João P. Ferreira

SVR Versus Neural-Fuzzy Network Controllers for the Sagittal Balance of a Biped Robot

The real-time balance control of an eight-link biped robot using a zero moment point (ZMP) dynamic model is difficult due to the processing time of the corresponding equations. To overcome this limitation, two alternative intelligent computing control techniques were compared: one based on support vector regression (SVR) and another based on a first-order Takagi-Sugeno-Kang (TSK)-type neural-fuzzy (NF) network. Both methods use the ZMP error and its variation as inputs and the output is the correction of the robots torso necessary for its sagittal balance. The SVR and the NF were trained based on simulation data and their performance was verified with a real biped robot. Two performance indexes are proposed to evaluate and compare the online performance of the two control methods. The ZMP is calculated by reading four force sensors placed under each robots foot. The gait implemented in this biped is similar to a human gait that was acquired and adapted to the robots size. Some experiments are presented and the results show that the implemented gait combined either with the SVR controller or with the TSK NF network controller can be used to control this biped robot. The SVR and the NF controllers exhibit similar stability, but the SVR controller runs about 50 times faster.

Human Gait Acquisition and Characterization

This paper analyzes human motion, more specifically the human gait in the sagittal plane. A video camera is used to acquire images of a walking person, fitted with a set of white light-emitting diodes (LEDs). The acquired trajectories of the light points are then used to specify joint trajectories in a biped robot. To analyze the stability of the human gait, a system was also developed to acquire the center of pressure (CoP). This system uses eight force sensors, four under each foot. The influence of the human torso angle on the CoP position during walking was confirmed. Some experiments were carried out on a biped robot, and the results show that the acquired human gait can be used in a biped robot, after scale conversion.

Control of a Biped Robot With Support Vector Regression in Sagittal Plane

This paper describes the control of an autonomous biped robot that uses the support vector regression (SVR) method for its sagittal balance. This SVR uses the zero moment point (ZMP) position and its variation as input and the torso correction of the robots body as output. As the robot model used segments the robot into eight parts, it is difficult to use online. This is the main reason for using the artificial intelligence method. The SVR was trained with simulation data that was previously tested with the real robot. The SVR was found to be faster (with similar accuracy) than a recurrent network and a neuro-fuzzy control. This method is more precise than the model based on an inverted pendulum. The design of the feet is considered in terms of accommodating the force sensors used to estimate the center of pressure (CoP). The SVR was tested in the real robot using joint trajectories that are similar to those of human beings, and the results are presented.

A neural-fuzzy walking control of an autonomous biped robot

In this paper, an adaptive neural-fuzzy walking control of an autonomous biped robot is proposed. This control system uses a feed forward neural network based on nonlinear regression. The general regression neural network is used to construct the base of an adaptive neuro-fuzzy system. The neural network uses an iterative grid partition method for the initial structure identification of the controller parameters. Comparison results are done between the proposed method and the ANFIS tool provided in the fuzzy MATLAB toolbox. The robots control system uses an inverted pendulum to balance of the gaits. The effectiveness of the proposed control system is demonstrated by simulation and experimental tests

Simulation control of a biped robot with Support Vector Regression

This paper describes the control of an autonomous biped robot that uses the Support Vector Regression (SVR) method for its longitudinal balance. This SVR uses the Zero Moment Point (ZMP) position and its variation as input and the longitudinal correction of the robots body is obtained as the output. The SVR was trained based on simulation data that was confirmed with the real robot. This method showed to be faster (with similar accuracy) than a recurrent network or a neuro-fuzzy control of the biped balance.

Energy efficiency of higher education buildings: a case study

Purpose – This paper aims to propose an energy efficiency plan (with technical and behavioural improvement measures) for a Portuguese higher education building – the Teaching Building of the Faculty of Economics of the University of Coimbra (FEUC). Design/methodology/approach – The study was developed in the context of both the “Green Campus – Challenge for Energy Efficiency in Higher Education” and the Energy for Sustainability Initiative of the University of Coimbra, Portugal. An energy audit was conducted based on the analysis of the energy consumption profiles. A monitoring campaign was carried out to measure and disaggregate the electricity consumption. The consumption of natural gas and water were also assessed. The building envelope and the heating and lighting systems were also evaluated. Some patterns of energy-environmental behaviours of the academic community were investigated through a Web-based survey. Findings – The energy efficiency plan contemplates short-term tangible/intangible actions. ...

ZMP trajectory reference for the sagittal plane control of a biped robot based on a human CoP and gait

This paper introduces two new important issues to be considered in the design of the zero moment point (ZMP) trajectory reference for the sagittal plane balance control of an autonomous walking biped robot with an human-like gait. ZMP trajectory reference generation is very important in the design and balance control of the walking of a biped robot. ZMP reference generation algorithms based on the linear inverted pendulum model (LIPM) and moving ZMP references in the swing phase have already been proposed with the ZMP trajectory during the swing phase being designed moving along a symmetric trajectory relative to the center of the foot. It was verified experimentally that in the human gait the ZMP trajectory moves along the foot in a way that it is shifted forward relative to its center. To take this into account a shift parameter is then proposed to move forward the XZMP trajectory reference during the swing phase. It was also verified experimentally that in the human gait the ZMP trajectory amplitude depends on the swing time. Its variation law has been determined experimentally and it was verified that this range decreases as the swing time increases, reducing to zero for a static gait. It is then proposed a parameter H to take into account this variation with the swing time of the gait. Six experiments were carried out for three different XZMP trajectory references. In order to evaluate and compare the performance of the biped robot using the three XZMP trajectory references two performance indexes are proposed.

SVR CONTROLLER FOR A BIPED ROBOT IN THE SAGITTAL PLANE WITH HUMAN-BASED ZMP TRAJECTORY REFERENCE AND GAIT

This paper introduces two new important issues to be considered in the design of the zero moment point (ZMP) trajectory of a biped robot. It was verified experimentally that in the human gait the ZMP trajectory moves along the foot in a way that it is shifted forward relative to its center. To take this into account a shift parameter is then proposed. It was also verified experimentally that in the human gait the ZMP trajectory amplitude depends on the swing time, reducing to zero for a static gait. It is then proposed a parameter to take into account this variation with the swing time of the gait. Six experiments were carried out for three different XZMP trajectory references. In order to evaluate and compare the performance of the biped robot using the three XZMP trajectory references two performance indexes are proposed. For the real-time balance control of this 8 link biped robot it was used an intelligent computing control technique, the Support Vector Regression (SVR). The control method uses the ZMP error and its variation as inputs and the output is the correction of the robots ankle and torso angles, necessary for the sagittal balance of the biped robot.

A gait retraining feedback system based on wearable sensors

The purpose of this study is to develop a gait retraining feedback system based on wearable sensors for the gait training and the recovery of knee osteoarthritis patients. The system is mainly composed of one motion sensor, six plantar pressure sensors, vibrator and upper computer. The foot progression angle of subject measured by the motion sensor was transmitted to a upper computer through a WIFI module. The judgment for foot progression angle by PC was then sent to the motion sensor for the feedback of gait retraining by a vibrator. In order to validate the training effect of the system, walking experiments of simulated patients was conducted. The results show that the gait retraining system can have a effective influence on the gait in real time and can be used to train the walking gait to reduce the knee adduction moment.

Low cost vision system for human gait acquisition and characterization

This paper presents a low cost system for human gait analysis. Two opposite-faced web cameras are used to acquire images of the walking of a person carrying a set of passive marks, where the color is chosen to contrast with the ambient dominant color. It is also used a treadmill with passive marks, where the user walks at different speeds. The acquired trajectories of the marks are used to determine body joint angles and other 3D crossed angles, obtained by both opposite sides from video images processing. With this low cost measurement system the analysis and reconstruction of human gait can be done with a mean error of 2 degrees, becoming a good alternative to more expensive systems to be used in human gait characterization. The system can be used to detect human gait pathologies and to accomplish physical rehabilitation.