International Journal of Humanoid Robotics

This paper deals with the design and the evaluation of human-like robot movements. Three criteria were proposed and evaluated regarding their impact on the human-likeness of the robot movements: The inertia of the base, the inertia of the end-effector and the velocity profile. A specific tool was designed to generate different levels of anthropomorphism according to these three parameters. An industrial use case was designed to compare several robot movements. This use case was implemented with a virtual robot arm in a virtual environment, using virtual reality. A user study was conducted to determine what were the important criteria in the perception of human-like robot movements and what were their correlations with other notions such as safety and preference. The results showed that inertia on the end-effector was of most importance for a movement to be perceived as human-like and nonaggressive, and that those characteristics helped the users feel safer, less stressed and more willing to work with the robot.

The aim of this work was to determine how an object of given shape should be grasped to maximize the grasping capacity of the human hand. To do that the model searches the optimal grip points on the object with the aim of maximizing the weight of the object lifted without slipping. The model solves both the equilibrium of the grasped object and the biomechanical constraints of the human hand, such as the stress limit of each muscle. To give some examples, grasps of three-dimensional (3D) objects of different shape and size were optimized. The results of the simulations done also allowed the identification of the parameters that further influence human grasping. Moreover, trials were done to prove the results given by the computational model.

This paper presents a novel online walking control that replans the gait pattern based on our proposed foot placement control using the actual center of mass (COM) state feedback. The analytic solution of foot placement is formulated based on the linear inverted pendulum model (LIPM) to recover the walking velocity and to reject external disturbances. The foot placement control predicts where and when to place the foothold in order to modulate the gait given the desired gait parameters. The zero moment point (ZMP) references and foot trajectories are replanned online according to the updated foothold prediction. Hence, only desired gait parameters are required instead of predefined or fixed gait patterns. Given the new ZMP references, the extended prediction self-adaptive control (EPSAC) approach to model predictive control (MPC) is used to minimize the ZMP response errors considering the acceleration constraints. Furthermore, to ensure smooth gait transitions, the conditions for the gait initiation and termination are also presented. The effectiveness of the presented gait control is validated by extensive disturbance rejection studies ranging from single mass simulation to a full body humanoid robot COMAN in a physics based simulator. The versatility is demonstrated by the control of reactive gaits as well as reactive stepping from standing posture. We present the data of the applied disturbances, the prediction of sagittal/lateral foot placements, the replanning of the foot/ZMP trajectories, and the COM responses.

Intelligent control of multi-agent autonomous humanoid robots is a very complex problem, especially in the RoboCup domain. This is due to the dynamics of the environment and the complexity of behaviors that should be executed in real time. Moreover, the overall complexity increases since another mechanism for coordinating the robot’s behaviors should be involved. Throughout the past years, acceptable results have been obtained using different approaches to solve the behavior control problem (decision trees, fuzzy techniques, support vector machines, reinforcement learning, etc.). As case-based reasoning (CBR) is tightly related to the way humans reason, researches are now concentrated on finding the most relevant solutions that could handle behavior control problems of humanoid soccer robots using CBR techniques. This paper proposes an extended algorithm of a more complex architecture to control more complex soccer behaviors such as dribbling and goal scoring applied to multi-robot scenarios between attacker and goalie. The decomposition of features into a hierarchy of levels has led to reduced complexity of the overall behavior execution in real time. However, the average retrieval accuracy and the average performance accuracy were relatively low (70.3% and 77%, respectively). We intend to combine neural networks with CBR to learn adaptation rules for reducing the complexity of hand-coded rules and improving the overall controller performance.

Applying principal component analysis (PCA) to find synergy signal for specific motion of Robot is a standard method. However, implementation of PCA gives synergy solely on quantitative basis. The algorithms proposed in this paper advocates the enhancement of qualitative measure of PCA to locate well-coordinated synergy signals. The two main control strategies of central nervous system (CNS) are taken into account for enhancement of algorithms. First one is the CNS strategy of separate synergy generation for individual limbs and second is the trajectory generation of complex movement using via-points. The proposed algorithms find the synergy without loss of generality of implementation. Humanoid robot NAO is used as a robotic platform to test the result of the algorithm. The synergy for a group of motors is calculated by implementing the algorithm on motors position sensor data of the robot corresponding to three motion pattern 1. Knee bend sitting–standing, 2. Sitting–standing on chair, and 3. Walking. The improvement in result is statistically measured by calculating error between original and reconstructed signal for proposed algorithms and applying Z-test tested on error signals. Another statistical measure of improvement is treated by calculating ‘Goodness of Fit’ for original and reconstructed signal.

This paper reports a method that fuses multiple sensor measurements for location estimation of an underwater robot. Synchronous and asynchronous (AS) implementation of the method are also proposed. Extended Kalman filter (EKF) is used to fuse four types of measurements: linear velocity by Doppler velocity log (DVL), angular velocity by gyroscope, ranges to acoustic beacons, and depth. The EKF approach is implemented in three ways to deal with asynchrony in measurements in correction step. The three implementation methods are synchronous collective (SC), synchronous individual (SI), and AS application. These methods are verified and compared through simulation and test tank experiments. The test reveals that the application methods need to be selected depending on the measurement properties: dependency between the measurements and degree of asynchrony. The distinctive features proposed in this study are three application methods together with derivation of an EKF approach to sensor fusion for underwater navigation.

Distant speaker recognition (DSR) system assumes the microphones are far away from the speaker’s mouth. Also, the position of microphones can vary. Furthermore, various challenges and limitation in terms of coloration, ambient noise and reverberation can bring some difficulties for recognition of the speaker. Although, applying speech enhancement techniques can attenuate speech distortion components, it may remove speaker-specific information and increase the processing time in real-time application. Currently, many efforts have been investigated to develop DSR for commercial viable systems. In this paper, state-of-the-art techniques in DSR such as robust feature extraction, feature normalization, robust speaker modeling, model compensation, dereverberation and score normalization are discussed to overcome the speech degradation components i.e., reverberation and ambient noise. Performance results on DSR show that whenever speaker to microphone distant increases, recognition rates decreases and equal error rate (EER) increases. Finally, the paper concludes that applying robust feature and robust speaker model varying lesser with distant, can improve the DSR performance.

This paper describes an algorithm that enables a humanoid robot to perform an impulsive pedipulation task on a spherical object in the environment; that is, by using its feet to exert an impulsive force capable of driving the object to a 3D goal position while achieving certain motion characteristics. This is done by planning a suitable motion for the legs of the humanoid, capable to exert the required impact conditions on the spherical object while maintaining the dynamic stability of the robot. As an example of this algorithm implementation we consider the free kick in soccer and take it as a case study. Finally, we provide some simulation and experimental results that intend to show the validity of this algorithm.