P. Revenga

Wheelchair for physically disabled people with voice, ultrasonic and infrared sensor control

This paper describes a wheelchair for physically disabled people developed within the UMIDAM Project. A dependent-user recognition voice system and ultrasonic and infrared sensor systems has been integrated in this wheelchair. In this way we have obtained a wheelchair which can be driven with using voice commands and with the possibility of avoiding obstacles and downstairs or hole detection. The wheelchair has also been developed to allow autonomous driving (for example, following walls). The project, in which two prototypes have been produced, has been carried out totally in the Electronics Department of the University of Alcalá (Spain). It has been financed by the ONCE. Electronic system configuration, a sensor system, a mechanical model, control (low level control, control by voice commands), voice recognition and autonomous control are considered. The results of the experiments carried out on the two prototypes are also given.

Electronic control of a wheelchair guided by voice commands

Abstract This paper describes the control of an electric wheel chair with voice commands. This chair has been developed and built at the U.A.H. Electronic Department and financed by the ONCE Foundation (Spain). The first prototype consists of voice recognition, motor control, user interface and central processor modules. The electronic system allows the chair user a safe, easy ride, and guarantees the concordance between user commands and actual trajectories. Furthermore, the system has been designed to allow the addition of future features, like obstacle and stair detection and the tele-commanding of electrical household appliances from the chair.

Teaching equipment for training in the control of DC, brushless, and stepper servomotors

This paper describes teaching equipment for instruction in motor control developed in the Electronics Department of the University of Alcala, Spain. This project (called Project DEDALO) involved the development of complete electronic equipment for studying and carrying out experiments on the control of stepper, medium and low-power DC and brushless motors. The use of a personal computer as user interface (for the setting up of different types of motors and controls, display of the control structures, signal display, generation of commands, etc.) makes the equipment very easy to use and highly versatile.

3D Candidate Selection Method for Pedestrian Detection on Non-Planar Roads

This paper describes a stereo-vision-based candidate selection method for pedestrian detection from a moving vehicle. Non-dense 3D maps are computed by using epipolar geometry and a robust correlation process. Non-flat road assumption is used for correcting pitch angle variations. Thus, non obstacle points can be easily removed since they lay on the road. Generic obstacles are selected by using Subtractive Clustering algorithm in a 3D space with an adaptive radius. This clustering technique can be configurable for different types of obstacles. An optimal configuration for pedestrian detection is presented in this work.

Modeling Radiated Electromagnetic Emissions of Electric Motorcycles in Terms of Driving Profile Using Mlp Neural Networks

Current automotive electromagnetic compatibility (EMC) standards do not discuss the efiect of the driving proflle on real tra-c vehicular radiated emissions. This paper describes a modeling methodology to evaluate the radiated electromagnetic emissions of electric motorcycles in terms of the driving proflle signals such as the vehicle velocity remotely controlled by means of a CAN bus. A time domain EMI measurement system has been used to measure the temporal evolution of the radiated emissions in a semi-anechoic chamber. The CAN bus noise has been reduced by means of adaptive frequency domain cancellation techniques. Experimental results demonstrate that there is a temporal relationship between the motorcycle velocity and the radiated emission power in some speciflc frequency ranges. A Multilayer Perceptron (MLP) neural model has been developed to estimate the radiated emissions power in terms of the motorcycle velocity. Details of the training and testing of the developed neural estimator are described.

Power Measurement Methods for Energy Efficient Applications

Energy consumption constraints on computing systems are more important than ever. Maintenance costs for high performance systems are limiting the applicability of processing devices with large dissipation power. New solutions are needed to increase both the computation capability and the power efficiency. Moreover, energy efficient applications should balance performance vs. consumption. Therefore power data of components are important. This work presents the most remarkable alternatives to measure the power consumption of different types of computing systems, describing the advantages and limitations of available power measurement systems. Finally, a methodology is proposed to select the right power consumption measurement system taking into account precision of the measure, scalability and controllability of the acquisition system.

Location of Optical Fibers for the Calibration of Incoherent Optical Fiber Bundles for Image Transmission

Image transmission by incoherent optical fiber bundles (IOFBs) requires prior calibration to obtain the spatial in-out fiber correspondence to reconstruct the image captured by the pseudocamera. This information is recorded in a lookup table (LUT), which is later used for reordering the fiber positions and reconstructing the original image. This paper shows how to apply a fiber detection process to minimize the calibration time and improve the quality of the recovered image. Two different fiber detection methods were developed. The former uses the circular Hough transform algorithm based on the image gradient. The second algorithm combines a number of morphological transformations with distance transform. The results demonstrate that this technique provides a remarkable reduction in the processing time while improving fiber detection accuracy.

GPU Acceleration on Embedded Devices. A Power Consumption Approach

This paper analyses the power consumption of hybrid computation on embedded architectures with an available GPU. Novel efficiency metrics are obtained using a well-known benchmark process based on the Fourier transform as computing work load. The measurement process is arranged in order to obtain specific power data for each hardware configuration, varying the data size and number of computation threads, disabling the GPU, mixing the power computation of CPU/GPU, etc. The resulting data may be of interest for new applications and cluster development (i.e. Beowulf clusters) based on low power devices, such as the Beobot project.

Electrical Drive Radiated Emissions Estimation in Terms of Input Control Using Extreme Learning Machines

With the increase of electrical/electronic equipment integration complexity, the electromagnetic compatibility (EMC) becomes one of the key points to be respected in order to meet the constructor standard conformity. Electrical drives are known sources of electromagnetic interferences due to the motor as well as the related power electronics. They are the principal radiated emissions source in automotive applications. This paper shows that there is a direct relationship between the input control voltage and the corresponding level of radiated emissions. It also introduces a novel model using artificial intelligence techniques for estimating the radiated emissions of a DC-motor-based electrical drive in terms of its input voltage. Details of the training and testing of the developed extreme learning machine (ELM) are described. Good agreement between the electrical drive behavior and the developed model is observed.

People Location System based on WiFi Signal Measure

This work presents a people location system based on WiFi(Wireless-Fidelity) signal measure. The current locations systems based on WiFi are mainly applied in the location of indoor robots using the measure of their communications interface and the measures of other additional sensors. The advantage of the system presented in this work is that it is not necessary to add additional hardware (HW) to the people whom is tried to locate, neither in the environment, because we use the WiFi communications infrastructure. A probabilistic method based on a Hidden Markov Model (HMM) is used to determine the location of the people in the environment. In addition, a study of the WiFi signal measure is made in indoors with the main objective to obtain the necessary conclusions for the design of the system. The proposed method has been tested in a real environment. The results and conclusions obtained in the work are presented.