A5019257524- Advanced Memory and Neural Computing
- Neuroscience and Neural Engineering
- CCD and CMOS Imaging Sensors
- Neural dynamics and brain function
- Ferroelectric and Negative Capacitance Devices
- Modular Robots and Swarm Intelligence
- Neural Networks and Reservoir Computing
- EEG and Brain-Computer Interfaces
- Visual Attention and Saliency Detection
- Robotics and Sensor-Based Localization
- Advanced Sensor and Energy Harvesting Materials
- Reinforcement Learning in Robotics
- Robotic Locomotion and Control
- Medical Imaging Techniques and Applications
- Robotics and Automated Systems
- Advanced Adaptive Filtering Techniques
- Robot Manipulation and Learning
- Tactile and Sensory Interactions
- Advanced Neural Network Applications
- Photoreceptor and optogenetics research
- Speech and Audio Processing
- Muscle activation and electromyography studies
- Social Robot Interaction and HRI
- Radiomics and Machine Learning in Medical Imaging
- Age of Information Optimization
Italian Institute of Technology
2016-2025
Weatherford College
2022-2024
Johns Hopkins University
2024
ETH Zurich
2004-2022
Board of the Swiss Federal Institutes of Technology
2022
Imperial College London
2022
Valeo (Germany)
2022
AGH University of Krakow
2022
University of Genoa
2001-2020
Abstract Modern computation based on von Neumann architecture is now a mature cutting-edge science. In the architecture, processing and memory units are implemented as separate blocks interchanging data intensively continuously. This transfer responsible for large part of power consumption. The next generation computer technology expected to solve problems at exascale with 10 18 calculations each second. Even though these future computers will be incredibly powerful, if they type...
Synapses are crucial elements for computation and information transfer in both real artificial neural systems. Recent experimental findings theoretical models of pulse-based networks suggest that synaptic dynamics can play a role learning codes encoding spatiotemporal spike patterns. Within the context hardware implementations networks, several analog VLSI circuits modeling functionality have been proposed. We present an overview previously proposed describe novel circuit suitable...
This paper introduces a new methodology to compute dense visual flow using the precise timings of spikes from an asynchronous event-based retina. Biological retinas, and their artificial counterparts, are totally data-driven rely on paradigm light acquisition radically different most currently used frame-grabber technologies. framework estimate local properties events' spatiotemporal space. We will show that orientation amplitude can be estimated differential approach surface defined by...
Several analog and digital brain-inspired electronic systems have been recently proposed as dedicated solutions for fast simulations of spiking neural networks. While these architectures are useful exploring the computational properties large-scale models nervous system, challenge building low-power compact physical artifacts that can behave intelligently in real world exhibit cognitive abilities still remains open. In this paper, we propose a set neuromorphic engineering to address...
The detection of consistent feature points in an image is fundamental for various kinds computer vision techniques, such as stereo matching, object recognition, target tracking and optical flow computation. This paper presents event-based approach to the corner points, which benefits from high temporal resolution, compressed visual information low latency provided by asynchronous neuromorphic camera. proposed method adapts commonly used Harris detector data, frames are replaced a stream...
Event cameras offer many advantages over standard frame-based cameras, such as low latency, high temporal resolution, and a dynamic range.They respond to pixellevel brightness changes and, therefore, provide sparse output.However, in textured scenes with rapid motion, millions of events are generated per second.Therefore, stateof-the-art event-based algorithms either require massive parallel computation (e.g., GPU) or depart from the processing paradigm.Inspired by pre-processing techniques...
Abstract Sensory information processing in robot skins currently rely on a centralized approach where signal transduction (on the body) is separated from computation and decision-making, requiring transfer of large amounts data periphery to central processors, at cost wiring, latency, fault tolerance robustness. We envision decentralized intelligence embedded sensing nodes, using unique neuromorphic methodology extract relevant robotic skins. Here we specifically address pain perception...
Abstract Upper-limb movement characterization is crucial for many applications, from research on motor control, to the extraction of relevant features driving active prostheses. While this usually performed using electrophysiological and/or kinematic measurements only, collection tactile data during grasping movements could enrich overall information about interaction with external environment. We provide a dataset collected 10 healthy volunteers performing 16 tasks, including simple (i.e.,...
Bidirectional brain-machine interfaces (BMIs) establish a two-way direct communication link 4 between the brain and external world. A decoder translates recorded neural activity into motor 5 commands an encoder delivers sensory information collected from environment directly 6 to creating closed-loop system. These two modules are typically integrated in bulky 7 devices. However, clinical support of patients with severe deficits 8 requires compact, low-power, fully implantable systems that...
Event cameras are a new technology that can enable low-latency, fast visual sensing in dynamic environments towards faster robotic vision as they respond only to changes the scene and have very high temporal resolution (<; 1μs). Moving targets produce dense spatio-temporal streams of events do not suffer from information loss "between frames", which occur when traditional used track fast-moving targets. Event-based tracking algorithms need be able follow target position within data, while...
The fast temporal-dynamics and intrinsic motion segmentation of event-based cameras are beneficial for robotic tasks that require low-latency visual tracking control, example a robot catching ball. When the event-driven iCub humanoid grasps an object its head torso move, inducing camera motion, tracked objects become no longer trivially segmented amongst mass background clutter. Current algorithms have mostly considered stationary clean event-streams with minimal This paper introduces novel...
Event cameras offer many advantages over standard frame-based cameras, such as low latency, high temporal resolution, and a dynamic range. They respond to pixel- level brightness changes and, therefore, provide sparse output. However, in textured scenes with rapid motion, millions of events are generated per second. Therefore, state- of-the-art event-based algorithms either require massive parallel computation (e.g., GPU) or depart from the processing paradigm. Inspired by pre-processing...
Spatio-temporal pattern recognition is a fundamental ability of the brain which required for numerous real-world activities. Recent deep learning approaches have reached outstanding accuracies in such tasks, but their implementation on conventional embedded solutions still very computationally and energy expensive. Tactile sensing robotic applications representative example where real-time processing efficiency are required. Following brain-inspired computing approach, we propose new...
Human Pose Estimation (HPE) is crucial as a building block for tasks that are based on the accurate understanding of human position, pose and movements. Therefore, accuracy efficiency in this echo throughout system, making it important to find efficient methods, run at fast rates online applications. The state art mainstream sensors has made considerable advances, but event camera HPE still its infancy. Event cameras boast high data capture compact structure, with advantages like dynamic...
Object tracking is an important step in many artificial vision tasks. The current state-of-the-art implementations remain too computationally demanding for the problem to be solved real time with high dynamics. This paper presents a novel real-time method visual part-based of complex objects from output asynchronous event-based camera. extends pictorial structures model introduced by Fischler and Elschlager 40 years ago introduces new formulation problem, allowing dynamic processing input at...
Event cameras are an emerging technology in computer vision, offering extremely low latency and bandwidth, as well a high temporal resolution dynamic range. Inherent data compression is achieved pixel only produced by contrast changes at the edges of moving objects. However, current trends state-of-the-art visual algorithms rely on deep-learning with networks designed to process colour intensity information contained dense arrays, but notoriously computationally heavy. While combination...
The field of neuromorphic computing holds great promise in terms advancing efficiency and capabilities by following brain-inspired principles. However, the rich diversity techniques employed research has resulted a lack clear standards for benchmarking, hindering effective evaluation advantages strengths methods compared to traditional deep-learning-based methods. This paper presents collaborative effort, bringing together members from academia industry, define benchmarks computing:...
Abstract Objective. We analyze and interpret arm forearm muscle activity in relation with the kinematics of hand pre-shaping during reaching grasping from perspective human synergistic motor control. Approach. Ten subjects performed six tasks involving reaching, object manipulation. recorded electromyographic (EMG) signals muscles a mix bipolar electrodes high-density grids electrodes. Motion capture was concurrently to estimate kinematics. Muscle synergies were extracted separately for...