Optimal sagittal gait with ZMP stability during complete walking cycle for humanoid robots

A parametric method to generate low energy gait for both single and double support phases with zero moment point（ZMP） stability is presented. The ZMP stability condition is expressed as a limit to the actuating torque of the support ankle, and the inverse dynamics of both walking phases is investigated. A parametric optimization method is implemented which approximates joint trajectories by cubic spline functions connected at uniformly distributed time knots and makes optimization parameters only involve finite discrete states describing key postures. Thus, the gait optimization is transformed into an ordinary constrained nonlinear programming problem. The effectiveness of the method is verified through numerical simulations conducted on the humanoid robot THBIP-I model.     

Optimal sagittal gait with ZMP stability during complete walking cycle for humanoid robots

A parametric method to generate low energy gait for both single and double support phases with zero moment point(ZMP) stability is presented. The ZMP stability condition is expressed as a limit to the actuating torque of the support ankle, and the inverse dynamics of both walking phases is investigated. A parametric optimization method is implemented which approximates joint trajectories by cubic spline functions connected at uniformly distributed time knots and makes optimization parameters only involve finite discrete states describing key postures. Thus, the gait optimization is transformed into an ordinary constrained nonlinear programming problem. The effectiveness of the method is verified through numerical simulations conducted on the humanoid robot THBIP-I model.     

Towards stratified model-based environmental visual perception for humanoid robots

An autonomous environmental visual perception approach for humanoid robots is presented. The proposed framework exploits the available model information and the context acquired during global localization by establishing a vision-model coupling in order to overcome the limitations of purely data-driven approaches in object recognition and surrounding status assertion. The exploitation of the model-vision coupling through the properceptive components is the key element to solve complex visual assertion-queries with proficient performance. An experimental evaluation with the humanoid robot ARMAR-IIIa is presented.     

Human-like natural behavior generation based on involuntary motions for humanoid robots

Human behaviors consist of both voluntary and involuntary motions. Almost all behaviors of task-oriented robots, however, consist solely of voluntary motions. Involuntary motions are important for generating natural motions like those of humans. Thus, we propose a natural behavior generation method for humanoid robots that is a hybrid generation between voluntary and involuntary motions. The key idea of our method is to control robots with a hybrid controller that combines the functions of a communication behavior controller and body balancing controllers. We also develop a wheeled inverted pendulum type of humanoid robot, named “Robovie-III”, in order to generate involuntary motions like oscillation. By applying our method to this robot and conducting preliminary experiments, we verify its validity. Experimental results show that the robot generates both voluntary and involuntary motions.     

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.     

人体步行规律与仿人机器人步态规划

从仿生学角度分析了人体的步行运动规律,提出了一种基于人体运动规律的仿人机器人步态参数设定方法.首先对人体步行运动数据进行捕捉并分析,得出人体各步态参数间的函数关系,以人体步行相似性作为评价指标,提出仿人机器人步态参数的设定方法.其次,通过分析人体在步行过程中的补偿支撑脚偏航力矩的基本原理,提出了基于双臂及腰关节协调运动的仿人机器人偏航力矩补偿算法,以提高仿人机器人行走的稳定性.最后通过仿真及实验验证了所提出的步态规划方法的正确性及有效性.     

Motion planning for humanoid robots based on virtual constraints extracted from recorded human movements

In the field of robotics there is a great interest in developing strategies and algorithms to reproduce human-like behavior. In this paper, we consider motion planning for humanoid robots based on the concept of virtual holonomic constraints. At first, recorded kinematic data of particular human motions are analyzed in order to extract consistent geometric relations among various joint angles defining the instantaneous postures. Second, a simplified human body representation leads to dynamics of an underactuated mechanical system with parameters based on anthropometric data. Motion planning for humanoid robots of similar structure can be carried out by considering solutions of reduced dynamics obtained by imposing the virtual holonomic constraints that are found in human movements. The relevance of such a reduced mathematical model in accordance with the real human motions under study is shown. Since the virtual constraints must be imposed on the robot dynamics by feedback control, the design procedure for a suitable controller is briefly discussed.     

A dynamic simulator for humanoid robots

Computer simulation is an essential step in the design and construction of various mechanical structures, including biped robots, because it enables rapid testing and virtual prototyping during the construction phase. Although many different simulators are available, this article gives an overview and a motivation for building a new dynamic multibody simulator. The simulator is especially adapted to humanoid robot Archie, developed at the IHRT Institute at the Technical University of Vienna. In addition, it is shown how the simulator can be used not only in the controller design, but also in the online control loop to extend the available sensors: a virtual sensors principle. This work was presented in part at the First European Workshop on Artificial Life and Robtics, Vienna, Austria, July 12–13, 2007     

Multi-level cognitive machine-learning based concept for human-like “artificial” walking: Application to autonomous stroll of humanoid robots

We propose a machine-learning based multi-level cognitive model inspired from early-ages’ cognitive development of human’s locomotion skills for humanoid robot’s walking modeling. Contrary to the most of already introduced works dealing with biped robot’s walking modeling, which place the problem within the context of controlling specific kinds of biped robots, the proposed model attends to a global concept of biped walking ability’s construction independently from the robot to which the concept may be applied. The chief-benefit of the concept is that the issued machine-learning based structure takes advantage from “learning” capacity and “generalization” propensity of such models: allowing a precious potential to deal with high dimensionality, nonlinearity and empirical proprioceptive or exteroceptive information. Case studies and validation results are reported and discussed evaluating potential performances of the proposed approach.     

Petri-net-based implementations for FIRA weightlifting and sprint games with a humanoid robot

In this paper, the Petri net-based wireless sensor node architecture (PN-WSNA) is used to control a humanoid robot to play weightlifting and sprint games in the FIRA HuroCup league. With the PN-WSNA approach, the control scenario and decision-making for playing weightlifting and sprint games can be modeled as a PN-WSNA model. The PN-WSNA inference engine is further used to interpret and execute the PN-WSNA model according to the sensor information from visual perception. Therefore, the implementation of playing weightlifting and sprint games is achieved in terms of the PN-WSNA model instead of native code. To verify the PN-WSNA-based implementation approach, an autonomous humanoid robot equipped with a camera and a single-board computer is used for experiments, where the camera is responsible for grabbing image frames; the single-board computer is responsible for visual localization; and the PN-WSNA models the execution and locomotion command generation. Finally, several PN-WSNA models for playing weightlifting and sprint games are proposed and the experimental results are demonstrated and discussed to validate the feasibility of applying the proposed PN-WSNA-based implementation approach.     

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.     

基于解藕合成及ZMP方程的仿人机器人三维步态规划

介绍了一种仿人机器人的新型步态规划方法。将仿人机器人前向步态简化为七连杆模型,侧向步态简化为五连杆模型;然后在Z坐标相等的情况下合成三维步态;最后通过ZMP方程来检验和仿真,并结合实际系统及其运行状况进行分析,验证了所提出规划方法的有效性。     

基于X86平台和RSI的工业机器人步态自动控制系统设计

工业环境中的任务和工作场景是动态变化的,机器人需要能够根据环境的变化调整步态,以满足新的任务需求。为此,设计基于X86平台和RSI的工业机器人步态自动控制系统。以复杂指令集计算机为基础的X86架构设计机器人控制器主板,使系统具有高集成度和扩展性。利用超声波传感器和红外线传感器获取步态自动控制传感信号。使用基于AS5040型高精密非接触磁性转动编码器的步态关节控制器,通过总线扩展,定位关节运动方向。分析机械臂前后摆动步态规划轨迹,控制髋关节。使用RSI应用程序包控制点位运动,实现步态自动控制。实验结果表明,设计系统的膝关节x方向与实际轨迹只存在最大为20mm的误差,y方向与实际轨迹一致;髋关节x方向与实际轨迹只存在最大为20mm的误差,y方向与实际轨迹只存在最大为15mm的误差,能够提高控制精度,控制效果较好。     

基于粗神经网络的仿人智能机器人的语音融合算法研究

将粗集合理论与神经网络相结合，提出一种基于粗神经网络的新的信息融合方法，用于仿人智能机器人的语音融合。该方法不仅可以接受定量输入，而且可以接受定性输入，即输入是一个范围，或在观测时间内输入是变化的。由于粗神经网络的误差传递函数不可微，所以采用遗传算法来训练粗神经网络。仿真实验结果表明，基于粗神经网络的信息融合方法有效地提高了语音的识别率。     

Toward sociable robots

This paper explores the topic of social robots—the class of robots that people anthropomorphize in order to interact with them. From the diverse and growing number of applications for such robots, a few distinct modes of interaction are beginning to emerge. We distinguish four such classes: socially evocative, social interface, socially receptive, and sociable. For the remainder of the paper, we explore a few key features of sociable robots that distinguish them from the others. We use the vocal turn-taking behavior of our robot, Kismet, as a case study to highlight these points.     

仿人机器人两步步态规划算法研究

为了进一步提高仿人机器人步行时的稳定性,通过对人类步行的研究,并从两足步行机的两步步态规划方法中得到启发,对仿人机器人步行也进行类似的两步规划,但由于结构上的不同,仿人机器人中采用加入上肢运动补偿的方式实现平衡.规划仿人机器人的运动姿态,然后根据零力矩点必须落在稳定区域的原则,对仿人机器人的上肢运动轨迹进行求解,通过这种加入上肢补偿的两步规划来实现仿人机器人的稳定步行.从实验结果可以看出,采用这种两足步态规划方法,在仿人机器人两足步行时,可以使机器人上肢与下肢协调运动,从而提高了步行的稳定性.     

Evolutionary design of Sugeno-type fuzzy systems for modelling humanoid robots

An evolutionary design of Sugeno-type fuzzy systems for modelling humanoid robots is presented in this article, and issues related to the determination of the antecedent and consequent structures of the fuzzy model are addressed. In the design of the fuzzy model, determination of the type, the number of membership functions assigned to the input variables, the types of consequent equations for the fuzzy rules, the optimal number of input variables, and the dominant input variables among the input candidates are carried out using evolutionary algorithms. Using these algorithms, proper structures are evolved for the antecedent and the consequent of the Sugeno-type fuzzy model. Simulations are performed to show the effectiveness of the developed method when applied to a humanoid robot system with strong nonlinearities that have 10 input candidates.     

基于体感的仿人机器人步态学习与控制

针对现有理想化步态动力学模型规划方法复杂、人为指定参数过多、计算量大的问题,提出一种基于体感数据学习人体步态的仿人机器人步态生成方法。首先,用体感设备收集人体骨骼信息,基于最小二乘拟合方法建立人体关节局部坐标系;其次,搭建人体与机器人映射的运动学模型,根据两者间主要关节映射关系,生成机器人关节转角轨迹,实现机器人对人类行走姿态的学习;然后,基于零力矩点(ZMP)稳定性原则,对机器人脚踝关节转角采用梯度下降算法进行优化控制;最后,在步态稳定性分析上,提出使用安全系数来评价机器人行走稳定程度的方法。实验结果表明,步行过程中安全系数保持在0~0.85,期望为0.4825,ZMP接近于稳定区域中心,机器人实现了仿人姿态的稳定行走,证明了该方法的有效性。     

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.