Synthesized articulated behavior using space-temporal on-line principal component analysis

This paper presents a new framework to synthesize humanoid behavior by learning and imitating the behavior of an articulated body using motion capture. The video-based motion capturing method has been developed mainly for analysis of human movement, but is very rarely used to teach or imitate the behavior of an articulated body to a virtual agent in an on-line manner. Using our proposed applications, new behaviors of one agent can be simultaneously analyzed and used to train or imitate another with a novel visual learning methodology. In the on-line learning phase, we propose a new way of synthesizing humanoid behavior based on on-line learning of principal component analysis (PCA) bases of the behavior. Although there are many existing studies which utilize PCA for object/behavior representation, this paper introduces two criteria to determine if the dimension of the subspace is to be expanded or not and applies a Fisher criterion to synthesize new behaviors. The proposed methodology is well-matched to both behavioral training and synthesis, since it is automatically carried out as an on-line long-term learning of humanoid behaviors without the overhead of an expanding learning space. The final outcome of these methodologies is to synthesize multiple humanoid behaviors for the generation of arbitrary behaviors. The experimental results using a humanoid figure and a virtual robot demonstrate the feasibility and merits of this method.     

Codevelopmental learning between human and humanoid robot using a dynamic neural-network model.

This paper examines characteristics of interactive learning between human tutors and a robot having a dynamic neural-network model, which is inspired by human parietal cortex functions. A humanoid robot, with a recurrent neural network that has a hierarchical structure, learns to manipulate objects. Robots learn tasks in repeated self-trials with the assistance of human interaction, which provides physical guidance until the tasks are mastered and learning is consolidated within the neural networks. Experimental results and the analyses showed the following: 1) codevelopmental shaping of task behaviors stems from interactions between the robot and a tutor; 2) dynamic structures for articulating and sequencing of behavior primitives are self-organized in the hierarchically organized network; and 3) such structures can afford both generalization and context dependency in generating skilled behaviors.     

Interaction rule learning with a human partner based on an imitation faculty with a simple visuo-motor mapping

Imitation has been receiving increasing attention from the viewpoint of not simply generating new motions but also the emergence of communication. This paper proposes a system for a humanoid who obtains new motions through learning the interaction rules with a human partner based on the assumption of the mirror system. First, a humanoid learns the correspondence between its own posture and the partner’s one on the ISOMAPs supposing that a human partner imitates the robot motions. Based on this correspondence, the robot can easily transfer the observed partner’s gestures to its own motion. Then, this correspondence enables a robot to acquire the new motion primitive for the interaction. Furthermore, through this process, the humanoid learns an interaction rule that control gesture turn-taking. The preliminary results and future issues are given.     

仿人机器人复杂动作设计中人体运动数据提取及分析方法

提出了仿人机器人复杂动作设计中人体运动数据提取及分析方法. 首先, 通过运动捕捉系统获取人体运动数据, 并采用运动重定向技术, 输出人--机简化模型的数据; 然后, 对运动数据进行分析和运动学解算, 给出基于人体运动数据的仿人机器人逆运动学求解方法, 得到仿人机器人模型的关节角数据; 再经过运动学约束和稳定性调节后, 生成能够应用于仿人机器人的运动轨迹. 最终, 通过在仿人机器人BHR-2上进行刀术实验验证了该方法的有效性.     

Effective input order of dynamics learning tree

In this paper, we discuss about the learning performance of dynamics learning tree (DLT) while mainly focusing on the implementation on robot arms. We propose an input-order-designing method for DLT. DLT has been applied to the modeling of boat, vehicle, and humanoid robot. However, the relationship between the input order and the performance of DLT has not been investigated. In the proposed method, a developer is able to design an effective input order intuitively. The proposed method was validated in the model learning tasks on a simulated robot manipulator, a real robot manipulator, and a simulated vehicle. The first/second manipulator was equipped with flexible arm/finger joints that made uncertainty around the trajectories of manipulated objects. In all of the cases, the proposed method improved the performance of DLT.     

Adaptive visual gesture recognition for human–robot interaction using a knowledge-based software platform

In human–human communication we can adapt or learn new gestures or new users using intelligence and contextual information. Achieving natural gesture-based interaction between humans and robots, the system should be adaptable to new users, gestures and robot behaviors. This paper presents an adaptive visual gesture recognition method for human–robot interaction using a knowledge-based software platform. The system is capable of recognizing users, static gestures comprised of the face and hand poses, and dynamic gestures of face in motion. The system learns new users, poses using multi-cluster approach, and combines computer vision and knowledge-based approaches in order to adapt to new users, gestures and robot behaviors. In the proposed method, a frame-based knowledge model is defined for the person-centric gesture interpretation and human–robot interaction. It is implemented using the frame-based Software Platform for Agent and Knowledge Management (SPAK). The effectiveness of this method has been demonstrated by an experimental human–robot interaction system using a humanoid robot ‘Robovie’.     

快速连续反应-避障作业环境下的七自由度灵巧臂轨迹规划

人类经长期学习训练后能对高速物体 (如棒球、乒乓球等)具有快速连续反应作业的运动技能, 从深层次上揭示是由于人体在其训练过程中不断学习优选了相应手臂的动作轨迹, 并储存了丰富的经验和知识. 受人体手臂动作此行为机制启发, 本文提出一种 7-DOF灵巧臂快速连续反应-避障作业的轨迹规划方法. 该方法将灵巧臂对高速物体目标作业的轨迹规划问题转化为动作轨迹参数化优选问题, 考虑作业过程中灵巧臂的机构物理约束和障碍约束条件, 以灵巧臂目标可作业度指标构建适应度函数, 采用粒子群优化 (Particle swarm optimization, PSO)方法优选作业轨迹中的冗余参数; 在此基础上 利用灵巧臂动作轨迹参数化优选方法构建相应作业环境下的知识数据库, 实现灵巧臂对高速物体目标的快速连续反应作业. 以仿人机器人乒乓球对弈作业为例, 将该方法应用于 7-DOF灵巧臂乒乓球作业的轨迹规划中. 数值实验及实际对弈试验结果表明, 该方法不仅能使灵巧臂所规划的轨迹 满足灵巧臂机构物理约束与障碍约束条件, 同时能实现灵巧臂对乒乓球体的快速连续反应作业, 验证了该方法的有效性.     

基于运动相似性的仿人机器人双足步行研究

提出了一种基于人体步行运动相似性的仿人机器人双足步行动作设计方法．改进了人体步行轨迹的参 数获取与相似性匹配系统,扩展了相似性函数的适用范围．根据仿人机器人的机械连杆特点定义了步行运动周期中 的关键姿势与子相变换,建立了运动学约束方程,并对行走中出现的动态稳定性问题进行了约束．仿真和实体机器 人实验验证了该方法的有效性．     

CMAC在仿人机器人逆运动学计算中的应用

本文采用关节角位移和末端位姿误差作为小脑模型神经网络(CMAC)的输入,根据仿人机器人的正运动学模型来调整CMAC的权值,使网络最终逼近仿人机器人的逆模型,从而得到末端位姿到各个关节角的映射关系,避免了传统解析方法面临的计算量大、解不唯一的问题。MATLAB仿真结果表明,利用CMAC对仿人机器人的逆运动学问题求解,可以保证机器人位姿较好地跟踪给定的参考轨迹,说明CMAC能够逼近仿人机器人的逆运动学模型。     

不同个性的情感机器人表情研究

在情感机器人研究中,不同个性的面部表情是情感机器人增强真实感的重要基础。为实现情感机器人更加丰富细腻的表情,将人类的个性特征引入情感机器人,分析个性理论和情感模型理论,得知不同个性机器人的情感强度。结合面部动作编码系统中面部表情与机器人控制点之间的映射关系,得到情感机器人不同个性的基本表情实现方法。利用Solidworks建立情感机器人脸部模型,在ANSYS工程软件中将SHFR-Ⅲ情感机器人脸部模型设置为弹性体,通过有限元仿真计算方法,对表情的有限元仿真方法进行了探究,得到实现SHFR-Ⅲ不同个性基本表情的控制区域载荷大小和仿真结果。最后,根据仿真结果,进行SHFR-Ⅲ情感机器人不同个性的表情动作实验。实验结果表明,有限元表情仿真可以指导SHFR-Ⅲ情感机器人实现近似人类的不同个性的基本面部表情。     

A syntactic approach to robot imitation learning using probabilistic activity grammars

This paper describes a syntactic approach to imitation learning that captures important task structures in the form of probabilistic activity grammars from a reasonably small number of samples under noisy conditions. We show that these learned grammars can be recursively applied to help recognize unforeseen, more complicated tasks that share underlying structures. The grammars enforce an observation to be consistent with the previously observed behaviors which can correct unexpected, out-of-context actions due to errors of the observer and/or demonstrator. To achieve this goal, our method (1) actively searches for frequently occurring action symbols that are subsets of input samples to uncover the hierarchical structure of the demonstration, and (2) considers the uncertainties of input symbols due to imperfect low-level detectors.We evaluate the proposed method using both synthetic data and two sets of real-world humanoid robot experiments. In our Towers of Hanoi experiment, the robot learns the important constraints of the puzzle after observing demonstrators solving it. In our Dance Imitation experiment, the robot learns 3 types of dances from human demonstrations. The results suggest that under reasonable amount of noise, our method is capable of capturing the reusable task structures and generalizing them to cope with recursions.     

Learning to Acquire Whole-Body Humanoid Center of Mass Movements to Achieve Dynamic Tasks

This paper presents a novel approach for acquiring dynamic whole-body movements on humanoid robots focused on learning a control policy for the center of mass (CoM). In our approach, we combine both a model-based CoM controller and a model-free reinforcement learning (RL) method to acquire dynamic whole-body movements in humanoid robots. (i) To cope with high dimensionality, we use a model-based CoM controller as a basic controller that derives joint angular velocities from the desired CoM velocity. The balancing issue can also be considered in the controller. (ii) The RL method is used to acquire a controller that generates the desired CoM velocity based on the current state. To demonstrate the effectiveness of our approach, we apply it to a ball-punching task on a simulated humanoid robot model. The acquired whole-body punching movement was also demonstrated on Fujitsu's Hoap-2 humanoid robot.     

Reinforcement learning of humanoid rhythmic walking parameters based on visual information

This paper presents a method for learning the parameters of rhythmic walking to generate purposive humanoid motions. The controller consists of the two layers: rhythmic walking is realized by the lower layer, which adjusts the speed of the phase on the desired trajectory depending on sensory information, and the upper layer learns (i) the feasible parameter sets that enable stable walking, (ii) the causal relationship between the walking parameters to be given to the lower-layer controller and the change in the sensory information and (iii) the feasible rhythmic walking parameters by reinforcement learning so that a robot can reach the goal based on visual information. The experimental results show that a real humanoid learns to reach the ball and to shoot it into the goal in the context of the RoboCup soccer competition, and the further issues are discussed.     

Computational intelligence for structured learning of a partner robot based on imitation

Imitation is a powerful tool for gestural interaction between children and for teaching behaviors to children by parent. Furthermore, others’ action can be a hint for acquiring a new behavior that might not be the same as the original action. The importance is how to map or represent others’ action into new one in the internal state space. A good instructor can teach an action to a learner by understanding the mapping or imitating method of the learner. This indicates a robot also can acquire various behaviors using interactive learning based on imitation. This paper proposes structured learning for a partner robot based on the interactive teaching mechanism. The proposed method is composed of a spiking neural network, self-organizing map, steady-state genetic algorithm, and softmax action selection. Furthermore, we discuss the interactive learning of a human and a partner robot based on the proposed method through experiment results.     

Learning proactive behavior for interactive social robots

Learning human–robot interaction logic from example interaction data has the potential to leverage “big data” to reduce the effort and time spent on designing interaction logic or crafting interaction content. Previous work has demonstrated techniques by which a robot can learn motion and speech behaviors from non-annotated human–human interaction data, but these techniques only enable a robot to respond to human-initiated inputs, and do not enable the robot to proactively initiate interaction. In this work, we propose a method for learning both human-initiated and robot-initiated behavior for a social robot from human–human example interactions, which we demonstrate for a shopkeeper interacting with a customer in a camera shop scenario. This was achieved by extending an existing technique by (1) introducing a concept of a customer yield action, (2) incorporating interaction history, represented by sequences of discretized actions, as inputs for training and generating robot behavior, and (3) using an “attention mechanism” in our learning system for training robot behaviors, that learns which parts of the interaction history are more important for generating robot behaviors. The proposed method trains a robot to generate multimodal actions, consisting of speech and locomotion behaviors. We compared this study with the previous technique in two ways. Cross-validation on the training data showed higher social appropriateness of predicted behaviors using the proposed technique, and a user study of live interaction with a robot showed that participants perceived the proposed technique to produce behaviors that were more proactive, socially-appropriate, and better in overall quality.     

The Effect of a Humanoid Robot’s Emotional Behaviors on Users’ Emotional Responses: Evidence from Pupillometry and Electroencephalography Measures

ABSTRACT

The design of humanoid robots’ emotional behaviors has attracted many scholars’ attention. However, users’ emotional responses to humanoid robots’ emotional behaviors which differ from robots’ traditional behaviors remain well understood. This study aims to investigate the effect of a humanoid robot’s emotional behaviors on users’ emotional responses using subjective reporting, pupillometry, and electroencephalography. Five categories of the humanoid robot’s emotional behaviors expressing joy, fear, neutral, sadness, or anger were designed, selected, and presented to users. Results show that users have a significant positive emotional response to the humanoid robot’s joy behavior and a significant negative emotional response to the humanoid robot’s sadness behavior, indicated by the metrics of reported valence and arousal, pupil diameter, frontal middle relative theta power, and frontal alpha asymmetry score. The results suggest that humanoid robot’s emotional behaviors can evocate users’ significant emotional response. The evocation might relate to the recognition of these emotional behaviors. In addition, the study provides a multimodal physiological method of evaluating users’ emotional responses to the humanoid robot’s emotional behaviors.     

Process control and machine learning: rule-based incrementalcontrol

In this paper, we discuss a rule-based incremental control program which has been used for controlling a laser cutting robot and in simulation for driving a car on a track, for a car parking manoeuvre, or for parking a truck with one trailer. The core of the paper concerns a learning program, Candide, which learns to control a process without a priori knowledge about the process, by observing random initial evolutions of the process and acquiring a qualitative model. Monotonous or derivative relationships between inputs and outputs are recognized, and then a rule-based incremental controller Is deduced from this model     

Autonomous online generation of a motor representation of the workspace for intelligent whole-body reaching

We describe a learning strategy that allows a humanoid robot to autonomously build a representation of its workspace: we call this representation Reachable Space Map. Interestingly, the robot can use this map to: (i) estimate the Reachability of a visually detected object (i.e. judge whether the object can be reached for, and how well, according to some performance metric) and (ii) modify its body posture or its position with respect to the object to achieve better reaching. The robot learns this map incrementally during the execution of goal-directed reaching movements; reaching control employs kinematic models that are updated online as well. Our solution is innovative with respect to previous works in three aspects: the robot workspace is described using a gaze-centered motor representation, the map is built incrementally during the execution of goal-directed actions, learning is autonomous and online. We implement our strategy on the 48-DOFs humanoid robot Kobian and we show how the Reachable Space Map can support intelligent reaching behavior with the whole-body (i.e. head, eyes, arm, waist, legs).     

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。     

Self-modeling in humanoid soccer robots

In this paper we discuss the applicability, potential benefits, open problems and expected contributions that an emerging set of self-modeling techniques might bring on the development of humanoid soccer robots. The idea is that robots might continuously generate, validate and adjust physical models of their sensorimotor interaction with the world. These models are exploited for adapting behavior in simulation, enhancing the learning skills of a robot with the regular transference of controllers developed in simulation to reality. Moreover, these simulations can be used to aid the execution of complex sensorimotor tasks, speed up adaptation and enhance task planning. We present experiments on the generation of behaviors for humanoid soccer robots using the Back-to-Reality algorithm. General motivations are presented, alternative algorithms are discussed and, most importantly, directions of research are proposed.