How far away is “artificial man”

The authors claim that a careful examination of robotics science and technology from its origins in the 1950s to its current status reveals that such progress, albeit very important, profitable, and with a strong impact on society, was basically the “side activities” to the ever-existing and continuous desire of mankind to build and realize humanoid robots, artificial men equipped uith proper intelligence capable of operating autonomously, thus replacing trained individuals for dexterous jobs. They consider such a humanoid robot through the realistic tasks/jobs it will most probably do. It is postulated that this humanoid robot be considered as a personal helper (a home robot or personal robot). Given the present level of technology, the question is posed: are we ready to move towards personal robotics, and what might be the first step? A possible answer to this question is given through a discussion of the human-like characteristics a personal robot must have; namely, human-like motion, human-like intelligence, and human-like communication     

Complement of Source Equation of Elastic Line

A new notion of joint, defined in terms of the state of motor (active or locked) and type of the elastic or rigid element, gear and/or link that follows after the motor, is introduced. Special attention is paid to the motion of the flexible links in the robotic configuration. The paper deals with the relationship between the equation of elastic line equilibrium, the “Euler–Bernoulli approach” (EBA), and equation of motion at the point of elastic line tip, the “Lumped-mass approach” (LMA). The Euler–Bernoulli equations (which have for a long time been used in the literature) should be expanded according to the requirements of the motion complexity of elastic robotic systems. The Euler–Bernoulli equation (based on the known laws of dynamics) should be supplemented with all the forces that are participating in the formation of the elasticity moment of the considered mode. This yields the difference in the structure of Euler–Bernoulli equations for each mode. The stiffness matrix is a full matrix. Mathematical model of the actuators also comprises coupling between elasticity forces. Particular integral of Daniel Bernoulli should be supplemented with the stationary character of elastic deformation of any point of the considered mode, caused by the present forces. General form of the elastic line is a direct outcome of the system motion dynamics, and cannot be described by one scalar equation but by three equations for position and three equations for orientation of every point on that elastic line. The choice of reference trajectory is analyzed. Simulation results are shown for a selected robotic example involving the simultaneous presence of elasticity of the gear and of the link (two modes), as well as the environment force dynamics.     

Hybrid Dynamic Control Algorithm for Humanoid Robots Based on Reinforcement Learning

In this paper, hybrid integrated dynamic control algorithm for humanoid locomotion mechanism is presented. The proposed structure of controller involves two feedback loops: model-based dynamic controller including impart-force controller and reinforcement learning feedback controller around zero-moment point. The proposed new reinforcement learning algorithm is based on modified version of actor-critic architecture for dynamic reactive compensation. Simulation experiments were carried out in order to validate the proposed control approach.The obtained simulation results served as the basis for a critical evaluation of the controller performance.     

On Reducing Numerical Complexity of Complex Robot Dynamics

An algorithm for the reduction of the numerical complexity of the analytical expressions participating in the dynamic model of robotic mechanism is a necessary part of the process of mathematical modelling of complex robotic mechanisms in symbolic form. Decomposition of the polynomial expressions into the products is a basic part of the algorithm for reducing the number of numerical operations in the analytical expressions of the robotic mechanisms dynamic models. The mathematical background for the data structures as well as the algorithm for decomposition of the polynomial expressions is developed and described in detail. The procedure for the reduction of the numerical complexity is illustrated by an example of the anthropomorphic locomotion configuration with fourteen degrees of freedom, and the obtained results are presented. The emphasis was placed on the procedure for decomposition of the expressions into the products because this procedure gives additional reduction in the number of mathematical operations.     

Forecasting of Reference Evapotranspiration by Artificial Neural Networks

In recent years, artificial neural networks (ANNs) have been applied to forecasting in many areas of engineering. In this note, a sequentially adaptive radial basis function network is applied to the forecasting of reference evapotranspiration (ETo). The sequential adaptation of parameters and structure is achieved using an extended Kalman filter. The criterion for network growing is obtained from the Kalman filter’s consistency test, while the criteria for neuron/connection pruning are based on the statistical parameter significance test. The weather parameter data (air temperature, relative humidity, wind speed, and sunshine) were available at Nis, Serbia and Montenegro, from January 1977 to December 1996. The monthly reference evapotranspiration data were obtained by the Penman-Monteith method, which is proposed as the sole standard method for the computation of reference evapotranspiration. The network learned to forecast ETo,t+1 based on ETo,t?11 and ETo,t?23. The results show that ANNs can be used for forecasting reference evapotranspiration with high reliability.     

Experiments with nontraditional hybrid control technique of biped locomotion robots

By using the previously established zero-moment point theory and the semi-inverse approach [1–4] for solving the artificial gait synthesis based on the prescribed dynamics to part of the active mechanism, in this new approach to dynamic control of legged locomotion robots, the conventional control synthesis, based on complete dynamic robot model, is abandoned. The paper describes the simulation experiments of biped control with a hybrid approach that combines the traditional model-based and fuzzy logic-based control techniques. The combined method is developed by extending a model-based decentralized control scheme by fuzzy logic-based tuners for modifying parameters of joint servo controllers. The simulation experiments performed on a simplified two-legged mechanism demonstrate the suitability of fuzzy logic-based methods for improving the performance of the robot control system.     

The Application of Connectionist Structures to Learning Impedance Control in Robotic Contact Tasks

The goal of this paper is to consider the synthesis of learning impedance control using recurrent connectionist structures for on-line learning of robot dynamic uncertainties in the case of robot contact tasks. The connectionist structures are integrated in non-learning impedance control laws that are intended to improve the transient dynamic response immediately after the contact. The recurrent neural network as a part of hybrid learning control algorithms uses fast learning rules and available sensor information in order to improve the robotic performance progressively for a minimum possible number of learning epochs. Some simulation results of deburring process with the MANUTEC r3 robot are presented here in order to verify the effectiveness of the proposed control learning algorithms.     

Formation of oxygen complexes in controlled atmosphere at surface of doped glassy carbon

The effects of boron and phosphorus incorporation in phenolic resin precursor to the oxidation resistance of glassy carbon have been studied. In order to reveal the nature and composition of the oxygen complexes formed at the surface of doped glassy carbon, under controlled atmosphere, the surface of the samples was cleaned under vacuum up to 1273 K. Specific functional groups, subsequently formed under dry CO₂ or O₂ atmosphere on the surface of boron-doped and phosphorus-doped glassy carbon samples, were examined using the temperature-programmed desorption method combined with mass spectrometric analysis. Characterization of surface properties of undoped and doped samples has shown that in the presence of either boron or phosphorus heteroatoms, a lower amount of oxygen complexes formed after CO₂ exposure, while, typically, higher amount of oxygen complexes formed after O₂ exposure. It has been concluded that the surface of undoped glassy carbon has a greater affinity towards CO₂, while in the presence of either boron or phosphorus heteroatoms, the glassy carbon surface affinity becomes greater towards O₂, under experimental conditions.     

Recommendations for energy efficient and visually acceptable street lighting

While designing new street lighting installations or dealing with reconstructions of the existing ones, lighting designers usually do not take into consideration all of the available means for energy savings and optimal performance. This paper offers a set of the most important recommendations regarding the relevant influencing factors for energy savings in street lighting, the majority of which represent the results and conclusions of original research. Recommendations which result from user needs and regard visual quality are also briefly presented. Taking all of these recommendations into account provides improvement of appearance and sense of security, as well as energy and cost savings.