四足机器人节律柔顺行走控制

针对节律运动突变碰撞力大和柔顺性低的问题,改进基于Hopf振荡器的中枢模式发生器模型,提出一种节律柔顺行走控制方法。分析Hopf振荡器输出信号与关节运动之间的关系,整合膝关节变量,改变神经元之间的作用关系,实现对称步态和非对称步态行走;分析节律运动碰撞力突变对四足机器人行走产生的负面影响,提出基于碰撞力大小和四足机器人身体姿态的柔顺性评估方法;通过连续调整碰撞阶段大腿的摆动幅度,增大摆动周期,减小碰撞阶段的关节运动速度,形成机器人本体与地面之间的缓冲,实现节律柔顺行走。四足机器人慢走步态和对角小跑步态仿真实验验证了该控制方法的有效性。     

基于环境反馈机制的四足机器人运动技能学习

哺乳动物的运动学习机制已得到广泛研究,犬科动物可以根据环境反馈的引导性信息自主地学习运动技能,对其提供更为特定的训练引导可以加快其对相关任务的学习速度.受上述启发,在软演员-评论家算法(SAC)的基础上提出一种基于期望状态奖励引导的强化学习算法(DSG-SAC),利用环境中的状态反馈机制来引导四足机器人进行有效探索,可以提高四足机器人仿生步态学习效果,并提高训练效率.在该算法中,策略网络与评价网络先近似拟合期望状态观测与当前状态的误差,再经过当前状态的正反馈后输出评价函数与动作,使四足机器人朝着期望的方向动作.将所提出算法在四足机器人上进行验证,通过实验结果可知,所提出的算法能够完成四足机器人的仿生步态学习.进一步,设计消融实验来探讨超参数温度系数和折扣因子对算法的影响,实验结果表明,改进后的算法具有比单纯的SAC算法更加优越的性能.     

四足机器人步态生成算法研究与仿真

在四足机器人行走动态控制的研究中,为使四足机器人能在复杂地面状况下行走,提出了一种四足机器人在不平坦地面爬行时的平动步态生成算法.首先构建四足机器人步行机构模型,根据静态稳定性对角线原理的判定确定机器人腿的摆动顺序;以平动步态为例根据机器人前行方向、初始位姿、地面不平坦等因素计算一个步态周期后机器人的位姿从而实现平动直线行走的连续步态算法.考虑了机器人机构约束以及状态变化因素使机器人在每一个步态周期都能跨出尽可能大的步幅实现行走效率的最大化.通过仿真验证了算法的正确性.仿真结果对四足机器人步态稳定性的研究及实现具有实际的参考价值.     

基于Fuzzy–CPG的双足机器人适应性行走控制

为提高双足机器人的环境适应性, 本文提出了一种基于模糊控制与中枢模式发生器(CPG)的混合控制策 略, 称之为Fuzzy–CPG算法. 高层控制中枢串联模糊控制系统, 将环境反馈信息映射为行走步态信息和CPG幅值参 数. 低层控制中枢CPG根据高层输出命令产生节律性信号, 作为机器人的关节控制信号. 通过机器人运动, 获取环境 信息并反馈给高层控制中枢, 产生下一步的运动命令. 在坡度和凹凸程度可变的仿真环境中进行混合控制策略的 实验验证, 结果表明, 本文提出的Fuzzy–CPG控制方法可以使机器人根据环境的变化产生适应的行走步态, 提高了 双足机器人的环境适应性行走能力.     

基于余弦振荡器的四足机器人步态生成与仿真

为实现四足机器人的稳定运动,基于四足机器人对角步态的几何模型,建立余弦振荡器,生成节律运动的上层架构以及上、下层之间的关节映射,得到完整的步态生成策略,并建立四种关节配置形式的机器人虚拟样机模型,进行运动学和动力学仿真.仿真结果表明,基于余弦振荡器的步态生成方法能够满足各种关节配置形式的机器人步态要求,验证了步态生成方法的正确性和普遍适用性,且根据机体波动率的比较,确定前肘后膝式具有更好的稳定性.     

一种六足步行机器人的自由步态算法

本文探讨了适用于六足步行机器人的步态类型和机器人腿运动的三个约束条件,提出了一种适用于六足步行机器人在不规则地形上运动的自由步态算法.机器人在大部分的地形状况下以标准模式行走.当标准模式失效时,则采用自适应模式,对机器人状态进行调整,以实现正常的行走运动.在保证运动速度和能量效率的前提下,使机器人具备良好的地形适应能力.最后,文章给出了算法的程序流程图,并在MATLAB下进行了仿真验证.     

四腿机器人步态参数自动进化研究与实现

采用进化算法和基于自主视觉的适应度评估方法,实现了四腿机器人在RoboCup机器人足球比赛现场的行走步态在线自动进化．我们引入内推法作为交叉方法,利用PC基站进行进化算法计算和流程主控,并采用了一些学习时间缩减策略．实现了进化学习的连续性和可扩展性,使得学习过程可以在4060min内完成,这样就能在比赛现场对ERS-7四足机器人进行行走再学习,提高了行走控制的适应性．算法最终结果使ERS-7型四足机器人的行走速度从27cm/s提升到43cm/s．     

基于深度强化学习的双足机器人斜坡步态控制方法

为提高准被动双足机器人斜坡步行稳定性, 本文提出了一种基于深度强化学习的准被动双足机器人步态控制方法. 通过分析准被动双足机器人的混合动力学模型与稳定行走过程, 建立了状态空间、动作空间、episode过程与奖励函数. 在利用基于DDPG改进的Ape-X DPG算法持续学习后, 准被动双足机器人能在较大斜坡范围内实现稳定行走. 仿真实验表明, Ape-X DPG无论是学习能力还是收敛速度均优于基于PER的DDPG. 同时, 相较于能量成型控制, 使用Ape-X DPG的准被动双足机器人步态收敛更迅速、步态收敛域更大, 证明Ape-X DPG可有效提高准被动双足机器人的步行稳定性.     

连续不规则台阶环境四足机器人步态规划与控制

为了实现四足机器人在无崎岖地形先验知识情况下的自主爬行,提出了一种四足机器人运动控制方法.该方法采用间歇爬行步态作为主步态,将爬行运动分解为若干任务分别进行控制:基于NESM(normalized energy stability margin)判据计算内外倾的稳定裕度并根据其比值进行质心位置调整;使用坐标映射的方式调整足端坐标进行地面坡度适应;通过调整各腿长度控制机器人的高度;利用姿态传感器信息进行姿态恢复.仿真和实验表明,机器人仅依赖内部传感器即实现了在崎岖地形稳定行走,验证了本文方法的有效性和可靠性.     

基于RBF-Q学习的四足机器人运动协调控制

通过分析四足机器人运动协调的实现方式, 利用RBF网络和Q学习算法设计了一种足端跟踪理想轨迹的运动协调方法。其仿真结果表明, 该方法可以控制四足机器人足端对给定位移和速度轨迹的精确跟踪, 实现四足机器人的运动协调。     

Energy-optimal gait analysis of quadruped robots

It is important for walking robots such as quadruped robots to have an efficient gait. Since animals and insects are the basic models for most walking robots, their walking patterns are good examples. In this study, the walking energy consumption of a quadruped robot is analyzed and compared with natural animal gaits. Genetic algorithms have been applied to obtain the energy-optimal gait when the quadruped robot is walking with a set velocity. In this method, an individual in a population represents the walking pattern of the quadruped robot. The gait (individual) which consumes the least energy is considered to be the best gait (individual) in this study. The energy-optimal gait is analyzed at several walking velocities, since the amount of walking energy consumption changes if the walking velocity of the robot is changed. The results of this study can be used to decide what type of gait should be generated for a quadruped robot as its walking velocity changes. This work was presented, in part, at the Sixth International Symposium on Artificial Life and Robotics, Tokyo, Japan, January 15–17, 2001.     

Intelligent proximal-policy-optimization-based decision-making system for humanoid robots

With the advancements in technology, robots have gradually replaced humans in different aspects. Allowing robots to handle multiple situations simultaneously and perform different actions depending on the situation has since become a critical topic. Currently, training a robot to perform a designated action is considered an easy task. However, when a robot is required to perform actions in different environments, both resetting and retraining are required, which are time-consuming and inefficient. Therefore, allowing robots to autonomously identify their environment can significantly reduce the time consumed. How to employ machine learning algorithms to achieve autonomous robot learning has formed a research trend in current studies. In this study, to solve the aforementioned problem, a proximal policy optimization algorithm was used to allow a robot to conduct self-training and select an optimal gait pattern to reach its destination successfully. Multiple basic gait patterns were selected, and information-maximizing generative adversarial nets were used to generate gait patterns and allow the robot to choose from numerous gait patterns while walking. The experimental results indicated that, after self-learning, the robot successfully made different choices depending on the situation, verifying this approach’s feasibility.     

Steady Crawl Gait Generation Algorithm for Quadruped Robots

The capability of stable walking on irregular terrain is the primary advantage of legged robots over wheeled mobile robots. However, the traditional foothold selection-based gait generation algorithms are not suitable at some points for blind robots which cannot obtain the exact terrain information. A velocity-based gait generation algorithm with real-time adaptation rules which are necessary for steady walking is suggested. Particularly, we have developed a steady crawl gait with duty factor β = 0.75. The main feature of the suggested algorithm is that it is not based on foothold selection and it can be used for the walking of blind robots on more realistic irregular terrain. The adaptation rules are the translational velocity modification to satisfy the steady gait requirement and the swing period modification to avoid the kinematic limitation. The suggested gait generation algorithm has been implemented in a simple quadruped robot that has a total of eight actuated joints on the legs. Using PD controllers for each actuated joint for the trajectory following and the adaptation algorithm of gait parameters, the steady periodic crawl gait on irregular terrain has been demonstrated.     

Crab walking of quadruped robots with a locked joint failure

Fault tolerance is an important aspect in the development of control systems for multi-legged robots since a failure in a leg may lead to a severe loss of static stability of a gait. In this paper, an algorithm for tolerating a locked joint failure is described in gait planning for a quadruped robot with crab walking. A locked joint failure is one for which a joint cannot move and is locked in place. If a failed joint is locked, the workspace of the resulting leg is constrained, but legged robots have fault tolerance capability to continue walking maintaining static stability. A strategy for fault-tolerant gaits is described and, especially, a periodic gait is presented for crab walking of a quadruped. The leg sequence and the formula of the stride length are analytically driven based on gait study and robot kinematics. The adjustment procedure from a normal gait to the proposed fault-tolerant crab gait is shown to demonstrate the applicability of the proposed scheme.     

Generation of a continuous free gait for quadruped robot over rough terrains

Generating a robust gait is one of the most important factors to improve the adaptability of quadruped robots on rough terrains. This paper presents a new continuous free gait generation method for quadruped robots capable of walking on the rough terrain characterized by the uneven ground and forbidden areas. When walking with the proposed gait, the robot can effectively maintain its stability by using the Center of Gravity (COG) trajectory planning method. After analyzing the point cloud of rough terrain, the forbidden areas of the terrain can be obtained. Based on this analysis, an optimal foothold search strategy is presented to help quadruped robot to determine the optimum foothold for the swing foot automatically. In addition, the foot sequence determining method is proposed to improve the performance of robot. With the free gait proposed in this paper, quadruped robot can walk through the rough terrains automatically and successfully. The correctness and effectiveness of the proposed method is verified via simulations.     

基于改进蚁群算法的四足机器人步态规划

四足机器人关节众多、运动方式复杂,步态规划是四足机器人运动控制的基础。传统的算法多基于仿生原理,缺乏广泛适应性。 在建立运动学方程的基础上,提出了一种基于改进蚁群算法的步态规划算法。该算法利用了四足机器人4条腿运动的线性无关性,将步态规划问题转换为在四维空间里求取最长路径问题。仿真结果表明,该算法得出了满足约束条件的所有步态,最后通过机器人样机检验,验证了该算法求取结果的有效性和合理性。     

Prior notice method of robotic arm motion for suppressing a threat to a human

The ability to develop a gait with one or more legs missing is an important issue for multi-legged robots used in demining applications. Accordingly, this paper presents a three-legged gait under the assumption that one leg of a quadruped walking robot is missing. After outlining a posture classification scheme for three-legged walking, the kick-and-swing gait is proposed as a basic and reasonable gait for three-legged walking and analyzed using a simple dynamic model. Minimum energy gait planning and an active shock-absorbing method are also investigated. The validity of the proposed gait is shown based on experiments using the quadruped walking robot TITAN VIII.     

基于改进近端策略优化算法的草酸钴合成过程优化

金属钴被广泛用于电池和金属复合材料,草酸钴合成过程是影响产品质量的关键工序.针对草酸钴平均粒径的优化问题,提出一种基于改进的近端策略优化(PPO)算法的草酸钴合成过程优化方法.首先,根据草酸钴合成过程的优化目标及约束条件设计相应的奖励函数,通过建立过程的马尔科夫决策模型,将优化问题纳入强化学习框架;其次,针对策略网络在训练过程中出现的梯度消失问题,提出将残差网络作为PPO算法的策略网络;最后,针对过程连续状态空间导致PPO算法陷入局部最优策略问题,利用交错模仿学习对初始策略进行改进.将所提出的方法与传统PPO算法进行比较,改进的PPO算法在满足约束条件的同时,具有更好的优化效果和收敛性.     

MAML2: meta reinforcement learning via meta-learning for task categories

Meta-learning has been widely applied to solving few-shot reinforcement learning problems, where we hope to obtain an agent that can learn quickly in a new task. However, these algorithms often ignore some isolated tasks in pursuit of the average performance, which may result in negative adaptation in these isolated tasks, and they usually need sufficient learning in a stationary task distribution. In this paper, our algorithm presents a hierarchical framework of double meta-learning, and the whole framework includes classification, meta-learning, and re-adaptation. Firstly, in the classification process, we classify tasks into several task subsets, considered as some categories of tasks, by learned parameters of each task, which can separate out some isolated tasks thereafter. Secondly, in the meta-learning process, we learn category parameters in all subsets via meta-learning. Simultaneously, based on the gradient of each category parameter in each subset, we use meta-learning again to learn a new meta-parameter related to the whole task set, which can be used as an initial parameter for the new task. Finally, in the re-adaption process, we adapt the parameter of the new task with two steps, by the meta-parameter and the appropriate category parameter successively. Experimentally, we demonstrate our algorithm prevents the agent from negative adaptation without losing the average performance for the whole task set. Additionally, our algorithm presents a more rapid adaptation process within re-adaptation. Moreover, we show the good performance of our algorithm with fewer samples as the agent is exposed to an online meta-learning setting.     

How to optimize the slope walking motion by the quadruped walking robot

Reduction of the energy consumption is one of the most important problems to utilize quadruped walking robots for various works on rugged terrain. The authors have studied basic strategy to achieve high energy efficiency when the quadruped walking robot do the motion essentially requires positive power by the analysis of body rising motion. This paper discusses the energy efficiency of the slope walking motion by the quadruped walking robot. First, we investigate the walking posture in consideration of ideal actuator characteristics where the robot consumes few negative powers at each joint which causes the main energy loss of the walking robot. Then, we investigate optimal walking posture in consideration of DC motor characteristics by the full search of three gait parameters which define the crawl gait. Furthermore, we derive the optimal walking motion by the optimization of three gait parameters which are kept constant during one cycle gait and instantaneous parameters such as body velocity and supporting forces changed at each moment simultaneously.