基于自学习中枢模式发生器的仿人机器人适应性行走控制

为了克服传统中枢模式发生器(Central pattern generator, CPG)关节空间控制方法的复杂性和局限性, 本文基于自学习中枢模式发生器模型, 提出了一套在线调制和融合多传感器信息的仿人机器人环境自适应行走控制方法.算法难点在于如何在机器人的工作空间将自学习CPG用于工作空间轨迹生成, 并使CPG参数直接和步态模式相关联.本文提出了利用自学习CPG来学习和实时生成机器人质心轨迹和脚掌轨迹的方法, 在线调节机器人步长、抬腿高度和步行速度等关键参数.参考生物反射行为, 利用传感反馈信息激发CPG以产生具有环境适应性的工作空间轨迹, 提升行走质量. 控制系统的参数通过优化算法来进一步改善行走性能.相比于传统的CPG关节空间法, 本文所采用的自学习CPG工作空间法不仅极大简化了CPG网络结构而且提高了仿人机器人行走的适应性.最后, 通过仿人机器人坡面适应性行走的仿真和实验, 验证了所提出控制策略的可行性和有效性.     

Realization of Dynamic Walking and Running of the Quadruped Using Neural Oscillator

In the present study we attempt to induce a quadruped robot to walk dynamically on irregular terrain and run on flat terrain by using a nervous system model. For dynamic walking on irregular terrain, we employ a control system involving a neural oscillator network, a stretch reflex and a flexor reflex. Stable dynamic walking when obstructions to swinging legs are present is made possible by the flexor reflex and the crossed extension reflex. A modification of the single driving input to the neural oscillator network makes it possible for the robot to walk up a step. For running on flat terrain, we combine a spring mechanism and the neural oscillator network. It became clear in this study that the matching of two oscillations by the spring-mass system and the neural oscillator network is important in order to keep jumping in a pronk gait. The present study also shows that entrainment between neural oscillators causes the running gait to change from pronk to bound. This finding renders running fairly easy to attain in a bound gait. It must be noticed that the flexible and robust dynamic walking on irregular terrain and the transition of the running gait are realized by the modification of a few parameters in the neural oscillator network.     

Adaptive walking control of quadruped robots based on central pattern generator （CPG） and reflex

This paper presents a central pattern generator (CPG) and vestibular reflex combined control strategy for a quadruped robot. An oscillator network and a knee-to-hip mapping function are presented to realize the rhythmic motion for the quadruped robot. A two-phase parameter tuning method is designed to adjust the parameters of oscillator network. First, based on the numerical simulation, the influences of the parameters on the output signals are analyzed, then the genetic algorithm (GA) is used to evolve the phase relationships of the oscillators to realize the basic animal-like walking pattern. Moreover, the animal’s vestibular reflex mechanism is mimicked to realize the adaptive walking of the quadruped robot on a slope terrain. Coupled with the sensory feedback information, the robot can walk up and down the slope smoothly. The presented bio-inspired control method is validated through simulations and experiments with AIBO. Under the control of the presented CPG and vestibular reflex combined control method, AIBO can cope with slipping, falling down and walk on a slope successfully, which demonstrates the effectiveness of the proposed walking control method.     

Sensorimotor Interactions During Locomotion: Principles Derived from Biological Systems

Rhythmic movements in biological systems are produced in part by central circuits called central pattern generators (CPGs). For example, locomotion in vertebrates derives from the spinal CPG with activity initiated by the brain and controlled by sensory feedback. Sensory feedback is traditionally viewed as controlling CPGs cycle by cycle, with the brain commanding movements on a top down basis. We present an alternative view which in sensory feedback alters the properties of the CPG on a fast as well as a slow time scale. The CPG, in turn, provides feedforward filtering of the sensory feedback. This bidirectional interaction is widespread across animals, suggesting it is a common feature of motor systems, and, therefore, might offer a new way to view sensorimotor interactions in all systems including robotic systems. Bidirectional interactions are also apparent between the cerebral cortex and the CPG. The motor cortex doesn't simply command muscle contractions, but rather operates with the CPG to produce adaptively structured movements. To facilitate these adaptive interactions, the motor cortex receives feedback from the CPG that creates a temporal activity pattern mirroring the spinal motor output during locomotion. Thus, the activity of the motor cortical cells is shaped by the spinal pattern generator as they drive motor commands. These common features of CPG structure and function are suggested as offering a new perspective for building robotic systems. CPGs offer a potential for adaptive control, especially when combined with the principles of sensorimotor integration described here.     

Development of adaptive locomotion of a caterpillar-like robot based on a sensory feedback CPG model

This paper presents a novel control mechanism for generating adaptive locomotion of a caterpillar-like robot in complex terrain. Inspired by biological findings in studies of the locomotion of the lamprey, we employ sensory feedback integration for online modulation of the control parameters of a new proposed central pattern generator (CPG). This closed-loop control scheme consists of the following stages: First, touch sensor information is processed and transformed into module states. Then, reactive strategies that determine the mapping between module states and sensory inputs are generated according to an analysis of the module states. Finally, by means of a genetic algorithm, adaptive locomotion is achieved by optimising the amount and speed of sensory input that is fed back to the CPG model. Incorporating the closed-loop controller in a caterpillar-like robot, both simulation and real on-site experiments are carried out. The results confirm the effectiveness of the control system, based on which the robot flexibly adapts to, and manages to crawl across the complex terrain.     

An adaptive locomotion controller for a hexapod robot: CPG,kinematics and force feedback

Insects can perform versatile locomotion behaviors such as multiple gaits, adapting to different terrains, fast escaping, etc. However, most of the existing bio-inspired legged robots do not possess such walking ability, especially when they walk on irregular terrains. To tackle this challenge, a central pattern generator （CPG）-based locomotion control methodology is proposed, integrated with a contact force feedback function. In this approach, multiple gaits are produced by the CFG module. After passing through a post-processing circuit and a delay-line, the control signal is fed into six trajectory generators to generate predefined feet trajectories for the six legs. Then, force feedback is employed to adjust these trajectories so as to adapt the robot to rough terrains. Finally the regulated trajectories are sent to inverse kinematics modules such that the position control instructions are generated to control the actuators. In both simulations and real robot experiments, we consistently show that the robot can perform sophisticated walking patterns. What is more, the robot can use the force feedback mechanism to deal with the irregularity in rough terrain. With this mechanism, the stability and adaptability of the robot are enhanced. In conclusion, the CPG-base control is an effective approach for legged robots and the force feedback approach is able to improve walking ability of the robots, especially when they walk on irregular terrains.     

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CPG模型的仿生机器鱼运动控制

仿生机器鱼的研究已经成为一个富有挑战性的热点问题.为了控制机器鱼自身的运动和姿态,本文研究了胸鳍对机器鱼运动的影响,并且基于CPG模型,提出了一种运动控制方法.采用的控制模型由4个振荡器构成,可根据反馈的信息产生节律信号以控制机器鱼胸鳍和尾鳍的运动.根据CPG模型参数与反馈输入之间的关系,设计了机器鱼俯仰和转弯反馈控制方法,利用反馈的信息自主调节CPG参数,达到控制胸鳍运动模式的目的.仿真实验验证了控制模型和反馈策略的有效性.     

Towards goal-directed biped locomotion: Combining CPGs and motion primitives

In this paper it is presented a CPG approach based on phase oscillators to bipedal locomotion where the designer with little a priori knowledge is able to incrementally add basic motion primitives, reaching bipedal walking and other locomotor behaviors as final result. The proposed CPG aims to be a model free solution for the generation of bipedal walking, not requiring the use of inverse kinematical models and previously defined joint trajectories.The proposed incremental construction of bipedal walking allows an easier parametrization and performance evaluation throughout the design process. Furthermore, the approach provides for a developmental mechanism, which enables progressively building a motor repertoire. It would easily benefit from evolutionary robotics and machine learning to explore this aspect.The proposed CPG system also offers a good substrate for the inclusion of feedback mechanisms for modulation and adaptation. It is explored a phase regulation mechanism using load sensory information, observable in vertebrate legged animals.Results from simulations, on HOAP and DARwIn-OP in Webots software show the adequacy of the locomotor system to generate bipedal walk on different robots. Experiments on a DARwIn-OP demonstrates how it can accomplish locomotion and how the proposed work can generalize, achieving several distinct locomotor behaviors.     

Connection topology selection in central pattern generators by maximizing the gain of information

A study of a general central pattern generator (CPG) is carried out by means of a measure of the gain of information between the number of available topology configurations and the output rhythmic activity. The neurons of the CPG are chaotic Hindmarsh-Rose models that cooperate dynamically to generate either chaotic or regular spatiotemporal patterns. These model neurons are implemented by computer simulations and electronic circuits. Out of a random pool of input configurations, a small subset of them maximizes the gain of information. Two important characteristics of this subset are emphasized: (1) the most regular output activities are chosen, and (2) none of the selected input configurations are networks with open topology. These two principles are observed in living CPGs as well as in model CPGs that are the most efficient in controlling mechanical tasks, and they are evidence that the information-theoretical analysis can be an invaluable tool in searching for general properties of CPGs.     

Biped Locomotion Control through a Biomimetic CPG-based Controller

Modern concepts of motor learning favour intensive training directed to the neural networks stimulation and reorganization within the spinal cord, the central pattern generator, by taking advantage of the neural plasticity. In the present work, a biomimetic controller using a system of adaptive oscillators is proposed to understand the neuronal principles underlying the human locomotion. A framework for neural control is presented, enabling the following contributions: a) robustness to external perturbations; b) flexibility to variations in the environmental constraints; and c) incorporation of volitional mechanisms for self-adjustment of gait dynamics. Phase modulation of adaptive oscillators and postural balance control are proposed as main strategies for stable locomotion. Simulations of the locomotion model with a biped robot in closed-loop control are presented to validate the implemented neuronal principles. Specifically, the proposed system for online modulation of previous learnt gait patterns was verified in terrains with different slopes. The proposed phase modulation method and postural balanced control enabled robustness enhancement considering a broader range of slope angles than recent studies. Furthermore, the system was also verified for tilted ground including different slopes in the same experiment and uneven terrain with obstacles. Adaptive Frequency Oscillators, under Dynamic Hebbian Learning Adaptation mechanism, are proposed to build a hierarchical control architecture with spinal and supra spinal centers with multiple rhythm-generating neural networks that drive the legs of a biped model. The proposed neural oscillators are based on frequency adaptation and can be entrained by sensory feedback to learn specific patterns. The proposed biomimetic controller intrinsically generates patterns of rhythmic activity that can be induced to sustain CPG function by specific training. This method provides versatile control, paving the way for the design of experimental motor control studies, optimal rehabilitation procedures and robot-assisted therapeutic outcomes.     

Central pattern generator based reflexive control of quadruped walking robots using a recurrent neural network

This paper presents a novel Central Pattern Generator (CPG) model for controlling quadruped walking robots. The improvement of this model focuses on generating any desired waveforms along with accurate online modulation. In detail, a well-analyzed Recurrent Neural Network is used as the oscillators to generate simple harmonic periodic signals that exhibit limit cycle effects. Then, an approximate Fourier series is employed to transform those mentioned simple signals into arbitrary desired outputs under the phase constraints of several primary quadruped gaits. With comprehensive closed-form equations, the model also allows the user to modulate the waveform, the frequency and the phase constraint of the outputs online by directly setting the inner parameters without the need for any manual tuning. In addition, an associated controller is designed using leg coordination Cartesian position as the control state space based on which stiffness control is performed at sub-controller level. In addition, several reflex modules are embedded to transform the feedback of all sensors into the CPG space. This helps the CPG recognize external disturbances and utilize inner limit cycle effect to stabilize the robot motion. Finally, experiments with a real quadruped robot named AiDIN III performing several dynamic trotting tasks on several unknown natural terrains are presented to validate the effectiveness of the proposed CPG model and controller.     

CPG-based control of a turtle-like underwater vehicle

This paper presents biologically inspired control strategies for an autonomous underwater vehicle (AUV) propelled by flapping fins that resemble the paddle-like forelimbs of a sea turtle. Our proposed framework exploits limit cycle oscillators and diffusive couplings, thereby constructing coupled nonlinear oscillators, similar to the central pattern generators (CPGs) in animal spinal cords. This paper first presents rigorous stability analyses and experimental results of CPG-based control methods with and without actuator feedback to the CPG. In these methods, the CPG module generates synchronized oscillation patterns, which are sent to position-servoed flapping fin actuators as a reference input. In order to overcome the limitation of the open-loop CPG that the synchronization is occurring only between the reference signals, this paper introduces a new single-layered CPG method, where the CPG and the physical layers are combined as a single layer, to ensure the synchronization of the physical actuators in the presence of external disturbances. The key idea is to replace nonlinear oscillators in the conventional CPG models with physical actuators that oscillate due to nonlinear state feedback of the actuator states. Using contraction theory, a relatively new nonlinear stability tool, we show that coupled nonlinear oscillators globally synchronize to a specific pattern that can be stereotyped by an outer-loop controller. Results of experimentation with a turtle-like AUV show the feasibility of the proposed control laws.     

Vision-based path following by using a neural network Guidance System

This article describes a neural network controller for guidance of a robot arm, used to model some aspects of autonomous vehicle technology. The controller uses video images with adaptive view-angles for the sensory input, and the system was configured to simulate an autonomous vehicle guidance system on a flat terrain using a high-contrast guiding path. To demonstrate the feasibility of using neural networks in this type of application, an Intelledex 405 robot fitted with a video camera and associated vision system was used. Phase I of the project consisted of a single-speed implementation and limited network training. Phase II featured a multi-speed implementation using adaptively varied view-angles based on robot arm velocity. It was shown that the neural network controller was able to control the robot arm along a path composed of path segments unlike those with which it was trained. In addition it was shown that a multi-speed implementation with adaptive view angles improved system performance. © 1994 John Wiley & Sons, Inc.     

Gait planning and intelligent control for a quadruped robot

We present a method for designing free gaits for a structurally symmetrical quadruped robot capable of performing statically stable, omnidirectional walking on irregular terrain. The robot＇s virtual model is constructed and a control algorithm is proposed by applying virtual components at some strategic locations. The deliberative-based controller can generate flexible sequences of leg transferences while maintaining walking speed, and choose optimum foothold for moving leg based on integration data of exteroceptive terrain profile. Simulation results are presented to show the gait＇s efficiency and system＇s stability in adapting to an uncertain terrain.     

Reflex-oscillations in evolved single leg neurocontrollers for walking machines

As a prerequisite for developing neural control for walking machines that are able to autonomously navigate through rough terrain, artificial structure evolution is used to generate various single leg controllers. The structure and dynamical properties of the evolved (recurrent) neural networks are then analysed to identify elementary mechanisms of sensor-driven walking behaviour. Based on the biological understanding that legged locomotion implies a highly decentralised and modular control, neuromodules for single, morphological distinct legs of a hexapod walking machine were developed by using a physical simulation. Each of the legs has three degrees of freedom (DOF). The presented results demonstrate how extremely small reflex-oscillators, which inherently rely on the sensorimotor loop and e.g. hysteresis effects, generate effective locomotion. Varying the fitness function by randomly changing the environmental conditions during evolution, neural control mechanisms are identified which allow for robust and adaptive locomotion. Relations to biological findings are discussed.     

Central pattern generators based on Matsuoka oscillators for the locomotion of biped robots

Biologically inspired control approaches based on central pattern generators (CPGs) with neural oscillators have been drawing much attention for the purpose of generating rhythmic motion for biped robots with human-like locomotion. This article describes the design of a neural-oscillator-based gait-rhythm generator using a network of Matsuoka oscillators to generate a walking pattern for biped robots. This includes the proper consideration of the oscillator’s parameters, such as a time constant for the adaptation rate, coupling factors for mutual inhibitory connections, etc., to obtain a stable and desirable response from the network. The article examines the characteristics of a CPG network with six oscillators, and the effect of assigning symmetrical and asymmetrical coupling coefficients among oscillators within the network structure under different possible inhibitions and excitations. The kinematics and dynamics of a five-link biped robot have been modeled, and its joints are actuated through simulation by the torques output from the neural rhythm generator to generate the trajectories for hip, knee, and ankle joints. The parameters of the neural oscillators are tuned to achieve flexible trajectories. The CPG-based control strategy is implemented and tested through a simulation. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007     

Walking Robots and the Central and Peripheral Control of Locomotion in Insects

This paper outlines aspects of locomotor control in insects that may serve as the basis for the design of controllers for autonomous hexapod robots. Control of insect walking can be considered hierarchical and modular. The brain determines onset, direction, and speed of walking. Coordination is done locally in the ganglia that control leg movements. Typically, networks of neurons capable of generating alternating contractions of antagonistic muscles (termed central pattern generators, or CPGs) control the stepping movements of individual legs. The legs are coordinated by interactions between the CPGs and sensory feedback from the moving legs. This peripheral feedback provides information about leg load, position, velocity, and acceleration, as well as information about joint angles and foot contact. In addition, both the central pattern generators and the sensory information that feeds them may be modulated or adjusted according to circumstances. Consequently, locomotion in insects is extraordinarily robust and adaptable.     

Gait transition and modulation in a quadruped robot: A brainstem-like modulation approach

In this article, we propose a bio-inspired architecture for a quadruped robot that is able to initiate/stop locomotion; generate different gaits, and to easily select and switch between the different gaits according to the speed and/or the behavioral context. This improves the robot stability and smoothness while locomoting.We apply nonlinear oscillators to model Central Pattern Generators (CPGs). These generate the rhythmic locomotor movements for a quadruped robot. The generated trajectories are modulated by a tonic signal, that encodes the required activity and/or modulation. This drive signal strength is mapped onto sets of CPG parameters. By increasing the drive signal, locomotion can be elicited and velocity increased while switching to the appropriate gaits. This drive signal can be specified according to sensory information or set a priori.The system is implemented in a simulated and real AIBO robot. Results demonstrate the adequacy of the architecture to generate and modulate the required coordinated trajectories according to a velocity increase; and to smoothly and easily switch among the different motor behaviors.     

State-incremental optimal control of 3D COG pattern generation for humanoid robots

Many researchers have proposed walking pattern generation methods with zero moment point – center of gravity (ZMP–COG) constraints. Some of the researchers used a neural-networks (NN), a central pattern generator (CPG), or a genetic algorithm (GA) for ZMP–COG pattern generation. However, the parameters used in those methods are too many, and the procedure to learn or to search them costs too much computation time. Other researchers designed controllers or used analytical solution method to generate COG trajectories. These methods generate the ZMP-COG pattern very quickly, but the COG height is limited to a constant to linearize the inverted pendulum model of the robot. Due to this limitation, the robots cannot walk freely on surfaces that change in height. To solve this problem, researchers start to use the original nonlinear inverted pendulum model to make the COG height changeable such as using a numerical method or a feedback controller. In this paper, an optimal control-based pattern generator that can allow COG height change is proposed. It can solve sagittal and lateral COG patterns with arbitrarily assigned COG height and ZMP trajectories in real time. Thus, dynamic walking on height-changing surfaces can be achieved.