Tactile Decoding of Edge Orientation With Artificial Cuneate Neurons in Dynamic Conditions

Bare finger tactile sensing for edge orientation and contact position using excitation from fingernail

In recording and reproducing skills involving the fingertips, a sensor that measures tactile information of fingertips is important. However, when the sensor covers the finger pad, the inherent sense of touch is compromised. We introduce a new tactile sensor, a pair of a vibration motor and a 6 degrees-of-freedom sensor attached to a fingernail that enables tactile sensing without covering the fingertip. This sensor estimates finger contact information by measuring vibrations caused by an eccentric motor positioned on the fingernail. The time series of the acquired angular velocity and acceleration data were utilized to identify the edge orientation and the contact position of the touching object. The results of the conducted experiments indicated that this setup can simultaneously identify both the edge orientation and the contact position with an accuracy of 71.67%. Potential applications include remote tactile transmission, integration with a robotic finger, and the detection of grasping postures in real objects.

Human tactile sensing and sensorimotor mechanism: from afferent tactile signals to efferent motor control

In tactile sensing, decoding the journey from afferent tactile signals to efferent motor commands is a significant challenge primarily due to the difficulty in capturing population-level afferent nerve signals during active touch. This study integrates a finite element hand model with a neural dynamic model by using microneurography data to predict neural responses based on contact biomechanics and membrane transduction dynamics. This research focuses specifically on tactile sensation and its direct translation into motor actions. Evaluations of muscle synergy during in -vivo experiments revealed transduction functions linking tactile signals and muscle activation. These functions suggest similar sensorimotor strategies for grasping influenced by object size and weight. The decoded transduction mechanism was validated by restoring human-like sensorimotor performance on a tendon-driven biomimetic hand. This research advances our understanding of translating tactile sensation into motor actions, offering valuable insights into prosthetic design, robotics, and the development of next-generation prosthetics with neuromorphic tactile feedback.

Neuromorphic Tactile Edge Orientation Classification in an Unsupervised Spiking Neural Network

Dexterous manipulation in robotic hands relies on an accurate sense of artificial touch. Here we investigate neuromorphic tactile sensation with an event-based optical tactile sensor combined with spiking neural networks for edge orientation detection. The sensor incorporates an event-based vision system (mini-eDVS) into a low-form factor artificial fingertip (the NeuroTac). The processing of tactile information is performed through a Spiking Neural Network with unsupervised Spike-Timing-Dependent Plasticity (STDP) learning, and the resultant output is classified with a 3-nearest neighbours classifier. Edge orientations were classified in 10-degree increments while tapping vertically downward and sliding horizontally across the edge. In both cases, we demonstrate that the sensor is able to reliably detect edge orientation, and could lead to accurate, bio-inspired, tactile processing in robotics and prosthetics applications.

Human Somatosensory Processing and Artificial Somatosensation

In the past few years, we have gained a better understanding of the information processing mechanism in the human brain, which has led to advances in artificial intelligence and humanoid robots. However, among the various sensory systems, studying the somatosensory system presents the greatest challenge. Here, we provide a comprehensive review of the human somatosensory system and its corresponding applications in artificial systems. Due to the uniqueness of the human hand in integrating receptor and actuator functions, we focused on the role of the somatosensory system in object recognition and action guidance. First, the low-threshold mechanoreceptors in the human skin and somatotopic organization principles along the ascending pathway, which are fundamental to artificial skin, were summarized. Second, we discuss high-level brain areas, which interacted with each other in the haptic object recognition. Based on this close-loop route, we used prosthetic upper limbs as an example to highlight the importance of somatosensory information. Finally, we present prospective research directions for human haptic perception, which could guide the development of artificial somatosensory systems.

Neurorobots as a Means Toward Neuroethology and Explainable AI

Understanding why deep neural networks and machine learning algorithms act as they do is a difficult endeavor. Neuroscientists are faced with similar problems. One way biologists address this issue is by closely observing behavior while recording neurons or manipulating brain circuits. This has been called neuroethology. In a similar way, neurorobotics can be used to explain how neural network activity leads to behavior. In real world settings, neurorobots have been shown to perform behaviors analogous to animals. Moreover, a neuroroboticist has total control over the network, and by analyzing different neural groups or studying the effect of network perturbations (e.g., simulated lesions), they may be able to explain how the robot's behavior arises from artificial brain activity. In this paper, we review neurorobot experiments by focusing on how the robot's behavior leads to a qualitative and quantitative explanation of neural activity, and vice versa, that is, how neural activity leads to behavior. We suggest that using neurorobots as a form of computational neuroethology can be a powerful methodology for understanding neuroscience, as well as for artificial intelligence and machine learning.

Cuneate spiking neural network learning to classify naturalistic texture stimuli under varying sensing conditions

We implemented a functional neuronal network that was able to learn and discriminate haptic features from biomimetic tactile sensor inputs using a two-layer spiking neuron model and homeostatic synaptic learning mechanism. The first order neuron model was used to emulate biological tactile afferents and the second order neuron model was used to emulate biological cuneate neurons. We have evaluated 10 naturalistic textures using a passive touch protocol, under varying sensing conditions. Tactile sensor data acquired with five textures under five sensing conditions were used for a synaptic learning process, to tune the synaptic weights between tactile afferents and cuneate neurons. Using post-learning synaptic weights, we evaluated the individual and population cuneate neuron responses by decoding across 10 stimuli, under varying sensing conditions. This resulted in a high decoding performance. We further validated the decoding performance across stimuli, irrespective of sensing velocities using a set of 25 cuneate neuron responses. This resulted in a median decoding performance of 96% across the set of cuneate neurons. Being able to learn and perform generalized discrimination across tactile stimuli, makes this functional spiking tactile system effective and suitable for further robotic applications.

Morphological Neural Computation Restores Discrimination of Naturalistic Textures in Trans-radial Amputees

Humans rely on their sense of touch to interact with the environment. Thus, restoring lost tactile sensory capabilities in amputees would advance their quality of life. In particular, texture discrimination is an important component for the interaction with the environment, but its restoration in amputees has been so far limited to simplified gratings. Here we show that naturalistic textures can be discriminated by trans-radial amputees using intraneural peripheral stimulation and tactile sensors located close to the outer layer of the artificial skin. These sensors exploit the morphological neural computation (MNC) approach, i.e., the embodiment of neural computational functions into the physical structure of the device, encoding normal and shear stress to guarantee a faithful neural temporal representation of stimulus spatial structure. Two trans-radial amputees successfully discriminated naturalistic textures via the MNC-based tactile feedback. The results also allowed to shed light on the relevance of spike temporal encoding in the mechanisms used to discriminate naturalistic textures. Our findings pave the way to the development of more natural bionic limbs.