Search

Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic (brain-inspired) control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this work, we have explored neuromorphic implementations of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID, and MPC, using a physics-aware simulation framework. We extensively evaluated these models with various intrinsic parameters and compared their performance with conventional CPU-based implementations. While being neural approximations, we show that neuromorphic models can perform competitively with their conventional counterparts. We provide guidelines for building neuromorphic architectures for control and describe the importance of their underlying tuning parameters and neuronal resources. Our results show that most models would converge to their optimal performances with merely 100-1,000 neurons. They also highlight the importance of hybrid conventional and neuromorphic designs, as was suggested here with the MPC controller. This study also highlights the limitations of neuromorphic implementations, particularly at higher (> 15 m/s) speeds where they tend to degrade faster than in conventional designs., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Halaly and Ezra Tsur.)

Biologically plausible computational modeling of visual perception has the potential to link high-level visual experiences to their underlying neurons' spiking dynamic. In this work, we propose a neuromorphic (brain-inspired) Spiking Neural Network (SNN)-driven model for the reconstruction of colorful images from retinal inputs. We compared our results to experimentally obtained V1 neuronal activity maps in a macaque monkey using voltage-sensitive dye imaging and used the model to demonstrate and critically explore color constancy, color assimilation, and ambiguous color perception. Our parametric implementation allows critical evaluation of visual phenomena in a single biologically plausible computational framework. It uses a parametrized combination of high and low pass image filtering and SNN-based filling-in Poisson processes to provide adequate color image perception while accounting for differences in individual perception., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2022 Cohen-Duwek et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Wheelchair-mounted robotic arms support people with upper extremity disabilities with various activities of daily living (ADL). However, the associated cost and the power consumption of responsive and adaptive assistive robotic arms contribute to the fact that such systems are in limited use. Neuromorphic spiking neural networks can be used for a real-time machine learning-driven control of robots, providing an energy efficient framework for adaptive control. In this work, we demonstrate a neuromorphic adaptive control of a wheelchair-mounted robotic arm deployed on Intel's Loihi chip. Our algorithm design uses neuromorphically represented and integrated velocity readings to derive the arm's current state. The proposed controller provides the robotic arm with adaptive signals, guiding its motion while accounting for kinematic changes in real-time. We pilot-tested the device with an able-bodied participant to evaluate its accuracy while performing ADL-related trajectories. We further demonstrated the capacity of the controller to compensate for unexpected inertia-generating payloads using online learning. Videotaped recordings of ADL tasks performed by the robot were viewed by caregivers; data summarizing their feedback on the user experience and the potential benefit of the system is reported., Competing Interests: LS was employed by company Accenture Labs. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Ehrlich, Zaidel, Weiss, Melamed Yekel, Gefen, Supic and Ezra Tsur.)

Recent findings suggest that electroencephalography (EEG) oscillations in the theta and alpha frequency-bands reflect synchronized interregional neuronal activity and are considered to reflect cognitive-control, and executive working memory mechanisms in humans. Above the age of 50 years, hypothesized pronounced alterations in alpha and theta-band power at resting or across different WM-functioning brain states may well be due to pre-dementia cognitive impairments, or increasing severity of age-related neurological disorders. Executive working memory (EWM) functioning was assessed in older-adult participants (54 to 83 years old) by obtaining their WM-related EEG oscillations and WM performance scores. WM performance and WM brain-state EEG were recorded during online-WM periods as well as during specific online WM events within EWM periods, and during resting offline-WM periods that preceded online-WM periods. Left-prefrontal alpha-power was enhanced during offline-WM periods versus online-WM periods and was significantly related to WM accuracy. Left-prefrontal alpha power and left prefrontal-parietal theta power anterior-posterior difference-gradient during online WM activity were related to reaction times (RT's). Importantly, during active-storage events, WM-offset offline-periods, and preparatory pre-retrieval events, excessive left-prefrontal alpha activity was related to poor EWM performance. The potential for developing targeted noninvasive cognition-enhancing interventions and developing clinical-monitoring EEG-based biomarkers of pathological cognitive-decline in elderly people is discussed.

Retinal direction-selectivity originates in starburst amacrine cells (SACs), which display a centrifugal preference, responding with greater depolarization to a stimulus expanding from soma to dendrites than to a collapsing stimulus. Various mechanisms were hypothesized to underlie SAC centrifugal preference, but dissociating them is experimentally challenging and the mechanisms remain debatable. To address this issue, we developed the Retinal Stimulation Modeling Environment (RSME), a multifaceted data-driven retinal model that encompasses detailed neuronal morphology and biophysical properties, retina-tailored connectivity scheme and visual input. Using a genetic algorithm, we demonstrated that spatiotemporally diverse excitatory inputs-sustained in the proximal and transient in the distal processes-are sufficient to generate experimentally validated centrifugal preference in a single SAC. Reversing these input kinetics did not produce any centrifugal-preferring SAC. We then explored the contribution of SAC-SAC inhibitory connections in establishing the centrifugal preference. SAC inhibitory network enhanced the centrifugal preference, but failed to generate it in its absence. Embedding a direction selective ganglion cell (DSGC) in a SAC network showed that the known SAC-DSGC asymmetric connectivity by itself produces direction selectivity. Still, this selectivity is sharpened in a centrifugal-preferring SAC network. Finally, we use RSME to demonstrate the contribution of SAC-SAC inhibitory connections in mediating direction selectivity and recapitulate recent experimental findings. Thus, using RSME, we obtained a mechanistic understanding of SACs' centrifugal preference and its contribution to direction selectivity., Competing Interests: The authors have declared that no competing interests exist.

Inverse kinematics is fundamental for computational motion planning. It is used to derive an appropriate state in a robot's configuration space, given a target position in task space. In this work, we investigate the performance of fully connected and residual artificial neural networks as well as recurrent, learning-based, and deep spiking neural networks for conventional and geometrically constrained inverse kinematics. We show that while highly parameterized data-driven neural networks with tens to hundreds of thousands of parameters exhibit sub-ms inference time and sub-mm accuracy, learning-based spiking architectures can provide reasonably good results with merely a few thousand neurons. Moreover, we show that spiking neural networks can perform well in geometrically constrained task space, even when configured to an energy-conserved spiking rate, demonstrating their robustness. Neural networks were evaluated on NVIDIA's Xavier and Intel's neuromorphic Loihi chip., Competing Interests: The authors declare no competing interests., (© 2021 The Author(s).)