Nicoletta Risi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nicoletta Risi has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Giacomo Indiveri
University of Zürich and ETH Zürich
4 shared publications - Elisa Donati
University of Zurich and ETHZ
3 shared publications - Leigh Ann Mrotek
Institute for Clinical and Translational Research, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
3 shared publications - Robert A. Scheidt
Department of Biomedical Engineering, Marquette University
3 shared publications - Valay A. Shah
Department of Applied Kinesiology and Physiology, University of Florida, Gainesville, FL, USA
3 shared publications - Maura Casadio
Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, 16145 Genoa, Italy
2 shared publications
Latest Publications
- 20 September 2023
- Published by Springer Nature
- p. 33-42
Fall Detection with Event-Based Data: A Case Study
- 20 September 2023
- Published by Springer Nature
- p. 33-42
Fall Detection with Event-Based Data: A Case Study
- Open Access
FPGA Implementation of An Event-driven Saliency-based Selective Attention Model
Artificial vision systems of autonomous agents face very difficult challenges, as their vision sensors are required to transmit vast amounts of information to the processing stages, and to process it in real-time. One first approach to reduce data transmission is to use event-based vision sensors, whose pixels produce events only when there are changes in the input. However, even for event-based vision, transmission and processing of visual data can be quite onerous. Currently, these challenges are solved by using high-speed communication links and powerful machine vision processing hardware. But if resources are limited, instead of processing all the sensory information in parallel, an effective strategy is to divide the visual field into several small sub-regions, choose the region of highest saliency, process it, and shift serially the focus of attention to regions of decreasing saliency. This strategy, commonly used also by the visual system of many animals, is typically referred to as ``selective attention''. Here we present a digital architecture implementing a saliency-based selective visual attention model for processing asynchronous event-based sensory information received from a DVS. For ease of prototyping, we use a standard digital design flow and map the architecture on an FPGA. We describe the architecture block diagram highlighting the efficient use of the available hardware resources demonstrated through experimental results exploiting a hardware setup where the FPGA interfaced with the DVS camera.
Open AccessFPGA Implementation of An Event-driven Saliency-based Selective Attention Model
Artificial vision systems of autonomous agents face very difficult challenges, as their vision sensors are required to transmit vast amounts of information to the processing stages, and to process it in real-time. One first approach to reduce data transmission is to use event-based vision sensors, whose pixels produce events only when there are changes in the input. However, even for event-based vision, transmission and processing of visual data can be quite onerous. Currently, these challenges are solved by using high-speed communication links and powerful machine vision processing hardware. But if resources are limited, instead of processing all the sensory information in parallel, an effective strategy is to divide the visual field into several small sub-regions, choose the region of highest saliency, process it, and shift serially the focus of attention to regions of decreasing saliency. This strategy, commonly used also by the visual system of many animals, is typically referred to as ``selective attention''. Here we present a digital architecture implementing a saliency-based selective visual attention model for processing asynchronous event-based sensory information received from a DVS. For ease of prototyping, we use a standard digital design flow and map the architecture on an FPGA. We describe the architecture block diagram highlighting the efficient use of the available hardware resources demonstrated through experimental results exploiting a hardware setup where the FPGA interfaced with the DVS camera.
- 25 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (4) , 546-556
Closed-Loop Spiking Control on a Neuromorphic Processor Implemented on the iCub
Neuromorphic engineering promises the deployment of low latency, adaptive and low power systems that can lead to the design of truly autonomous artificial agents. However, many building blocks for developing a fully neuromorphic artificial agent are still missing. While neuromorphic sensing, perception, and decision-making building blocks are quite mature, the ones for motor control and actuation are lagging behind. In this paper we present a closed-loop motor controller implemented on a mixed-signal analog/digital neuromorphic processor which emulates a spiking neural network that continuously calculates an error signal from the desired target and the feedback signals. The system uses population coding and recurrent Winner-Take-All networks to encode the signals robustly. Recurrent connections within each population are used to speed up the convergence, decrease the effect of mismatch and improve selectivity. The error signal computed in this way is then fed into three additional populations of spiking neurons which produce the proportional, integral and derivative terms of classical controllers exploiting the temporal dynamics of the network synapses and neurons. To validate this approach we interfaced this neuromorphic motor controller with an iCub robot simulator. We tested our spiking controller in a single joint control task for the robot head yaw. We demonstrate the correct performance of the spiking controller in a step response experiment and apply it to a target pursuit task.
- 25 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (4) , 546-556
Closed-Loop Spiking Control on a Neuromorphic Processor Implemented on the iCub
Neuromorphic engineering promises the deployment of low latency, adaptive and low power systems that can lead to the design of truly autonomous artificial agents. However, many building blocks for developing a fully neuromorphic artificial agent are still missing. While neuromorphic sensing, perception, and decision-making building blocks are quite mature, the ones for motor control and actuation are lagging behind. In this paper we present a closed-loop motor controller implemented on a mixed-signal analog/digital neuromorphic processor which emulates a spiking neural network that continuously calculates an error signal from the desired target and the feedback signals. The system uses population coding and recurrent Winner-Take-All networks to encode the signals robustly. Recurrent connections within each population are used to speed up the convergence, decrease the effect of mismatch and improve selectivity. The error signal computed in this way is then fed into three additional populations of spiking neurons which produce the proportional, integral and derivative terms of classical controllers exploiting the temporal dynamics of the network synapses and neurons. To validate this approach we interfaced this neuromorphic motor controller with an iCub robot simulator. We tested our spiking controller in a single joint control task for the robot head yaw. We demonstrate the correct performance of the spiking controller in a step response experiment and apply it to a target pursuit task.
- Open Access
- 13 November 2020
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 14
A Spike-Based Neuromorphic Architecture of Stereo Vision
The problem of finding stereo correspondences in binocular vision is solved effortlessly in nature and yet it is still a critical bottleneck for artificial machine vision systems. As temporal information is a crucial feature in this process, the advent of event-based vision sensors and dedicated event-based processors promises to offer an effective approach to solve the stereo matching problem. Indeed, event-based neuromorphic hardware provides an optimal substrate for fast, asynchronous computation, that can make explicit use of precise temporal coincidences. Although several biologically-inspired solutions have already been proposed, the performance benefits of combining event-based sensing with asynchronous and parallel computation are yet to be explored. Here we present a spike-based stereo-vision system that leverages the advantages of brain-inspired neuromorphic computing by interfacing two event-based vision sensors to an event-based mixed-signal analog/digital neuromorphic processor. We describe a prototype interface designed to enable the emulation of a stereo-vision system on neuromorphic hardware and we quantify the stereo matching performance with two datasets. Our results demonstrate a proof of concept for a low-latency, end-to-end event-based, neuromorphic architecture of stereo vision.
- 13 November 2020
- Published by Frontiers Media SA in Frontiers in Neurorobotics
- Vol. 14
Open AccessA Spike-Based Neuromorphic Architecture of Stereo Vision
The problem of finding stereo correspondences in binocular vision is solved effortlessly in nature and yet it is still a critical bottleneck for artificial machine vision systems. As temporal information is a crucial feature in this process, the advent of event-based vision sensors and dedicated event-based processors promises to offer an effective approach to solve the stereo matching problem. Indeed, event-based neuromorphic hardware provides an optimal substrate for fast, asynchronous computation, that can make explicit use of precise temporal coincidences. Although several biologically-inspired solutions have already been proposed, the performance benefits of combining event-based sensing with asynchronous and parallel computation are yet to be explored. Here we present a spike-based stereo-vision system that leverages the advantages of brain-inspired neuromorphic computing by interfacing two event-based vision sensors to an event-based mixed-signal analog/digital neuromorphic processor. We describe a prototype interface designed to enable the emulation of a stereo-vision system on neuromorphic hardware and we quantify the stereo matching performance with two datasets. Our results demonstrate a proof of concept for a low-latency, end-to-end event-based, neuromorphic architecture of stereo vision.
- 1 July 2019
- Published by American Physiological Society in Journal of Neurophysiology
- Vol. 122 (1) , 22-38
Supplemental vibrotactile feedback of real-time limb position enhances precision of goal-directed reaching
We examined vibrotactile stimulation as a form of supplemental limb state feedback to enhance planning and ongoing control of goal-directed movements. Subjects wore a two-dimensional vibrotactile display on their nondominant arm while performing horizontal planar reaching with the dominant arm. The vibrotactile display provided feedback of hand position such that small hand displacements were more easily discriminable using vibrotactile feedback than with intrinsic proprioceptive feedback. When subjects relied solely on proprioception to capture visuospatial targets, performance was degraded by proprioceptive drift and an expansion of task space. By contrast, reach accuracy was enhanced immediately when subjects were provided vibrotactile feedback and further improved over 2 days of training. Improvements reflected resolution of proprioceptive drift, which occurred only when vibrotactile feedback was active, demonstrating that benefits of vibrotactile feedback are due, in part to its integration into the ongoing control of movement. A partial resolution of task space expansion persisted even when vibrotactile feedback was inactive, demonstrating that training with vibrotactile feedback also induced changes in movement planning. However, the benefits of vibrotactile feedback come at a cognitive cost. All subjects adopted a stereotyped strategy wherein they attempted to capture targets by moving first along one axis of the vibrotactile display and then the other. For most subjects, this inefficient approach did not resolve over two bouts of training performed on separate days, suggesting that additional training is needed to integrate vibrotactile feedback into the planning and online control of goal-directed reaching in a way that promotes smooth and efficient movement. NEW & NOTEWORTHY A two-dimensional vibrotactile display provided state (not error) feedback to enhance control of a moving limb. Subjects learned to use state feedback to perform blind reaches with accuracy and precision exceeding that attained using intrinsic proprioception alone. Feedback utilization incurred substantial cognitive cost: subjects moved first along one axis of the vibrotactile display, then the other. This stereotyped control strategy must be overcome if vibrotactile limb state feedback is to promote naturalistic limb movements.
- 1 July 2019
- Published by American Physiological Society in Journal of Neurophysiology
- Vol. 122 (1) , 22-38
Supplemental vibrotactile feedback of real-time limb position enhances precision of goal-directed reaching
We examined vibrotactile stimulation as a form of supplemental limb state feedback to enhance planning and ongoing control of goal-directed movements. Subjects wore a two-dimensional vibrotactile display on their nondominant arm while performing horizontal planar reaching with the dominant arm. The vibrotactile display provided feedback of hand position such that small hand displacements were more easily discriminable using vibrotactile feedback than with intrinsic proprioceptive feedback. When subjects relied solely on proprioception to capture visuospatial targets, performance was degraded by proprioceptive drift and an expansion of task space. By contrast, reach accuracy was enhanced immediately when subjects were provided vibrotactile feedback and further improved over 2 days of training. Improvements reflected resolution of proprioceptive drift, which occurred only when vibrotactile feedback was active, demonstrating that benefits of vibrotactile feedback are due, in part to its integration into the ongoing control of movement. A partial resolution of task space expansion persisted even when vibrotactile feedback was inactive, demonstrating that training with vibrotactile feedback also induced changes in movement planning. However, the benefits of vibrotactile feedback come at a cognitive cost. All subjects adopted a stereotyped strategy wherein they attempted to capture targets by moving first along one axis of the vibrotactile display and then the other. For most subjects, this inefficient approach did not resolve over two bouts of training performed on separate days, suggesting that additional training is needed to integrate vibrotactile feedback into the planning and online control of goal-directed reaching in a way that promotes smooth and efficient movement. NEW & NOTEWORTHY A two-dimensional vibrotactile display provided state (not error) feedback to enhance control of a moving limb. Subjects learned to use state feedback to perform blind reaches with accuracy and precision exceeding that attained using intrinsic proprioception alone. Feedback utilization incurred substantial cognitive cost: subjects moved first along one axis of the vibrotactile display, then the other. This stereotyped control strategy must be overcome if vibrotactile limb state feedback is to promote naturalistic limb movements.
- Top Cited Papers
- 27 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 13 (5) , 795-803
Discrimination of EMG Signals Using a Neuromorphic Implementation of a Spiking Neural Network
An accurate description of muscular activity plays an important role in the clinical diagnosis and rehabilitation research. The electromyography (EMG) is the most used technique to make accurate descriptions of muscular activity. The EMG is associated with the electrical changes generated by the activity of the motor neurons. Typically, to decode the muscular activation during different movements, a large number of individual motor neurons are monitored simultaneously, producing large amounts of data to be transferred and processed by the computing devices. In this work, we follow an alternative approach that can be deployed locally on the sensor side. We propose a neuromorphic implementation of a spiking neural network (SNN) to extract spatio-temporal information of EMG signals locally and classify hand-gestures with very low power consumption. We present experimental results on the input data stream using a mixed signal analog/digital neuromorphic processor. We performed a thorough investigation on the performance of the SNN implemented on the chip, by: i) calculating PCA on the activity of the silicon neurons at the input and the hidden layers to show how the network helps in separating the samples of different classes; ii) performing classification of the data using state-of-the- art SVM and logistic regression methods and a hardware-friendly spike-based read-out. The traditional algorithm achieved a classification rate of 84% and 81%, respectively, and the spiking learning method achieved 74%. The power consumption of the SNN is 0:05 mW, showing the potential of this approach for ultra-low power processing.
- 27 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Circuits and Systems
- Vol. 13 (5) , 795-803
Top Cited PapersDiscrimination of EMG Signals Using a Neuromorphic Implementation of a Spiking Neural Network
An accurate description of muscular activity plays an important role in the clinical diagnosis and rehabilitation research. The electromyography (EMG) is the most used technique to make accurate descriptions of muscular activity. The EMG is associated with the electrical changes generated by the activity of the motor neurons. Typically, to decode the muscular activation during different movements, a large number of individual motor neurons are monitored simultaneously, producing large amounts of data to be transferred and processed by the computing devices. In this work, we follow an alternative approach that can be deployed locally on the sensor side. We propose a neuromorphic implementation of a spiking neural network (SNN) to extract spatio-temporal information of EMG signals locally and classify hand-gestures with very low power consumption. We present experimental results on the input data stream using a mixed signal analog/digital neuromorphic processor. We performed a thorough investigation on the performance of the SNN implemented on the chip, by: i) calculating PCA on the activity of the silicon neurons at the input and the hidden layers to show how the network helps in separating the samples of different classes; ii) performing classification of the data using state-of-the- art SVM and logistic regression methods and a hardware-friendly spike-based read-out. The traditional algorithm achieved a classification rate of 84% and 81%, respectively, and the spiking learning method achieved 74%. The power consumption of the SNN is 0:05 mW, showing the potential of this approach for ultra-low power processing.
- 5 June 2018
- Published by Springer Nature
- Vol. 10893, 3-14
Effect of Dual Tasking on Vibrotactile Feedback Guided Reaching – A Pilot Study
Vibrotactile feedback (VTF) has been proposed as a non-invasive way to augment impaired or lost kinesthetic feedback in certain patient populations, thereby enhancing the real-time control of purposeful limb movements and quality of life. We used a dual tasking scenario to investigate the effects of cognitive load and short-term VTF training on VTF-guided reaching. Participants grasped the handle of a planar manipulandum with one hand and received VTF of its motion via a vibrotactile display attached to the non-moving arm. We asked participants to simultaneously perform VTF-guided reaching and a choice reaction time task both before and after training with VTF-guided reaching. Participants readily used VTF to guide goal-directed hand movements in the absence of visual feedback in the dual-task setting, even prior to training. This capability came at the cost of increased movement completion time. Short-term training on VTF-guided reaching induced significant improvements in target capture errors. Pre- and post-training comparisons of dual-task performance found training-related improvements in VTF-guided reach accuracy were resistant to dual-task interference. We found no training-related improvements in movement completion time or in the performance of the secondary task. These results indicate that VTF can be used to complete goal-directed reaches in a dual-task situation, and that a single short bout of training sufficed for participants to begin the transition between the cognitive and associative phases of learning for the integration of VTF into the planning and ongoing control of reaching movements.
- 5 June 2018
- Published by Springer Nature
- Vol. 10893, 3-14
Effect of Dual Tasking on Vibrotactile Feedback Guided Reaching – A Pilot Study
Vibrotactile feedback (VTF) has been proposed as a non-invasive way to augment impaired or lost kinesthetic feedback in certain patient populations, thereby enhancing the real-time control of purposeful limb movements and quality of life. We used a dual tasking scenario to investigate the effects of cognitive load and short-term VTF training on VTF-guided reaching. Participants grasped the handle of a planar manipulandum with one hand and received VTF of its motion via a vibrotactile display attached to the non-moving arm. We asked participants to simultaneously perform VTF-guided reaching and a choice reaction time task both before and after training with VTF-guided reaching. Participants readily used VTF to guide goal-directed hand movements in the absence of visual feedback in the dual-task setting, even prior to training. This capability came at the cost of increased movement completion time. Short-term training on VTF-guided reaching induced significant improvements in target capture errors. Pre- and post-training comparisons of dual-task performance found training-related improvements in VTF-guided reach accuracy were resistant to dual-task interference. We found no training-related improvements in movement completion time or in the performance of the secondary task. These results indicate that VTF can be used to complete goal-directed reaches in a dual-task situation, and that a single short bout of training sufficed for participants to begin the transition between the cognitive and associative phases of learning for the integration of VTF into the planning and ongoing control of reaching movements.
- Open Access
Supplemental vibrotactile feedback of real-time limb position enhances precision of goal-directed reaching
We examined vibrotactile stimulation as a form of supplemental limb state feedback to enhance on-going control goal-directed movements. Subjects wore a two-dimensional vibrotactile display on their non-dominant arm while performing horizontal planar reaching movements with their dominant arm. The vibrotactile display provided feedback of hand position such that small hand displacements were more easily discriminable using vibrotactile feedback than with intrinsic proprioceptive feedback. When subjects relied solely on proprioceptive feedback to capture visuospatial targets, target capture performance was degraded by proprioceptive drift and an expansion of task space. By contrast, reach accuracy was enhanced immediately when subjects were provided vibrotactile feedback, and further improved over two days of training. Improvements reflected a resolution of proprioceptive drift which occurred only when vibrotactile feedback was active, demonstrating that the benefits of vibrotactile feedback are due in part to its integration into the ongoing control of movement. A partial resolution of task space expansion that persisted even when the vibrotactile feedback was inactive demonstrated that training with vibrotactile feedback also induced changes in movement planning. However, the benefits of vibrotactile feedback come at a cognitive cost. All subjects adopted a stereotyped, movement decomposition strategy wherein they attempted to capture targets by moving first along one axis of the vibrotactile display and then the other. For most subjects, this inefficient movement approach did not resolve over two bouts of training performed on separate days, suggesting that additional training is needed to fully integrate vibrotactile feedback into the planning and online control of goal-directed reaching.
Open AccessSupplemental vibrotactile feedback of real-time limb position enhances precision of goal-directed reaching
We examined vibrotactile stimulation as a form of supplemental limb state feedback to enhance on-going control goal-directed movements. Subjects wore a two-dimensional vibrotactile display on their non-dominant arm while performing horizontal planar reaching movements with their dominant arm. The vibrotactile display provided feedback of hand position such that small hand displacements were more easily discriminable using vibrotactile feedback than with intrinsic proprioceptive feedback. When subjects relied solely on proprioceptive feedback to capture visuospatial targets, target capture performance was degraded by proprioceptive drift and an expansion of task space. By contrast, reach accuracy was enhanced immediately when subjects were provided vibrotactile feedback, and further improved over two days of training. Improvements reflected a resolution of proprioceptive drift which occurred only when vibrotactile feedback was active, demonstrating that the benefits of vibrotactile feedback are due in part to its integration into the ongoing control of movement. A partial resolution of task space expansion that persisted even when the vibrotactile feedback was inactive demonstrated that training with vibrotactile feedback also induced changes in movement planning. However, the benefits of vibrotactile feedback come at a cognitive cost. All subjects adopted a stereotyped, movement decomposition strategy wherein they attempted to capture targets by moving first along one axis of the vibrotactile display and then the other. For most subjects, this inefficient movement approach did not resolve over two bouts of training performed on separate days, suggesting that additional training is needed to fully integrate vibrotactile feedback into the planning and online control of goal-directed reaching.