Edge Computing in Nature: Minimal pre-processing of multi-muscle ensembles of spindle signals improves discriminability of limb movements.

Multiple proprioceptive signals, like those from muscle spindles, are thought to enable robust estimates of body configuration. Yet, it remains unknown whether spindle signals suffice to discriminate limb movements. Here, a simulated 4-musculotendon, 2-joint planar limb model produced repeated cycles of five end-point trajectories in forward and reverse directions, which generated spindle Ia and II afferent signals (proprioceptors for velocity and length, respectively) from each musculotendon. We find that cross-correlation of the 8D time series of raw firing rates (four Ia, four II) cannot discriminate among most movement pairs (∼ 29% accuracy). However, projecting these signals onto their 1st and 2nd principal components greatly improves discriminability of movement pairs (82% accuracy). We conclude that high-dimensional ensembles of muscle proprioceptors can discriminate among limb movements-but only after dimensionality reduction. This may explain the pre-processing of some afferent signals before arriving at the somatosensory cortex, such as processing of cutaneous signals at the cat's cuneate nucleus.

Estimating Center of Pressure of a Bipedal Mechanism Using a Proprioceptive Artificial Skin around its Ankles.

Estimating the Center of Pressure (CoP) under legged robots is useful to control their posture and gait. This is traditionally done using contact sensors at the base of the foot or with sensors on distal joints, which are subject to wear and damage due to impulse forces. In vertebrates, skin and ligament deformation at the ankle is a particularly rich source of sensory information for locomotion. For our bipedal mechanism, afferent signals from sensors on synthetic skin wrapped around the ankles sufficed to estimate the location of the CoP with a mean accuracy >81.5%. For this we used K-Nearest Neighbors (KNN) algorithm trained on the same force magnitude applied at four and nine ground-truth CoP locations. For a single mechanical foot (i.e., single stance), signals from skin or ligaments (i.e., elastic rubber sheets and cables, respectively) also sufficed to calculate the CoP (Mean prediction accuracy >91.3%). Moreover, the visco-elasticity of these elements serves to passively stabilize the ankle. Importantly, training the single leg case with forces of different magnitudes also resulted in similarly accurate mean CoP prediction accuracy >84.5%. We show that using bio-inspired proprioceptive skins and/or ligament arrangements can provide reliable COP predictions, while permitting arbitrary postures of the ankle and no sensors on the sole of the foot prone to wear and damage. This novel approach to estimation of the CoP can be used to improve locomotion control in a new class of bio-inspired rigid, soft and hybrid (soft-rigid) legged robots.

Data-efficient Causal Decoding of Spiking Neural Activity using Weighted Voting.

Brain-Computer Interface systems can contribute to a vast set of applications such as overcoming physical disabilities in people with neural injuries or hands-free control of devices in healthy individuals. However, having systems that can accurately interpret intention online remains a challenge in this field. Robust and data-efficient decoding-despite the dynamical nature of cortical activity and causality requirements for physical function-is among the most important challenges that limit the widespread use of these devices for real-world applications. Here, we present a causal, data-efficient neural decoding pipeline that predicts intention by first classifying recordings in short sliding windows. Next, it performs weighted voting over initial predictions up to the current point in time to report a refined final prediction. We demonstrate its utility by classifying spiking neural activity collected from the human posterior parietal cortex for a cue, delay, imaginary motor task. This pipeline provides higher classification accuracy than state-of-the-art time windowed spiking activity based causal methods, and is robust to the choice of hyper-parameters.

insideOut: A Bio-Inspired Machine Learning Approach to Estimating Posture in Robots Driven by Compliant Tendons.

Estimates of limb posture are critical for controlling robotic systems. This is generally accomplished with angle sensors at individual joints that simplify control but can complicate mechanical design and robustness. Limb posture should be derivable from each joint's actuator shaft angle but this is problematic for compliant tendon-driven systems where (i) motors are not placed at the joints and (ii) nonlinear tendon stiffness decouples the relationship between motor and joint angles. Here we propose a novel machine learning algorithm to accurately estimate joint posture during dynamic tasks by limited training of an artificial neural network (ANN) receiving motor angles and tendon tensions, analogous to biological muscle and tendon mechanoreceptors. Simulating an inverted pendulum-antagonistically-driven by motors and nonlinearly-elastic tendons-we compare how accurately ANNs estimate joint angles when trained with different sets of non-collocated sensory information generated via random motor-babbling. Cross-validating with new movements, we find that ANNs trained with motor angles and tendon tension data predict joint angles more accurately than ANNs trained without tendon tension. Furthermore, these results are robust to changes in network/mechanical hyper-parameters. We conclude that regardless of the tendon properties, actuator behavior, or movement demands, tendon tension information invariably improves joint angle estimates from non-collocated sensory signals.

Autonomous Control of a Tendon-driven Robotic Limb with Elastic Elements Reveals that Added Elasticity can Enhance Learning.

Passive elastic elements can contribute to stability, energetic efficiency, and impact absorption in both biological and robotic systems. They also add dynamical complexity which makes them more challenging to model and control. The impact of this added complexity to autonomous learning has not been thoroughly explored. This is especially relevant to tendon-driven limbs whose cables and tendons are inevitably elastic. Here, we explored the efficacy of autonomous learning and control on a simulated bio-plausible tendon-driven leg across different tendon stiffness values. We demonstrate that increasing stiffness of the simulated muscles can require more iterations for the inverse map to converge but can then perform more accurately, especially in discrete tasks. Moreover, the system is robust to subsequent changes in muscle stiffnesses and can adapt on-the-go within 5 attempts. Lastly, we test the system for the functional task of locomotion and found similar effects of muscle stiffness to learning and performance. Given that a range of stiffness values led to improved learning and maximized performance, we conclude the robot bodies and autonomous controllers-at least for tendon-driven systems-can be co-developed to take advantage of elastic elements. Importantly, this opens also the door to development efforts that recapitulate the beneficial aspects of the co-evolution of brains and bodies in vertebrates.

Simple Kinematic Feedback Enhances Autonomous Learning in Bio-Inspired Tendon-Driven Systems.

Error feedback is known to improve performance by correcting control signals in response to perturbations. Here we show how adding simple error feedback can also accelerate and robustify autonomous learning in a tendon-driven robot. We have implemented two versions of the General-to-Particular (G2P) autonomous learning algorithm using a tendon-driven leg with two joints and three tendons: one with and one without real-time kinematic feedback. We have performed a rigorous study on the performance of each system, for both simulation and physical implementation cases, over a wide range of tasks. As expected, feedback improved performance in simulation and hardware. However, we see these improvements even in the presence of sensory delays of up to 100 ms and when experiencing substantial contact collisions. Importantly, feedback accelerates learning and enhances G2P's continual refinement of the initial inverse map by providing the system with more relevant data to train on. This allows the system to perform well even after only 60 seconds of initial motor babbling.

Autonomous Functional Movements in a Tendon-Driven Limb via Limited Experience.

Robots will become ubiquitously useful only when they can use few attempts to teach themselves to perform different tasks, even with complex bodies and in dynamical environments. Vertebrates, in fact, use sparse trial-and-error to learn multiple tasks despite their intricate tendon-driven anatomies-which are particularly hard to control because they are simultaneously nonlinear, under-determined, and over-determined. We demonstrate-for the first time in simulation and hardware-how a model-free, open-loop approach allows few-shot autonomous learning to produce effective movements in a 3-tendon 2-joint limb. We use a short period of motor babbling (to create an initial inverse map) followed by building functional habits by reinforcing high-reward behavior and refinements of the inverse map in a movement's neighborhood. This biologically-plausible algorithm, which we call G2P (General-to-Particular), can potentially enable quick, robust and versatile adaptation in robots as well as shed light on the foundations of the enviable functional versatility of organisms.

Model-Free Control of Movement in a Tendon-Driven Limb via a Modified Genetic Algorithm.

Tendon-driven systems have many benefits over other actuation strategies such as torque-driven systems; however, their over-determined nature and posture-dependent actuation presents strong constraints on their control. Also, parameters or even exact structure of the model in these systems, especially in the biological ones, are normally not clear to the controller. Here, we propose a modified Genetic Algorithm that provides the tendon excursion values for the limb to follow a desired trajectory. Our results show that the proposed algorithm was able to accurately follow the desired trajectory without the model of the system being exposed to it. We believe that this method can enable biologically inspired tendon-driven mechanisms with variable mechanical structures to autonomously control their movements.

An Analytical Approach to Posture-Dependent Muscle Force and Muscle Activation Patterns.

Personalized training by taking into account individual anatomy to improve performance is a research frontier. In this paper, we first introduce an analytical method to study the pattern of changes in muscle forces as a function of posture. Our method is also able to analyze variation of maximal muscle force and muscle activation values (in various postures) as a result of posture-dependent changes in moment arms. This method also helps us evaluate the utility of person specific training. It also provides us with model based approximations for activation and muscle force patterns during different motions without a need for subject recordings, which enables athletes to have a better understanding of how each muscle contributes during each posture, in a fast and efficient way. Second, we analyze the results of this method for a simple squat move. Our results show that both maximal muscle force and muscle activation values have variable sensitivity to the moment arm values for different postures and muscles. It suggests that individually modified training plans could likely improve performance for some sets of movements.

Finger movements are mainly represented by a linear transformation of energy in band-specific ECoG signals.

Electrocardiogram (ECoG) recordings are very attractive for Brain Machine Interface (BMI) applications due to their balance between good signal to noise ratio and minimal invasiveness. The design of ECoG signal decoders is an open research area to date which requires a better understanding of the nature of these signals and how information is encoded in them. In this study, a linear and a non-linear method, Linear Regression Model (LRM) and Artificial Neural Network (ANN) respectively, were used to decode finger movements from energy in band-specific ECoG signals. It is shown that the ANN only slightly outperformed the LRM, which suggests that finger movements are mainly represented by a linear transformation of energy in band-specific ECoG signals. In addition, comparing our results to similar Electroencephalogram (EEG) studies illustrated that the spatio-temporal summation of multiple neural signals is itself linearly correlated with movement, and is not an artifact introduced by the scalp or cranium. Furthermore, a new algorithm was employed to reduce the number of spectral features of the input signals required for either of the decoding methods.

A model-based exploration of the role of pattern generating circuits during locomotor adaptation.

In this study, we used a model-based approach to explore the potential contributions of central pattern generating circuits (CPGs) during adaptation to external perturbations during locomotion. We constructed a neuromechanical modeled of locomotion using a reduced-phase CPG controller and an inverted pendulum mechanical model. Two different forms of locomotor adaptation were examined in this study: split-belt treadmill adaptation and adaptation to a unilateral, elastic force field. For each simulation, we first examined the effects of phase resetting and varying the model's initial conditions on the resulting adaptation. After evaluating the effect of phase resetting on the adaptation of step length symmetry, we examined the extent to which the results from these simple models could explain previous experimental observations. We found that adaptation of step length symmetry during split-belt treadmill walking could be reproduced using our model, but this model failed to replicate patterns of adaptation observed in response to force field perturbations. Given that spinal animal models can adapt to both of these types of perturbations, our findings suggest that there may be distinct features of pattern generating circuits that mediate each form of adaptation.