

An optimal control strategy of winner-take-all (WTA) model is proposed for target tracking and cooperative competition of multi-UAVs (unmanned aerial vehicles). In this model, firstly, based on the artificial potential field method, the artificial potential field function is improved and the fuzzy control decision is designed to realize the trajectory tracking of dynamic targets. Secondly, according to the finite-time convergence high-order differentiator, a double closed-loop UAV speed tracking the controller is designed to realize the speed control and tracking of the target tracking trajectory. Numerical simulation results show that the designed speed tracking controller has the advantages of fast tracking, high precision, strong stability and avoiding chattering. Finally, a cooperative competition scheme of multiple UAVs based on WTA is designed to find the minimum control energy from multiple UAVs and realize the optimal control strategy. Theoretical analysis and numerical simulation results show that the model has the fast convergence, high control accuracy, strong stability and good robustness.      

基于Sigmoid函数的机器人鲁棒滑模跟踪控制系统设计

为了保证机器人能够在保持稳定的情况下,按照规划轨迹执行工作任务,从硬件和软件两个方面,设计了基于Sigmoid函数的机器人鲁棒滑模跟踪控制系统。装设机器人传感器与状态观测器,改装机器人鲁棒滑模跟踪控制器,完成系统硬件设计;综合机器人结构、运动机理和动力机制3个方面,构建机器人数学模型;根据状态数据采集结果与规划轨迹之间的偏差,计算机器人跟踪控制量;依据滑模运动与切换方程,利用Sigmoid函数生成机器人鲁棒滑模控制律,将生成控制指令作用在机器人执行元件上,实现系统的鲁棒滑模跟踪控制功能;在系统测试与分析中,所设计控制系统的平均位置跟踪控制误差为0.93 mm,与设定轨迹目标基本重合,机器人姿态角跟踪控制误差为0.06 mm,具有较好的鲁棒滑模跟踪控制效果,能够有效提高机器人鲁棒滑模跟踪控制精度。     

带有激励机制的车联网合作下载信任管理方案

由于高速公路上行驶的车辆间未预先建立信任关系，车辆相互进行合作下载服务时，存在信任危机及安全隐患，严重影响合作下载的发展。为实现可信任的安全合作下载服务，提出基于SORT算法的信任管理方案，通过服务信任值选择合适的车辆进行合作，设计激励机制和公平交易协议保证合作下载的积极性和公平性，应用区块链技术对车辆的身份隐私以及数据信息进行存储和保护。分析结果表明，该方案能够使用户选择可信任的车辆进行安全的合作下载服务，促进车辆用户下载效率的提高。     

Adaptive Task-Space Control of Flexible-Joint Manipulators

This paper considers the motion control and compliance control problemsfor uncertain rigid-link, flexible-joint manipulators, and presents newadaptive task-space controllers as solutions to these problems. The motioncontrol strategy is simple and computationally efficient, requires littleinformation concerning either the manipulator or actuator/transmissionmodels, and ensures uniform boundedness of all signals and arbitrarilyaccurate task-space trajectory tracking. The proposed compliant motioncontrollers include an adaptive impedance control scheme, which isappropriate for tasks in which the dynamic character of theend-effector/environment interaction must be controlled, and an adaptiveposition/force controller, which is useful for those applications thatrequire independent control of end-effector position and contact force. Thecompliance control strategies retain the simplicity and model independenceof the trajectory tracking scheme upon which they are based, and are shownto ensure uniform boundedness of all signals and arbitrarily accuraterealization of the given compliance control objectives. The capabilities ofthe proposed control strategies are illustrated through computer simulationswith a robot manipulator possessing very flexible joints.     

Integrated Guidance and Feedback Control of Underactuated Robotics System in SE(3)

An integrated guidance and feedback control scheme for steering an underactuated vehicle through desired waypoints in three-dimensional space, is developed here. The underactuated vehicle is modeled as a rigid body with four control inputs. These control inputs actuate the three degrees of freedom of rotational motion and one degree of freedom of translational motion in a vehicle body-fixed coordinate frame. This actuation model is appropriate for a wide range of underactuated vehicles including spacecraft with internal attitude actuators, vertical take-off and landing (VTOL) aircraft, fixed-wing multirotor unmanned aerial vehicles (UAVs), maneuverable robotic vehicles, etc. The guidance problem is developed on the special Euclidean group of rigid body motions, SE(3), in the framework ofgeometric mechanics, which represents the vehicle dynamics globally on this configuration manifold. The integrated guidance and control algorithm selects the desired trajectory for the translational motion that passes through the given waypoints, and the desired trajectory for the attitude based on the desired thrust direction to achieve the translational motion trajectory. A feedback control law is then obtained to steer the underactuated vehicle towards the desired trajectories in translation and rotation. This integrated guidance and control scheme takes into account known bounds on control inputs and generates a trajectory that is continuous and at least twice differentiable, which can be implemented with continuous and bounded control inputs. The integrated guidance and feedback control scheme is applied to an underactuated quadcopter UAV to autonomously generate a trajectory through a series of given waypoints in SE(3) and track the desired trajectory in finite time. The overall stability analysis of the feedback system is addressed. Discrete time models for the dynamics and control schemes of the UAV are obtained in the form of Lie group variational integrators using the discrete Lagrange-d’Alembert principle. Almost global asymptotic stability of the feedback system over its state space is shown analytically and verified through numerical simulations.     

V2X环境下基于MPC算法的弯道区域CACC车队轨迹跟踪控制策略

针对CACC(cooperative adaptive cruise control)车队在弯道行驶的安全性和稳定性问题,提出一种V2X(vehicle to everything)环境下基于MPC(model predictive control)算法的弯道区域CACC车队行驶轨迹跟踪策略.首先,分析CACC车队在弯道区域的行驶工况以及纵向平衡问题,并基于牛顿第二定律构建车辆在弯道行驶的车辆动力学模型;其次,CACC车队基于V2X技术实现车车之间状态信息的实时交互,并以基于车辆运动学的MPC算法为基础,引入可变间距的车队安全距离控制模型,提出一种适用于弯道区域的轨迹跟踪模型;最后,通过二次规划进行模型求解.实验分析结果表明:V2X环境下的CACC车队在弯道行驶过程中面对不同的行驶工况能够不同程度地保证车车之间的安全性、稳定性以及驾乘人员的舒适性,有效验证了所提V2X环境下基于MPC算法的弯道区域CACC车队轨迹跟踪策略的可行性.     

Semi‐decentralized nonlinear cooperative control strategies for a network of heterogeneous autonomous underwater vehicles

In this paper, we develop nonlinear distributed or semi‐decentralized cooperative control schemes for a team of heterogeneous autonomous underwater vehicles (AUVs). The objective is to have the network of AUVs follow a desired trajectory, while the agents maintain a desired formation when there is a virtual leader whose position information is only available and known to a very small subset of the agents. The virtual leader does not receive any feedback and information from the other agents and the agents only communicate with their nearest neighboring agents. It is assumed that the model parameters associated with each vehicle/agent is different, although the order of the agents is the same. The developed and proposed nonlinear distributed cooperative control schemes are based on the dynamic surface control methodology for a network of heterogeneous autonomous vehicles with uncertainties. The development and investigation of the dynamic surface control methodology for a team of cooperative heterogenous multi‐agent nonlinear systems is accomplished for the first time in the literature. Simulation results corresponding to a team of six AUVs are provided to demonstrate and illustrate the advantages and superiority of our proposed cooperative control strategies as compared to the methods that are available in the literature. Copyright © 2016 John Wiley & Sons, Ltd.     

基于微分平坦与MPC的智能车换道控制算法

为了提高智能车换道的安全性,提出了一种基于微分平坦理论与模型预测控制(MPC)算法相结合的智能车换道轨迹规划与跟踪算法。该算法利用约束求解得到基于sigmoid函数的优化路径;将其与多项式参数化时间函数作为平坦输出,利用微分平坦理论构造一个非线性性能指标函数并对其进行优化求解完成车速规划;从而实现对智能车辆路径-速度分解式的轨迹规划。利用动力学模型预测控制算法线上控制的优点,对智能车的车轮转向进行实时控制,使得车辆按照规划好的轨迹行驶完成换道。通过CarSim与MATLAB/Simulink的联合仿真,将提出的轨迹规划算法应用于车辆系统仿真软件中进行验证,结果表明该算法能够实现对智能车进行轨迹规划和跟踪控制,使其安全高效地换至目标车道。     

复杂环境下多无人机协作式地面移动目标跟踪

针对多无人机(UAV)协同地面移动目标跟踪问题展开研究.提出一种基于主动感知的问题求解框架,建立多UAV协同目标跟踪问题模型;在此基础上,采用分布式无色信息滤波实现目标状态融合估计与预测;然后,基于预测目标状态,结合滚动时域控制与遗传算法设计一种多UAV在线协同航迹规划算法.仿真结果表明:结合预测目标状态在线优化UAV...     

无人仓多搬运机器人协同作业轨迹自动控制研究

由于无人仓多搬运机器人协同作业线路较为复杂,导致协同作业轨迹控制难度增加,为了保证多搬运机器人能够按照规划路线执行搬运作业,提出了无人仓多搬运机器人协同作业轨迹自动控制方法;采用栅格图建模法,结合无人仓内货架的实际分布情况,建立无人仓环境场景;从组成结构、运动学以及动力学3个方面,构建搬运机器人的数学模型;遵循就近原则分配多机器人搬运任务,规划多搬运机器人的协同作业轨迹,根据多搬运机器人实时位姿的自动检测结果计算控制量,利用作业轨迹自动控制器的安装与运行,完成无人仓多搬运机器人协同作业轨迹的自动控制任务;实验结果表明,在该方法应用后,多搬运机器人在无人仓中的作业轨迹与规划轨迹基本相同,计算得出的平均位置控制误差和姿态角控制误差分别为2.27 cm和0.05°,搬运机器人的碰撞次数能被控制在规定范围内,实际应用效果好。     

基于对象阻抗控制的多机器人协调方法——模型、算法与实验

推广了单机械手的阻抗控制思想,基于被操作对象的目标阻抗关系,推导了面向对象 的多手协调动力学模型和控制算法.该算法包含不同的抓持类型,考虑对象与环境的接触点信 息,能够补偿整个系统的动力学特性,同时实现对象运动、外力和内力的控制;另外,该算法具有 模块化结构,它的分层和并行实现缩短了双手的控制周期.在两台PUMA562机械手上的实验 结果验证了算法的有效性.     

基于简化三维线性倒立摆模型的模糊控制射门算法

针对双足机器人传统射门算法存在仅适用于固定射门角度和射门姿态的问题,提出了一种基于简化三维线性倒立摆模型的模糊控制射门算法,用于实现多角度、多姿态的射门。首先利用简化三维线性倒立摆模型规划出零力矩点(ZMP)轨迹和质心轨迹;其次在双腿支撑相对双足机器人进行射门角度和姿态的调整,同时利用贝塞尔曲线规划出游动腿的轨迹;最后利用模糊控制算法精确地规划出双足机器人的射门轨迹。实验部分利用NAO机器人仿真平台验证了本文提出射门算法的性能,并与其它射门算法进行了比较。最后将实物NAO机器人用于全过程与多角度的实际射门实验,验证了本文提出射门的算法可行性与准确性。     

General fight rule-based trajectory planning for pairwise collision avoidance in a known environment

This paper presents a general flight rule-based autonomous trajectory planning scheme for two aerial vehicles to avoid obstacles and collisions in known environments in low-altitude airspace for general aviation. Flight rules in low-altitude airspace are first introduced based on the general flight rules in US, UK and China, and then the suitable flight rules are embedded into the trajectory planning algorithm. It is supposed that the flight parameters, such as positions and velocities, are all available to the aerial vehicles involved in the possible conflict. Then the trajectory of each aerial vehicle is calculated by optimizing an objective function, such as distance and fuel consumption, with the constraints corresponding to the airspace traffic rules. The optimization problem is solved by receding horizon control (RHC) based mixed integer linear programming (MILP). Compared with other collision avoidance algorithms, the proposed algorithm can be adapted to plan the autonomous trajectory to avoid pairwise collision and obstacles as proposed general flight rules. Simulations show the feasibility of the proposed scheme.     

全方位六足步行机器人运动规划的相对运动算法

本文提出了步行机器人运动控制算法。该方法以相对运动学原理为基础,把机体的运动规划问题转化为腿的足端轨迹规划问题,从而使步行机器人运动控制问题得到大大简化.并应用该方法对全方位三角步态算法及稳定性进行分析求解.     

基于小波逼近的非线性系统鲁棒迭代学习控制

针对存在扰动的未知非线性系统,利用小波逼近将系统参数化,结合变结构控制技术, 提出了一种鲁棒迭代学习控制算法.该算法采用迭代学习的方式修正小波逼近的系数,利用具 有死区的滑模变结构技术保证算法的鲁棒收敛性.收敛性分析表明,每次迭代学习都将减小所 得到的逼近系数与最佳系数的差异.因此,期望轨迹变化后,该算法针对以前轨迹的学习结果仍 然可以起作用,部分克服了传统迭代学习控制的学习结果仅对某一特定轨迹有效的缺点.     

A design technique for fast sampled-data nonlinear model predictive control with convergence and stability results

ABSTRACT

In this study, a sampled-data nonlinear model predictive control scheme is developed. The control algorithm uses a prediction horizon with variable length, a terminal constraint set, and a feedback controller defined on this set. Following a suboptimal solution strategy, a defined number of steps of an iterative optimisation routine improve the current input trajectory at each sampling point. The value of the objective function monotonically decreases and the state converges to a target set. A discrete-time formulation of the algorithm and a discrete-time design model ensure high computational efficiency and avoid an ad hoc quasi-continuous implementation. This design technique for a fast sampled-data nonlinear model predictive control algorithm is the main contribution of the paper. Based on a benchmark control problem, the performance of the developed control algorithm is assessed against state-of-the-art nonlinear model predictive control methods available in the literature. This assessment demonstrates that the developed control algorithm stabilises the system with very low computational effort. Hence, the algorithm is suitable for real-time control of fast dynamical systems.     

汽车转向/防抱死制动协同控制

为了解决汽车转向过程中防抱死制动稳定性问题,提出一种新的协同控制系统.该协同控制结构由转向控制器和制动控制器组成.在转向控制中设计滑模鲁棒自适应控制器和横摆力矩控制器力求改善汽车动态响应,鲁棒自适应性和稳定性.此外定义协同误差,建立汽车协同误差模型并设计汽车防抱死制动鲁棒自适应控制系统.为了减少转向系统和制动系统之间的补偿控制律难以确定的困难,提出耦合误差补偿原理与同一给定控制相结合的新的耦合控制策略.最后用仿真结果验证所设计控制算法的有效性.     

Fixed-time backstepping distributed cooperative control for multiple unmanned aerial vehicles

This paper proposes a fixed-time backstepping distributed cooperative control scheme based on fixed-time extended state observer (FxTESO) for multiple unmanned aerial vehicles (UAVs). A fixed-time ESO, which is convergent independently of initial conditions, is designed to estimate and compensate the external disturbances in tracking process. Moreover, to eliminate the “explosion of complexity” in the traditional backstepping architecture, a nonlinear first-order filter is adopted to construct the distributed fixed-time control scheme. Based on the local information of neighboring UAVs, a fixed-time backstepping cooperative controller is designed. The proposed formation algorithm can be shown practicable for the UAV control system by using of Lyapunov stability theory and graph theory. Simulation results are given to demonstrate the effectiveness of the proposed control scheme.