In this paper, we validate the extended neglect tolerance model for estimation of human robot team performance in relation to robot autonomy and compare its results with the traditionally adopted neglect tolerance model which assumes zero false alarms in human robot interactions. Extended neglect tolerance model estimates robot performance in human robot teams, where the human operator switches control between robots sequentially, based on acceptable performance levels, taking into account any false alarms and their respective demands. Experiments were performed with Robo-Erectus@Home, a service robot across tele-operation, and semi-autonomous modes of autonomy where a human operator controlled the robot to perform a walking assistant task. Measured false alarm demands and robot performances were largely consistent with the extended neglect tolerance model predictions for both autonomy modes. We also compared traditionally adopted neglect tolerance and extended neglect tolerance model for the same experimental design. The results showed that the latter offers better estimates of robot performance and attention demands, due to the inclusion of false alarms into the model.

This paper focuses on the creation of a realistic simulation of a humanoid robot in a virtual environment. This model will help researchers to implement and study different behaviours of the humanoid robot Robo-Erectus without its physical presence. The dynamics and the appearance of the robot and the other objects within the simulator are faithfully reproduced in the virtual environment. Moreover, the virtual robot can be controlled with the same program controlling the real robot. The simulator has been used successfully to generate and test behaviours for the robot to prepare for the RoboCup 2008.

As rehabilitation robots are increasingly serving to improve the quality of life for physically disabled people in clinical environments, the concept of emotional expressiveness in robots becomes increasingly important. The human perception of robot's emotional expressions plays a crucial role in human robot interaction. Virtual expression systems outperform hardware systems in realizing human like expressions due the limitations in hardware actuators and advances in animation tools. This paper evaluates the human perception of robot's emotional expressions with two different virtual emotional expression systems: one where the robot exhibits emotions through icon faced expressions and in other the robot exhibits emotions through human faced expressions in clinical environment. A rehabilitation HRI research robot Robbie is introduced and the results of the comparative study on human perception of robotpsilas emotional expressions with two different systems are discussed.

During last years, robotic research has explored Human-Robot interactions especially for the challenge of the robot companion. This type of robot would be equipped with perception, motion, and manipulation among other skills, to be help humans in daily tasks. Guidance is one of the tasks that the robot companion must perform. This paper describes Robbie, a wheeled robot companion uses for guiding missions. The Robbie combines visual clues, voice, distance and PC input to detect humans and features in the environment. To complete its task Robbie could receive extra information from smart beacons located in the building. The paper also explores two modalities to the guiding missions. Finally, experiments are presented in order to highlight the relevance of the approach.

In the field of human-computer interaction, natural goals, operators, methods, and selection rules language (NGOMSL) model is one of the most popular method for modelling knowledge and cognitive processes for rapid usability evaluation. NGOMSL model is a description of the knowledge that a user must possess to operate the system represented as elementary actions for effective usability evaluations. In the last few years, mobile robots have been exhibiting a stronger presence in the commercial markets and very little work has been done with NGOMSL modelling for usability evaluations in human-robot interaction discipline. This paper focuses on applying NGOMSL modelling for usability evaluation of human-humanoid robot interaction in soccer domain. Usability evaluations were performed and adequate results were obtained. Evaluated interaction design was adopted by our Robo-Erectus Junior version of humanoid robots in the RoboCup 2007 humanoid soccer league.

A new estimation of distribution algorithm (EDA) with spline kernel function (EDA_S) is proposed to optimize biped gait for a nine-link humanoid robot. Gait synthesis of the biped locomotion is firstly formulated as a multi-constraint optimization problem with consideration of two objectives, including zero-moment point (ZMP) for dynamically stable locomotion and driving torque for energy efficiency. The parameters to be optimized are joint coordinates at transition poses between three successive phases. Rather than searching in joint angle permutation space directly, the proposed method approximates the probability distribution by Catmull-Rom (CR) cubic spline function and updates them with gradient descent learning strategy. The effectiveness of EDA_S for biped gait optimization has been successfully tested on the simulated model of a humanoid soccer robot. It is shown that the flexible kernel with the updating rule is able to remarkably accelerate the learning speed with comparison to the traditional EDA

A new biped gait generation and optimization method is proposed in the frame of estimation of distribution algorithms (EDAs) with Q-learning method. By formulating the biped gait synthesis as a constrained multi-objective optimization problem, a dynamically stable and low energy cost biped gait is generated by EDAs with Q-learning (EDA_Q), which estimate probability distributions derived from the objective function to be optimized to generate searching points in the highly-coupled and high dimensional working space of biped robots. To get the preferable permutation of the interrelated parameters, Q-learning is combined to build and modify the probability models in EDA autonomously. By making use of the global optimization capability of EDA, the proposed EDA_Q can also solve the local minima problem in traditional Q-learning. On the other hand, with the learning agent, EDA_Q can evaluate the probability distribution model regularly without pre-designed structure and updating rule. The simulation results show that faster and more accurate searching can be achieved to generate preferable biped gait. The gait has been successfully used to drive a soccer-playing humanoid robot called Robo-Erectus which is one of the foremost leading soccer-playing humanoid robots in the RoboCup Humanoid League

In this article, we look at the excellent effect of vertical force as regards the stabilization of the inverted pendulum (IP) and demonstrate how the fuzzy control design methodology can be used to construct a hybrid fuzzy control system that incorporates PD control into a Takagi–Sugeno fuzzy control structure for stabilizing the IP via a vertical force. By gaining an intuitive understanding of the dynamics of the IP, the IP state space is fuzzily divided into six regions. In each region, a PD controller is designed to satisfy the stability conditions obtained by Lyapunov's direct and indirect methods. It shows that the proposed hybrid fuzzy control scheme provides a more flexible and intuitive way to stabilize the IP via a vertical force. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 195–211, 2005.

A novel robust adaptive fuzzy control (RAFC) algorithm for the permanent magnet (PM) synchronous servomotor drives with uncertain nonlinearities and time-varying uncertainties is presented in this article. Takagi–Sugeno-type fuzzy logic systems are used to approximate uncertain functions. The RAFC algorithm is designed by use of the input-to-state stability (ISS) approach and small gain theorem. The closed-loop system is proven to be semiglobally uniformly ultimately bounded. In addition, the possible controller singularity problem in some of the existing adaptive control schemes met with feedback linearization techniques can be removed and the adaptive mechanism with only one learning parameterization can be achieved. The proposed methodology is applied to design the position control of the PM synchronous servomotor drives. Simulation results show the effectiveness of the proposed control scheme. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 153–171, 2005.

A novel adaptive fuzzy controller with H/sub /spl infin// performance is proposed for a wide class of strict-feedback canonical nonlinear systems. The systems may possess a class of uncertainties referred to as unstructured uncertain functions, which are not linearly parameterized and have no prior knowledge of the bound. The Takagi-Sugeno-type fuzzy logic systems are used to approximate the uncertainties and a systematic design procedure is developed for synthesis of adaptive fuzzy control with H/sub /spl infin// performance, which combines the backstepping technique and generalized small gain approach. The method preserves the three advantages, those are, the semiglobal uniform ultimate bound of adaptive control in the presence of unstructured uncertainties can be guaranteed, the adaptive mechanism with only one learning parameter is obtained and the possible controller singularity problem in some of the existing adaptive control schemes with feedback linearization techniques can be removed. Performance and limitations of proposed method are discussed and illustrated with simulation results.

This paper presents a third-order spline interpolation based trajectory planning method which is aiming to achieve smooth biped swing leg trajectory by reducing the instant velocity change which occurs at the time of collision of the biped swing leg with the ground. We first characterize the bipedal walking cycle and point out some major issues that need to be addressed to plan a continuous swing leg trajectory by using the concept of the spline interpolation and zero moment points (ZMP). We demonstrate that the impact effects can be avoided at the time of the swing foot's heel touching with the ground. The proposed biped trajectory planning method has been tested on our soccer-playing humanoid robot, Robo-Erectus, which got Second Place at the 2002 RoboCup Humanoid Walk competition.

A new fuzzy adaptive robust control algorithm is presented for a class of uncertain nonlinear systems by use of the small gain approach and dissipative system theory. In the algorithm, Takagi-Sugeno type fuzzy logic systems are employed to approximate unknown functions in the systems and the adaptive mechanism with minimal learning parameterizations can be achieved. An example illustrating the method described is included for ship roll stabilization by a fin control system. We confirm that the designed system guarantees the performance of global asymptotic stability.

The stabilization of a class of uncertain nonlinear systems within the system complication formulation function and unknown control gain parameters is investigated. A fuzzy system is employed to approximate the system complication formulation function, then the fuzzy system is used as the upper bound of uncertainty, and a variable structure fuzzy adaptive robust control that can evaluate the bound parameter of uncertainty and input control gain online is presented. An example demonstrating the method described is included for ship roll stabilization using fin control system. It is shown that the designed system guarantees the performance of robustness with respect to the perturbations and uncertainties.

A novel approach to design a fuzzy controller using fuzzy Lyapunov synthesis and constrained fuzzy arithmetic operations in the frame of computing with words is presented. We demonstrate that a set of fuzzy control rules with singleton consequent can be derived systematically, rather than heuristically from perception-based information using the constrained fuzzy arithmetic. The stability of the devised singleton fuzzy controller can be guaranteed by means of fuzzy Lyapunov synthesis that gives a linguistic description on the plant and the control objective. Furthermore, we also show that some deficiencies of the standard fuzzy arithmetic in fuzzy controller design can be overcome by the constrained fuzzy arithmetic which takes all available information into consideration. The performance and applicability of the proposed method are illustrated through the practical implementation of fuzzy control of an autonomous pole-balancing mobile robot.

Sensor-based operation of autonomous robots in unstructured environments has been proved to be an extremely challenging problem. However, humans seem to cope very well with uncertain and unpredictable environments, often relying on their perceptions. Furthermore, humans can also utilize the perceptions to guide their learning on those parts of the perception-action space that are actually relevant for the task. To make use of perceptions to assist robot learning and control, by using computational theory of perceptions (CTP), a linguistic version of Lyapunov synthesis working with fuzzy arithmetic operations in the domain of computing with words (CW) is proposed to derive a set of stable fuzzy control rules from the perception-based information. Then the fuzzy rules are incorporated in a fuzzy reinforcement learning (FRL) agent to accelerate its learning. The experimental and simulation results show that it is possible for a robot to start with the perception-based information and then refine its behavior through further learning.

Proposes a fuzzy reinforcement learning algorithm for biped gait synthesis. It is based on a modified GARIC (generalized approximate reasoning for intelligent control) architecture that can accept fuzzy evaluative feedback rather than a numerical one. The proposed gait synthesizer forms the initial gait from intuitive balancing knowledge, and it is then trained by the fuzzy reinforcement learning algorithm that uses a fuzzy critical signal to evaluate the degree of success for the biped dynamic walking by means of the zero moment point. The performance and applicability of the proposed method are illustrated through biped simulation.

A prescribed synergy method-based hybrid intelligent gait synthesis scheme is proposed for the problem of biped dynamic balance. It only synthesizes trunk trajectories by the hybrid intelligent system (HIS), while all the other joints' trajectories are prescribed. Based on HIS, the data fusion theory and the knowledge available, we propose two gait synthesis schemes, one is neurofuzzy-based gait synthesis, and the other is fuzzy rule extraction-based gait synthesis. The proposed gait synthesizers can integrate both linguistic rules obtained from human intuitive balancing knowledge and biomechanical studies and numerical data received from biped walking experiments for improving the biped dynamic walking performance.

For complex engineering systems, two kinds of information are available; numerical data received from sensor measurement, and linguistic rules obtained from human operators and domain experts. However, some of information obtained in this manner are hybrid, that is, their components are not homogeneous but a blend of direct and indirect, numerical and linguistic information. In order to integrate the above linguistic and numerical information for hybrid intelligent control, which employ an integration of fuzzy logic, neural networks, genetic algorithms and related intelligent control methodologies, based on inverse learning and some simple and intuitive information combination operators, we propose two integration schemes. One is neurofuzzy based integration, and another is fuzzy rules extraction based integration. The effectiveness of the proposed methods are verified through hybrid intelligent control of a biped walking robot.