Search

Sound source localization (SSL) is used in various applications such as industrial noise-control, speech detection in mobile phones, speech enhancement in hearing aids and many more. Newest video conferencing setups use SSL. The position of a speaker is detected from the difference in the audio waves received by a microphone array. After detection the camera focuses onto the location of the speaker. The human brain is also able to detect the location of a speaker from auditory signals. It uses, among other cues, the difference in amplitude and arrival time of the sound wave at the two ears, called interaural level and time difference. However, the substrate and computational primitives of our brain are different from classical digital computing. Due to its low power consumption of around 20 W and its performance in real time the human brain has become a great source of inspiration for emerging technologies. One of these technologies is neuromorphic hardware which implements the fundamental principles of brain computing identified until today using complementary metal-oxide-semiconductor technologies and new devices. In this work we propose the first neuromorphic closed-loop robotic system that uses the interaural time difference for SSL in real time. Our system can successfully locate sound sources such as human speech. In a closed-loop experiment, the robotic platform turned immediately into the direction of the sound source with a turning velocity linearly proportional to the angle difference between sound source and binaural microphones. After this initial turn, the robotic platform remains at the direction of the sound source. Even though the system only uses very few resources of the available hardware, consumes around 1 W, and was only tuned by hand, meaning it does not contain any learning at all, it already reaches performances comparable to other neuromorphic approaches. The SSL system presented in this article brings us one step closer towards neuromorphic

Neuromorphic computation processes sensors output in the spiking domain, which presents constraints in many cases when converting information to spikes, loosing, as example, temporal accuracy. This paper presents a spike-based system to adapt audio information from low-power pulse-density modulation (PDM) microelectromechanical systems microphones into rate coded spike frequencies. These spikes could be directly used by the neuromorphic auditory sensor (NAS) for frequency decomposition in different bands, avoiding the analog or digital conversion to spike streams. This improves the time response of the NAS, allowing its use in more time restrictive applications. This adaptation was conducted in VHDL as an interface for PDM microphones, converting their pulses into temporal distributed spikes following a pulse-frequency modulation scheme with an accurate inter-spike-interval, known as PDM to spikes interface (PSI). We introduce a new architecture of spike-based band-pass filter to reject DC components and distribute spikes in time. This was tested in two scenarios, first as a stand-alone circuit for its characterization, and then integrated with a NAS for verification. The PSI achieves a total harmonic distortion of −46.18 dB and a signal-to-noise ratio of 63.47 dB, demands less than 1% of the resources of a Spartan-6 FPGA and its power consumption is around 7 mW.

Múltiples lesiones neurológicas, como los Accidentes Cardíacos Vasculares (ACV), provocan una degeneración y/o atrofia de la movilidad en las extremidades. La terapia pasiva se suele usar en los procesos de recuperación tras sufrir este tipo de lesiones, pero los ejercicios de brazos y manos utilizados habitualmente se basan en la realización de actividades de alta intensidad y repetitivos, haciendo que la recuperación sea larga, necesite de mucho trabajo y de la ayuda de varios fisiotera- peutas. En este trabajo se realiza el diseño, montaje, implementación y testeo de un sistema hardware-software basado en exoesqueleto y sensores de captación de movimiento de brazo y manos para su utilización en la rehabilitación de los miembros superiores con el fin de reducir el tiempo de recuperación. El usuario dispondrá de una aplicación que le guiará en todo momento haciendo uso de técnicas activas de gamificación para aumentar la motivación.

Hearing can be considered as one of the most important senses since it plays a key role in the audiovisual learning process. While a lot of effort has been made for achieving good results from the traditional approach of auditory perception, new trends such as neuromorphic computing are showing promising achievements in the implementation of brain structures for sensory perception. In this work, the design and integration of a neuromorphic event based digital model of the auditory ascending pathway within the iCub robotic platform is proposed. This model, which comprises from the cochlea up to the inferior colliculus, replaces the traditional approach for sound processing already implemented on iCub and is able to perform sound recognition and spatial localization in real time, allowing the implementation of auditory attention models in complex scenarios, like the cocktail party problem

Neuromorphic systems are a viable alternative to conventional systems for real-time tasks with constrained resources. Their low power consumption, compact hardware realization, and low-latency response characteristics are the key ingredients of such systems. Furthermore, the event-based signal processing approach can be exploited for reducing the computational load and avoiding data loss due to its inherently sparse representation of sensed data and adaptive sampling time. In event-based systems, the information is commonly coded by the number of spikes within a specific temporal window. However, the temporal information of event-based signals can be difficult to extract when using rate coding. In this work, we present a novel digital implementation of the model, called time difference encoder (TDE), for temporal encoding on event-based signals, which translates the time difference between two consecutive input events into a burst of output events. The number of output events along with the time between them encodes the temporal information. The proposed model has been implemented as a digital circuit with a configurable time constant, allowing it to be used in a wide range of sensing tasks that require the encoding of the time difference between events, such as optical flow-based obstacle avoidance, sound source localization, and gas source localization. This proposed bioinspired model offers an alternative to the Jeffress model for the interaural time difference estimation, which is validated in this work with a sound source lateralization proof-of-concept system. The model was simulated and implemented on a field-programmable gate array (FPGA), requiring 122 slice registers of hardware resources and less than 1 mW of power consumption.

In this work, it is intended to advance on the development of the neuromorphic audio processing systems in robots through the implementation of an open-source neuromorphic cochlea, event-based models of primary auditory nuclei, and their potential use for real-time robotics applications. First, the main gaps when working with neuromorphic cochleae were identified. Among them, the accessibility and usability of such sensors can be considered as a critical aspect. Silicon cochleae could not be as flexible as desired for some applications. However, FPGA-based sensors can be considered as an alternative for fast prototyping and proof-of-concept applications. Therefore, a software tool was implemented for generating open-source, user-configurable Neuromorphic Auditory Sensor models that can be deployed in any FPGA, removing the aforementioned barriers for the neuromorphic research community. Next, the biological principles of the animals' auditory system were studied with the aim of continuing the development of the Neuromorphic Auditory Sensor. More specifically, the principles of binaural hearing were deeply studied for implementing event-based models to perform real-time sound source localization tasks. Two different approaches were followed to extract inter-aural time differences from event-based auditory signals. On the one hand, a digital, event-based design of the Jeffress model was implemented. On the other hand, a novel digital implementation of the Time Difference Encoder model was designed and implemented on FPGA. Finally, three different robotic platforms were used for evaluating the performance of the proposed real-time neuromorphic audio processing architectures. An audio-guided central pattern generator was used to control a hexapod robot in real-time using spiking neural networks on SpiNNaker. Then, a sensory integration application was implemented combining sound source localization and obstacle avoidance for autonomous robots navigation. Lastly, the Neu, En este trabajo se pretende avanzar en el desarrollo de los sistemas de procesamiento de audio neuromórficos en robots a través de la implementación de una cóclea neuromórfica de código abierto, modelos basados en eventos de los núcleos auditivos primarios, y su potencial uso para aplicaciones de robótica en tiempo real. En primer lugar, se identificaron los principales problemas a la hora de trabajar con cócleas neuromórficas. Entre ellos, la accesibilidad y usabilidad de dichos sensores puede considerarse un aspecto crítico. Los circuitos integrados analógicos que implementan modelos cocleares pueden no pueden ser tan flexibles como se desea para algunas aplicaciones específicas. Sin embargo, los sensores basados en FPGA pueden considerarse una alternativa para el desarrollo rápido y flexible de prototipos y aplicaciones de prueba de concepto. Por lo tanto, en este trabajo se implementó una herramienta de software para generar modelos de sensores auditivos neuromórficos de código abierto y configurables por el usuario, que pueden desplegarse en cualquier FPGA, eliminando las barreras mencionadas para la comunidad de investigación neuromórfica. A continuación, se estudiaron los principios biológicos del sistema auditivo de los animales con el objetivo de continuar con el desarrollo del Sensor Auditivo Neuromórfico (NAS). Más concretamente, se estudiaron en profundidad los principios de la audición binaural con el fin de implementar modelos basados en eventos para realizar tareas de localización de fuentes sonoras en tiempo real. Se siguieron dos enfoques diferentes para extraer las diferencias temporales interaurales de las señales auditivas basadas en eventos. Por un lado, se implementó un diseño digital basado en eventos del modelo Jeffress. Por otro lado, se diseñó una novedosa implementación digital del modelo de codificador de diferencias temporales y se implementó en FPGA. Por último, se utilizaron tres plataformas robóticas diferentes para evaluar el rendimi

Este TFG se centra en al ámbito de la domótica, es decir, el conjunto de tecnologías y sistemas capaces de automatizar una vivienda con el fin de aportar seguridad, bienestar y confort. En este caso, el proyecto se basa en la creación de una placa de circuito impreso o PCB. Los componentes más relevantes que conforman el diseño del circuito impreso son: Un módulo ESP-12E basado en el SoC ESP8266, un convertidor AC\DC HLK-PM03 y un relé SRD-05. La función de este sistema será poder controlar, de forma manual o usando una conexión inalámbrica tipo WiFi, un elemento de la instalación doméstica, por ejemplo una bombilla. Cabe destacar que el formato creado para la PCB es genérico lo que implica que permite controlar cualquier componente que cumpla las especificaciones operativas del sistema. A lo largo de la memoria se detalla la elección de componentes para cumplir los objetivos del sistema, el diseño del mismo a través del software Eagle, el ensamblado y finalmente las pruebas realizadas para comprobar el correcto funcionamiento del dispositivo. Teniendo en cuenta la conectividad de todo el ecosistema a través de WiFi, se implementará en paralelo un servidor doméstico propio a través de una Rasperry Pi 4. Para esta labor se utilizará Home Assistant, software gratuito y de código abierto diseñado para ser un sistema de control central de dispositivos inteligentes con un enfoque en el control local y la privacidad., This TFG focuses on the field of home automation, that is, the set of technologies and systems capable of automating a home in order to provide security, well-being and comfort. In this case, the project is based on the creation of a printed circuit board or PCB. The most relevant components that make up the printed circuit design are: An ESP-12E module based on the ESP8266 SoC, an HLK-PM03 AC\DC converter and an SRD-05 relay. The function of this system will be to be able to control, manually or using a WiFi-type wireless connection, an element of the domestic installation, for example a light bulb. It should be noted that the format created for the PCB is generic, which means that it allows controlling any component that meets the operating specifications of the system. Throughout the report, the choice of components to meet the objectives of the system, its design through the Eagle software, the assembly and finally the tests carried out to verify the correct operation of the device are detailed. Taking into account the connectivity of the entire ecosystem through WiFi, a home server of its own will be implemented in parallel through a Rasperry Pi 4. For this task, Home Assistant will be used, free and open source software designed to be a central control of smart devices with a focus on local control and privacy.

Monitoring animals’ behavior living in wild or semi-wild environments is a very interesting subject for biologists who work with them. The difficulty and cost of implanting electronic devices in this kind of animals suggest that these devices must be robust and have low power consumption to increase their battery life as much as possible. Designing a custom smart device that can detect multiple animal behaviors and that meets the mentioned restrictions presents a major challenge that is addressed in this work. We propose an edge-computing solution, which embeds an ANN in a microcontroller that collects data from an IMU sensor to detect three different horse gaits. All the computation is performed in the microcontroller to reduce the amount of data transmitted via wireless radio, since sending information is one of the most power-consuming tasks in this type of devices. Multiples ANNs were implemented and deployed in different microcontroller architectures in order to find the best balance between energy consumption and computing performance. The results show that the embedded networks obtain up to 97.96% ± 1.42% accuracy, achieving an energy efficiency of 450 Mops/s/watt.

The correct identi cation of burst events is crucial in many scenarios, ranging from basic neuroscience to biomedical applications. However, none of the burst detection methods that can be found in the literature have been widely adopted for this task. As an alternative to conventional techniques, a novel neuromorphic approach for real-time burst detection is proposed and tested on acquisitions from in vitro cultures. The system consists of a Neuromorphic Auditory Sensor, which converts the input signal obtained from electrophysiological recordings into spikes and decomposes them into di erent frequency bands. The output of the sensor is sent to a trained spiking neural network implemented on a SpiNNaker board that discerns between bursting and non-bursting activity. This data-driven approach was compared with 8 di erent conventional spike-based methods, addressing some of their drawbacks, such as being able to detect both high and low frequency events and working in an online manner. Similar results in terms of number of detected events, mean burst duration and correlation as current state-ofthe- art approaches were obtained with the proposed system, also bene ting from its lower power consumption and computational latency. Therefore, our neuromorphic-based burst detection paves the road to future implementations for neuroprosthetic applications.

Prostate cancer (PCa) is the second most frequently diagnosed cancer among men worldwide, with almost 1.3 million new cases and 360,000 deaths in 2018. As it has been estimated, its mortality will double by 2040, mostly in countries with limited resources. These numbers suggest that recent trends in deep learning-based computer-aided diagnosis could play an important role, serving as screening methods for PCa detection. These algorithms have already been used with histopathological images in many works, in which authors tend to focus on achieving high accuracy results for classifying between malignant and normal cases. These results are commonly obtained by training very deep and complex convolutional neural networks, which require high computing power and resources not only in this process, but also in the inference step. As the number of cases rises in regions with limited resources, reducing prediction time becomes more important. In this work, we measured the performance of current state-of-the-art models for PCa detection with a novel benchmark and compared the results with PROMETEO, a custom architecture that we proposed. The results of the comprehensive comparison show that using dedicated models for specific applications could be of great importance in the future.

The use of deep learning solutions in different disciplines is increasing and their algorithms are computationally expensive in most cases. For this reason, numerous hardware accelerators have appeared to compute their operations efficiently in parallel, achieving higher performance and lower latency. These algorithms need large amounts of data to feed each of their computing layers, which makes it necessary to efficiently handle the data transfers that feed and collect the information to and from the accelerators. For the implementation of these accelerators, hybrid devices are widely used, which have an embedded computer, where an operating system can be run, and a field-programmable gate array (FPGA), where the accelerator can be deployed. In this work, we present a software API that efficiently organizes the memory, preventing reallocating data from one memory area to another, which improves the native Linux driver with a 85% speed-up and reduces the frame computing time by 28% in a real application.

Prostate cancer (PCa) is one of the most commonly diagnosed cancer and one of the leading causes of death among men, with almost 1.41 million new cases and around 375,000 deaths in 2020. Artificial Intelligence algorithms have had a huge impact on medical image analysis, including digital histopathology, where Convolutional Neural Networks (CNNs) are used to provide a fast and accurate diagnosis, supporting experts in this task. To perform an automatic diagnosis, prostate tissue samples are first digitized into gigapixel-resolution whole-slide images. Due to the size of these images, neural networks cannot use them as input and, therefore, small subimages called patches are extracted and predicted, obtaining a patch-level classification. In this work, a novel patch aggregation method based on a custom Wide & Deep neural network model is presented, which performs a slide-level classification using the patch-level classes obtained from a CNN. The malignant tissue ratio, a 10-bin malignant probability histogram, the least squares regression line of the histogram, and the number of malignant connected components are used by the proposed model to perform the classification. An accuracy of 94.24% and a sensitivity of 98.87% were achieved, proving that the proposed system could aid pathologists by speeding up the screening process and, thus, contribute to the fight against PCa.

El reciente Grado en Ingeniería de la Salud se originó con el planteamiento de cubrir la carencia de conoci miento sobre la rama sanitaria de un Ingeniero Infor mático. Es en dicho grado donde, de forma optativa, el alumno cursa la asignatura Sistemas de Rehabilitación y Ayuda a la Discapacidad, que tiene un papel funda mental para el diseño de sistemas enfocados tanto a la rehabilitación como a proveer facilidades a pacien tes con ciertas dificultades. En este artículo se describe la metodología de las prácticas de laboratorio para la docencia en dicha asignatura, la cual se basa en el con cepto de aprendizaje basado en proyectos. Las distin tas sesiones de laboratorio se reparten en dos bloques, diferenciando entre sesiones de introducción a ciertos contenidos y dispositivos hardware, y un gran bloque donde los alumnos desarrollan un proyecto de rehabi litación o ayuda a la discapacidad con los conocimien tos adquiridos, que posteriormente documentan en for mato artículo. Esta dinámica ha conseguido una gran acogida y ha incrementado la motivación de los alum nos, llevando a muchos a desarrollar un Trabajo Fin de Grado relacionado con la asignatura. La dinámica propuesta tiene un papel fundamental en futuros Inge nieros de la Salud tanto a nivel de aprendizaje como a nivel laboral.

OpenNAS is an open-source tool for automatically generating the source files to create a Neuromorphic Auditory Sensor (NAS) VHDL project for FPGA. OpenNAS guides the user with a friendly interface that allows configuring the NAS’ parameters using a five-step wizard for code generation. OpenNAS provides support to several audio input interfaces (AC’97 audio codec, I2S-ADC and PDM microphones), different processing architectures (cascade and parallel), and neuromorphic output interfaces (parallel AER, SpiNNaker). After NAS generation, users have everything ready for building, simulating, and synthesizing the VHDL project for a target FPGA. OpenNAS is fully modular, which allows providing support to new features in an easy way

Visualizing the output from event-based sensors and analyzing the information within it is crucial when developing new neuromorphic systems. A novel open-source, cross-platform Python package called pyNAVIS is proposed, which provides a set of functionalities to analyze and process spiking information obtained from neuromorphic cochleas, along with other tools to generate files and datasets for machine learning tasks. This modular package can be integrated in complex and higher-level projects, which could be useful for researchers working in neuromorphic audio processing tasks.

El mundo ha cambiado desde la aparición del nue vo virus de la familia de los coronavirus (COVID-19), el cual fue declarado pandemia en tan sólo unos po cos meses. El COVID-19 ha tenido un alto impacto en todos los ámbitos conocidos, incluida la docencia. Las medidas de seguridad impartidas por las autorida des sanitarias implicaron una necesaria adaptación de la docencia en general, y más en concreto la univer sitaria. Este artículo se centra en cómo ha afectado la pandemia a la asignatura de Informática en el ámbito del Grado de Ingeniería Química Industrial. En dicha asignatura se introducen a los alumnos los conceptos básicos de la informática, incluyendo sistemas opera tivos, bases de datos y redes de computadores, además de un bloque de sesiones de laboratorio dedicado a la programación en lenguaje C. La situación actual ha dado lugar a la semipresencialidad en la docencia de la asignatura durante el curso 2020/2021, repercutien do tanto a las metodologías de enseñanza como a los contenidos teórico-prácticos. En el presente trabajo se describen los cambios realizados de cara a adaptar el contenido de la asignatura a la semipresencialidad, re portando resultados tanto a nivel de evaluación como a nivel de seguimiento y motivación del alumnado

Este artículo presenta una práctica de laboratorio impartida mediante una metodología de aprendizaje basado en proyectos cuyo objetivo principal es adqui rir la capacidad de programación de microcontrolado res para el diseño e implantación de una red de co municación inalámbrica de bajo consumo en el ámbi to de las comunicaciones industriales. Este proyecto se desarrolla en las sesiones prácticas de la asignatura Comunicaciones Industriales del Máster Universitario en Sistemas Inteligentes en Energía y Transporte cuyas competencias contemplan la capacidad para planificar la instalación de redes de comunicación en entornos industriales, así como la aplicación de los conocimientos adquiridos en la resolución de proble mas multidisciplinares. El proyecto de laboratorio expuesto en este trabajo abarca ambas competencias, ya que propone establecer una red de control jerár quica en las comunicaciones industriales mediante la programación de microcontroladores, abordando el desarrollo de sistemas empotrados en tiempo real. Los dispositivos empleados para establecer la red de sensores son módulos XBee conectados a un puerto UART de un microcontrolador ARM Cortex-M0 para establecer comunicación serie asíncrona entre el módulo XBee y el microcontrolador. La arquitectura de la red está basada en la topología estrella. El módulo XBee central está conectado a través de un puerto COM Virtual a un PC. En el PC se ejecuta una interfaz de usuario desarrollada en lenguaje C# usan do el entorno Visual Studio basada en la interfaz gráfica Windows Forms.

Abnormal foot postures can be measured during the march by plantar pressures in both dynamic and static conditions. These detections may prevent possible injuries to the lower limbs like fractures, ankle sprain or plantar fasciitis. This information can be obtained by an embedded instrumented insole with pressure sensors and a low-power microcontroller. However, these sensors are placed in sparse locations inside the insole, so it is not easy to correlate manually its values with the gait type; that is why a machine learning system is needed. In this work, we analyse the feasibility of integrating a machine learning classifier inside a low-power embedded system in order to obtain information from the user’s gait in real-time and prevent future injuries. Moreover, we analyse the execution times, the power consumption and the model effectiveness. The machine learning classifier is trained using an acquired dataset of 3000+ steps from 6 different users. Results prove that this system provides an accuracy over 99% and the power consumption tests obtains a battery autonomy over 25 days.

Initially, robots were developed with the aim of making our life easier, carrying out repetitive or dangerous tasks for humans. Although they were able to perform these tasks, the latest generation of robots are being designed to take a step further, by performing more complex tasks that have been carried out by smart animals or humans up to date. To this end, inspiration needs to be taken from biological examples. For instance, insects are able to optimally solve complex environment navigation problems, and many researchers have started to mimic how these insects behave. Recent interest in neuromorphic engineering has motivated us to present a real-time, neuromorphic, spike-based Central Pattern Generator of application in neurorobotics, using an arthropod-like robot. A Spiking Neural Network was designed and implemented on SpiNNaker. The network models a complex, online-change capable Central Pattern Generator which generates three gaits for a hexapod robot locomotion. Recon gurable hardware was used to manage both the motors of the robot and the real-time communication interface with the Spiking Neural Networks. Real-time measurements con rm the simulation results, and locomotion tests show that NeuroPod can perform the gaits without any balance loss or added delay.

The brain is able to solve complex tasks in real time by combining different sensory cues with previously acquired knowledge. Inspired by the brain, we designed a neuromorphicdemonstrator which combines auditory and visual input to find an obstacle free direction closest to the sound source. The system consists of two event-based sensors (the eDVS for vision and the NAS for audition) mounted onto a pan-tilt unit and a spiking neural network implemented on the SpiNNaker platform. By combining the different sensory information, the demonstrator is able to point at a sound source direction while avoiding obstacles in real time

In this paper we present a sub-system to convert audio information from low-power MEMS microphones with pulse density modulation (PDM) output into rate coded spike streams. These spikes represent the input signal of a Neuromorphic Auditory Sensor (NAS), which is implemented with Spike Signal Processing (SSP) building blocks. For this conversion, we have designed a HDL component for FPGA able to interface with PDM microphones and converts their pulses to temporal distributed spikes following a pulse frequency modulation (PFM) scheme with an accurate configurable Inter-Spike-Interval. The new FPGA component has been tested in two scenarios, first as a stand-alone circuit for its characterization, and then it has been integrated with a full NAS design to verify its behavior. This PDM interface demands less than 1% of a Spartan 6 FPGA resources and has a power consumption below 5mW.

Animals combine various sensory cues with previously acquired knowledge to safely travel towards a target destination. In close analogy to biological systems, we propose a neuromorphic system which decides, based on auditory and visual input, how to reach a sound source without collisions. The development of this sensory integration system, which identifies the shortest possible path, is a key achievement towards autonomous robotics. The proposed neuromorphic system comprises two event based sensors (the eDVS for vision and the NAS for audition) and the SpiNNaker processor. Open loop experiments were performed to evaluate the system performances. In the presence of acoustic stimulation alone, the heading direction points to the direction of the sound source with a Pearson correlation coefficient of 0.89. When visual input is introduced into the network the heading direction always points at the direction of null optical flow closest to the sound source. Hence, the sensory integration network is able to find the shortest path to the sound source while avoiding obstacles. This work shows that a simple, task dependent mapping of sensory information can lead to highly complex and robust decisions.

Spiking convolutional neural networks have become a novel approach for machine vision tasks, due to the latency to process an input stimulus from a scene, and the low power consumption of these kind of solutions. Event-based systems only perform sum operations instead of sum of products of framebased systems. In this work an upgrade of a neuromorphic event-based convolution accelerator for SCNN, which is able to perform multiple layers with different kernel sizes, is presented. The system has a latency per layer from 1.44 μs to 9.98μs for kernel sizes from 1x1 to 7x7.

In this work, a novel distance estimation mechanism using received signal strength indication (RSSI) signals with ZigBee modules is designed, implemented and tested in several scenarios. This estimator was used for a research project focused on a wildlife behavioral classification system deployed in Doñana’s National Park. As a supporting feature for that project, this work was implemented for locating animal’s collars acting as wireless nodes in order to find those who went outside of the coverage area of the network or that were accidentally detached from animals. This work describes the system architecture and the implementation of a mobile assistant capable of recovering devices located beyond the coverage of the network. The analytical model needed for distance estimation and the signal filtering are described, as well as the difficulties that the researchers must deal when building robust location estimators. This theoretical model was applied to three different scenarios and tested with two validation experiments.

Along with the proliferation of mobile devices and wireless signal coverage, IoT devices, such as smart wristbands for monitoring its owner’s activity or sleep patterns, get great popularity. Wearable technology in human life has become quite useful due to the information given (sleep hours, heart rate, etc). However, wearables for animals does not give information about behaviour directly: they collect raw data that is sent to a server where, after a post-processing step, the behaviour is known. In this work, we present a smart IoT device that classifies different animal behaviours from the information obtained from on-board sensors using an embedded neural network running in the device. This information is uploaded to a server through a wireless sensor network based on Zigbee communication. The architecture of the device allows an easy assembly in a reduced dimension wearable case. The firmware allows a modular functionality by activating or deactivating modules independently, which improve the power efficiency of the device. The power consumption has been analyzed, allowing the 1Ah battery to work the system during several days. A novel localization and distance estimation technique (for 802.15.4 networks) is presented to recover a lost device in Do˜nana National Park with unidirectional antennas and log-normalization distance estimation over RSSI.

Autonomous robots have become a very popular topic within the artificial intelligence field. These systems are able to perform difficult or risky tasks that could be dangerous when done by humans or trained animals. Vision is commonly considered the most relevant input sensor for autonomous robots and tracking systems. However, auditory information is also important in some specific situations where vision cannot provide any useful information when navigating. In this work, a spike-based model of the medial superior olive of the inner ear has been implemented in reconfigurable hardware for performing sound source localization in real time. Future works will focus on integrating this information with vision in order to achieve a fully bio-inspired autonomous tracking system.

This live demonstration presents an audio-guided neuromorphic robot: from a Neuromorphic Auditory Sensor (NAS) to locomotion using Spiking Central Pattern Generators (sCPGs). Several gaits are generated by sCPGs implemented on a SpiNNaker board. The output of these sCPGs is sent in a real-time manner to an Field Programmable Gate Array (FPGA) board using an AER-to-SpiNN interface. The control of the hexapod robot joints is performed by the FPGA board. The robot behavior can be changed in real-time by means of the NAS. The audio information is sent to the SpiNNaker board which classifies it using a Spiking Neural Network (SNN). Thus, the input sound will activate a specific gait pattern which will eventually modify the behavior of the robot.

In this demonstration a spiking neural network architecture for vision recognition using an FPGA spiking convolution processor, based on leaky integrate and fire neurons (LIF) and a SpiNNaker board is presented. The network has been trained with Poker-DVS dataset in order to classify the four different card symbols. The spiking convolution processor extracts features from images in form of spikes, computes by one layer of 64 convolutions. These features are sent to an OKAERtool board that converts from AER to 2-7 protocol to be classified by a spiking neural network deployed on a SpiNNaker platform.

Los sistemas neuronales biológicos responden a estímulos de una forma rápida y eficiente en el movimiento motor del cuerpo, comparado con los sistemas robóticos clásicos, los cuales requieren una capacidad de computación mucho más elevada. Una de las claves de estos sistemas es la codificación de la información en el dominio pulsante. Las neuronas se comunican por eventos con pequeños pulsos de corrientes producidas por intercambio de iones entre las dendritas y los axones de las mismas. La configuración en redes de neuronas permite no sólo el procesado de la información sensorial y su procesamiento en el dominio pulsante, sino también la propia actuación sobre los músculos en el formato pulsante. Este trabajo presenta la aplicación de un modelo de control motor basado en el procesado de pulsos, incluyendo la propia actuación sobre motores en el contexto de los pulsos. Se ha desarrollado un sistema de control en lazo cerrado por pulsos, denominado spikebased PID controller para FPGA, el cual se ha integrado en el esqueleto de un robot bioinspirado, BioRob X5 del CITEC de la Universidad de Bielefeld, para su uso en el desarrollo de modelos bioinspirados. El Robot, de más de 1m de largo, permite controlar las posiciones de las articulaciones usando control por pulsos y con un consumo menor de 1A para todos los grados de libertad funcionando al mismo tiempo., Compared to classic robotics, biological nervous systems respond to stimulus in a fast and efficient way regarding to the body motor movement. Classic robotic systems usually require higher computational capacity. One of the main keys of biological systems respect to robotic machines is the way the information is codded and transmitted. They use spikes. A neuron is the “basic” element that form biological nervous systems. Neurons communicate in an event-driven way through small current pulses (spikes) produced when ions are interchanged between dendrites and axons of different neurons. When neurons are arranged in networks, they allow not only the sensory information processing, but they also allow the actuation over the muscles in a spiking way. This paper presents the application of a motor control model based on spike processing, including the motor actuation in the spike domain. A close-loop control system, called spike-PID controller, has been developed for FPGA. This controller has been embedded into a bioinspired robot, called BioRob X5, at CITEC of the University of Bielefeld during a “Salvador de Madariaga” grant for a research visit in the july-september 2018 term. The robot, longer than 1 meter tall, allows the joint position control through spiking signals with a power consumption bellow 1A for the 4 DoF working at the same time.