Search

Modern manufacturing and assembly environments are characterized by a high variability in the built process which challenges human–robot cooperation. To reduce the cognitive workload of the operator, the robot should not only be able to learn from experience but also to plan and decide autonomously. Here, we present an approach based on Dynamic Neural Fields that apply brain-like computations to endow a robot with these cognitive functions. A neural integrator is used to model the gradual accumulation of sensory and other evidence as time-varying persistent activity of neural populations. The decision to act is modeled by a competitive dynamics between neural populations linked to different motor behaviors. They receive the persistent activation pattern of the integrators as input. In the first experiment, a robot learns rapidly by observation the sequential order of object transfers between an assistant and an operator to subsequently substitute the assistant in the joint task. The results show that the robot is able to proactively plan the series of handovers in the correct order. In the second experiment, a mobile robot searches at two different workbenches for a specific object to deliver it to an operator. The object may appear at the two locations in a certain time period with independent probabilities unknown to the robot. The trial-by-trial decision under uncertainty is biased by the accumulated evidence of past successes and choices. The choice behavior over a longer period reveals that the robot achieves a high search efficiency in stationary as well as dynamic environments., The work received financial support from FCT through the PhD fellowships PD/BD/128183/2016 and SFRH/BD/124912/2016, the project “Neurofield” (PTDC/MAT-APL/31393/2017) and the research centre CMAT within the project UID/MAT/00013/2013.

Neurofeedback training (NFT) is a technique often proposed to train brain activity SR with promising results. However, some criticism has been raised due to the lack of evaluation, reliability, and validation of its learning effects. The current work evaluates the hypothesis that SR learning may be improved by priming the subject before NFT with guided mindfulness meditation (MM). The proposed framework was tested in a two-way parallel-group randomized controlled intervention with a single session alpha NFT, in a simplistic serious game design. Sixty-two healthy naïve subjects, aged between 18 and 43 years, were divided into MM priming and no-priming groups. Although both the EG and CG successfully attained the up-regulation of alpha rhythms (F(1,59) = 20.67, p &lt, 0.001, ηp2 = 0.26), the EG showed a significantly enhanced ability (t(29) = 4.38, p &lt, 0.001) to control brain activity, compared to the CG (t(29) = 1.18, p &gt, 0.1). Furthermore, EG superior performance on NFT seems to be explained by the subject’s lack of awareness at pre-intervention, less vigour at post-intervention, increased task engagement, and a relaxed non-judgemental attitude towards the NFT tasks. This study is a preliminary validation of the proposed assisted priming framework, advancing some implicit and explicit metrics about its efficacy on NFT performance, and a promising tool for improving naïve “users” self-regulation ability.

Accepted Manuscript, The literature on gait analysis in Vascular Parkinsonism (VaP), addressing issues such as variability, foot clearance patterns, and the effect of levodopa, is scarce. This study investigates whether spatiotemporal, foot clearance and stride-to-stride variability analysis can discriminate VaP, and responsiveness to levodopa. Fifteen healthy subjects, 15 Idiopathic Parkinson's Disease (IPD) patients and 15 VaP patients, were assessed in two phases: before (Off-state), and one hour after (On-state) the acute administration of a suprathreshold (1.5 times the usual) levodopa dose. Participants were asked to walk a 30-meter continuous course at a self-selected walking speed while wearing foot-worn inertial sensors. For each gait variable, mean, coefficient of variation (CV), and standard deviations SD1 and SD2 obtained by Poincaré analysis were calculated. General linear models (GLMs) were used to identify group differences. Patients were subject to neuropsychological evaluation (MoCA test) and Brain MRI. VaP patients presented lower mean stride velocity, stride length, lift-off and strike angle, and height of maximum toe (later swing) (p, projects NORTE-01-0145-FEDER-000016 (NanoSTIMA) and NORTE-01-0145-FEDER-000026 (DeM), financed by the Regional Operational Program of the North (NORTE2020), under PORTUGAL2020 and FEDER.

Many of our sequential activities require that behaviors must be both precisely timed and put in the proper order. This article presents a neurocomputational model based on the theoretical framework of dynamic neural fields that supports the rapid learning and flexible adaptation of coupled order-timing representations of sequential events. A key assumption is that elapsed time is encoded in the monotonic buildup of self-stabilized neural population activity representing event memory. A stable activation gradient over subpopulations carries the information of an entire sequence. With robotics applications in mind, we test the model in simulations of learning by observation paradigm, in which the cognitive agent first memorizes the order and relative timing of observed events and, subsequently, recalls the information from memory taking potential speed constraints into account. Model robustness is tested by systematically varying sequence complexity along the temporal and the ordinal dimensions. Furthermore, an adaptation rule is proposed that allows the agent to adjust in a single trial a learned timing pattern to a changing temporal context. The simulation results are discussed with respect to our goal to endow autonomous robots with the capacity to efficiently learn complex sequences with time constraints, supporting more natural human-robot interactions., This work was supported in part by FCT (Portuguese Foundation for Science and Technology) through the Ph.D. Fellowship under Grant PD/BD/128183/2016; in part by the European Structural and Investment Funds in the FEDER Component, through the Operational Competitiveness and Internationalization Programme (COMPETE 2020) and National Funds, through the FCT under Project PTDC/MAT-APL/31393/2017 (NEUROFIELD) and Project POCI-01-0247FEDER-039334; and in part by Research and Development Units Project Scope under Project UIDB/00319/2020 and Project UIDB/00013/2020.

Idiopathic Parkinson's disease (IPD) and vascular parkinsonism (VaP) present highly overlapping phenotypes, making it challenging to distinguish between these two parkinsonian syndromes. Recent evidence suggests that gait assessment and response to levodopa medication may assist in the objective evaluation of clinical differences. In this paper, we propose a new approach for gait pattern differentiation that uses convolutional neural networks (CNNs) based on gait time series with and without the influence of levodopa medication. Wearable sensors positioned on both feet were used to acquire gait data from 14 VaP patients, 15 IPD patients, and 34 healthy subjects. An individual's gait features are affected by physical characteristics, including age, height, weight, sex, and walking speed or stride length. Therefore, to reduce bias due to intersubject variations, a multiple regression normalization approach was used to obtain gait data. Recursive feature elimination using the linear support vector machine, lasso, and random forest were applied to infer the optimal feature subset that led to the best results. CNNs were implemented by means of various hyperparameters and feature subsets. The best CNN classifiers achieved accuracies of 79.33%±6.46, 82.33%±10.62, and 86.00%±7.12 without (off state), with (on state), and with the simultaneous consideration of the effect of levodopa medication (off/on state), respectively. The response to levodopa medication improved classification performance. Based on gait time series and response to medication, the proposed approach differentiates between IPD and VaP gait patterns and reveals a high accuracy rate, which might prove useful when distinguishing other diseases related to movement disorders., This research was partially financed by NORTE2020 and FEDER within the project NORTE-01–0145-FEDER- 000026 (DeM-Deus Ex Machina) and by Portuguese Funds through FCT (Fundação para a Ciência e a Tecnologia) within the Projects UIDB/00013/2020, UIDP/00013/2020 and UIDB/00319/2020.

Programming by demonstration allows non-experts in robot programming to train the robots in an intuitive manner. However, this learning paradigm requires multiple demonstrations of the same task, which can be time-consuming and annoying for the human tutor. To overcome this limitation, we propose a fast learning system – based on neural dynamics – that permits collaborative robots to memorize sequential information from single task demonstrations by a human-tutor. Important, the learning system allows not only to memorize long sequences of sub-goals in a task but also the time interval between them. We implement this learning system in Sawyer (a collaborative robot from Rethink Robotics) and test it in a construction task, where the robot observes several human-tutors with different preferences on the sequential order to perform the task and different behavioral time scales. After learning, memory recall (of what and when to do a sub-task) allows the robot to instruct inexperienced human workers, in a particular human-centered task scenario., POFC - Programa Operacional Temático Factores de Competitividade(POCI-01-0247-FEDER-024541)

Fabry disease (FD) is a rare disease commonly complicated with white matter lesions (WMLs). WMLs, which have extensively been associated with gait impairment, justify further investigation of its implication in FD. This study aims to identify a set of gait characteristics to discriminate FD patients with/without WMLs and healthy controls. Seventy-six subjects walked through a predefined circuit using gait sensors that continuously acquired different stride features. Data were normalized using multiple regression normalization taking into account the subject physical properties, with the assessment of 32 kinematic gait variables. A filter method (Mann Whitney U test and Pearson correlation) followed by a wrapper method (recursive feature elimination (RFE) for Logistic Regression (LR) and Support Vector Machine (SVM) and information gain for Random Forest (RF)) were used for feature selection. Then, five different classifiers (LR, SVM Linear and RBF kernel, RF, and K-Nearest Neighbors (KNN)) based on different selected set features were evaluated. For FD patients with WMLs versus controls the highest accuracy of 72% was obtained using LR based on 3 gait variables: pushing, foot flat, and maximum toe clearance 2. For FD patients without WMLs versus controls, the best performance was observed using LR and SVM RBF kernel based on loading, foot flat, minimum toe clearance, stride length variability, loading variability, and lift-off angle variability with an accuracy of 83%. These findings are the first step to demonstrate the potential of machine learning techniques based on gait variables as a complementary tool to understand the role of WMLs in the gait impairment of FD., This work has been supported by FCT -Fundacao para a Ciencia e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020 and UIDB/00013/2020.

The goal of this study was grouping patients with parkinsonism that share similar gait characteristics based on principal component analysis (PCA). Spatiotemporal gait data during self-selected walking were obtained from 15 patients with Vascular Parkinsonism, 15 patients with Idiopathic Parkinson's Disease and 15 Controls. PCA was used to reduce the dimensionality of 12 gait characteristics for the 45 subjects. Fuzzy C-mean cluster analysis was performed plotting the first two principal components, which accounted for 84.1% of the total variability. Results indicates that it is possible to quantitatively differentiate different gait types in patients with parkinsonism using PCA. Objective graphical classification of gait patterns could assist in clinical evaluation as well as aid treatment planning., POCI-01-0145-FEDER-006961, National Funds through the FCT as part of project UID/EEA/50014/2013

This paper presents a novel analytic method to uniquely solve inverse kinematics of 7 degrees-of-freedom manipulators while avoiding joint limits and singularities. Two auxiliary parameters are introduced to deal with the self-motion manifolds: the global configuration (GC), which specifies the branch of inverse kinematics solutions; and the arm angle (ψ) that parametrizes the elbow redundancy within the specified branch. The relations between the joint angles and the arm angle are derived, in order to map the joint limits and singularities to arm angle values. Then, intervals of feasible arm angles for the specified target pose and global configuration are determined, taking joint limits and singularities into account. A simple metric is proposed to compute the elbow position according to the feasible intervals. When the arm angle is determined, the joint angles can be uniquely calculated from the position-based inverse kinematics algorithm. The presented method does not exhibit the disadvantages inherent to the use of the Jacobian matrix and can be implemented in real-time control systems. This novel algorithm is the first position-based inverse kinematics algorithm to solve both global and local manifolds, using a redundancy resolution strategy to avoid singularities and joint limits., This work was partially supported by the NETT Project [FP7-PEOPLE-2011-ITN-289146]; and Foundation for Science and Technology, Portugal [grant number SFRH/BD/86499/2012]., info:eu-repo/semantics/publishedVersion

The continuous real-time motor interaction with our environment requires the capacity to measure and produce time intervals in a highly flexible manner. Recent neurophysiological evidence suggests that the neural computational principles supporting this capacity may be understood from a dynamical systems perspective: Inputs and initial conditions determine how a recurrent neural network evolves from a “resting state” to a state triggering the action. Here we test this hypothesis in a time measurement and time reproduction experiment using a model of a robust neural integrator based on the theoretical framework of dynamic neural fields. During measurement, the temporal accumulation of input leads to the evolution of a self-stabilized bump whose amplitude reflects elapsed time. During production, the stored information is used to reproduce on a trial-by-trial basis the time interval either by adjusting input strength or initial condition of the integrator. We discuss the impact of the results on our goal to endow autonomous robots with a human-like temporal cognition capacity for natural human-robot interactions., The work received financial support from FCT through the PhD fellowship PD/BD/128183/2016, the project ”Neurofield” (POCI-01-0145-FEDER-031393) and the research centre CMAT within the project UID/MAT/00013/2013.

Neural field models, formalized by integro-differential equations, describe the large-scale spatio-temporal dynamics of neuronal populations [1]. They have been used in the past as a framework for modeling a wide range of brain functions, including multi-item working memory [2]. Neural field equations support spatially localized regions of high activity (or bumps) that are initially triggered by brief sensory inputs and subsequently become self-sustained by recurrent interactions within the neural population. We apply a special class of oscillatory coupling functions and analyze how the shape and spatial extension of multi-bump solutions change as the spatial ranges of excitation and inhibition within the field are varied [3]. More precisely, we use numerical continuation to find and follow solutions of neural field equations as the parameter controlling the distance between consecutive zeros of the coupling function is varied [4]. Important for a working memory application (e.g. [5]), we investigate how changes in this parameter affect the shape of bump solutions and therefore the maximum number of bumps that may exist in a given finite interval., The work received financial support from FCT through the PhD fellowship PD/BD/128183/2016.

"Available online 3 March 2016", We study the conditions for the formation of multiple regions of high activity or “bumps” in a one-dimensional, homogeneous neural field with localized inputs. Stable multi-bump solutions of the integro-differential equation have been proposed as a model of a neural population representation of remembered external stimuli. We apply a class of oscillatory coupling functions and first derive criteria to the input width and distance, which relate to the synaptic couplings that guarantee the existence and stability of one and two regions of high activity. These input-induced patterns are attracted by the corresponding stable one-bump and two-bump solutions when the input is removed. We then extend our analytical and numerical investigation to NN-bump solutions showing that the constraints on the input shape derived for the two-bump case can be exploited to generate a memory of N>2N>2 localized inputs. We discuss the pattern formation process when either the conditions on the input shape are violated or when the spatial ranges of the excitatory and inhibitory connections are changed. An important aspect for applications is that the theoretical findings allow us to determine for a given coupling function the maximum number of localized inputs that can be stored in a given finite interval., The work received financial support from FCT through a PhD grant (SFRH/BD/41179/2007) and from the EU-FP7 ITN project NETT: Neural Engineering Transformative Technologies (nr. 289146).

In Portugal the natural cycle of fire has been reduced, fires have become recurrent, their intensity and expansion have increased, and they have taken on catastrophic proportions. From 2003 to 2012, were accounted, for Portuguese mainland territory, 31 “large forest fires” (LFF) larger than 5000 ha (12 of them with an area exceeding 10,000 ha), and these always occurred in the months from July to September. Although the relationship between atmospheric dynamics, certain synoptic situations and the occurrence of LFF is already known in Portugal, several authors tried to identify the most favorable, in the new fire reality, that can even configure the existence of a new fire regime in Portugal, it is essential to identify synoptic patterns associated with LFF (5000 ha above), which could be an important meteorological tool in the management of wildfires., This work was co-financed by the European Regional Development Fund (ERDF) through the COMPETE 2020 Operational Programe Competitiveness and Internationalization (POCI) and national funds by FCT under the POCI-01-0145-FEDER-006891 project (FCT Ref: UID/ GEO 04084/2013)., info:eu-repo/semantics/publishedVersion

If we want robots to engage effectively with humans in service applications or in collaborative work scenarios they have be endowed with the capacity to perceive the passage of time and control the timing of their actions. Here we report result of a robotics experiment in which we test a computational model of action timing based on processing principles of neurodynamics. A key assumption is that elapsed time is encoded in the consistent buildup of persistent population activity representing the memory of sensory or motor events. The stored information can be recalled using a ramp-to-threshold dynamics to guide actions in time. For the experiment we adopt an assembly paradigm from our previous work on natural human-robot interactions. The robot first watches a human executing a sequence of assembly steps. Subsequently, it has to execute the steps from memory in the correct order and in synchrony with an external timing signal. We show that the robot is able to efficiently adapt its motor timing and to store this information in memory using the temporal mismatch between the neural processing of the sensory feedback about executed actions and the external cue., FCT - Fundació Catalana de Trasplantament(PD/BD/128183/2016)This research was supported by the Marie Curie Network for Initial Training NETT, FCT through the PhD fellowship PD/BD/128183/2016, the FCT-Research Center CMAT (PEstOE/MAT/UI0013/2014), and FCT - Algoritmi research Centre (COMPETE: POCI-01-0145-FEDER-007043 and FCT - Fundação para a Ciência e Tecnologia within the Project ˆ Scope: UID/CEC/00319/2013)

The recurrence of forest fires is degrading an important part of the Portuguese natural heritage namely its forest and soils. In this paper we present the case study of Cabeço da Vaca (Cabreira Mountain—northwest Portugal), where in recent decades, particularly in the 70s, there was a significant increase in the number of forest fires and in the areas scorched annually. There is thus a turning point between a period when fire was an integral part of the ecosystems and when fire has become a serious threat to woodland management and development (Bento Gonçalves, 2006). Starting with a thorough characterization of forest fires and based on the mapping of scorched areas between 1990 and 2006, we have proceeded to identify the annual pattern of maximum recurrence and the definition of the return interval in Cabeço da Vaca, producing thus a valuable document to support management and forestry development in general.

Many of our everyday tasks require the control of the serial order and the timing of component actions. Using the dynamic neural field (DNF) framework, we address the learning of representations that support the performance of precisely time action sequences. In continuation of previous modeling work and robotics implementations, we ask specifically the question how feedback about executed actions might be used by the learning system to fine tune a joint memory representation of the ordinal and the temporal structure which has been initially acquired by observation. The perceptual memory is represented by a self-stabilized, multi-bump activity pattern of neurons encoding instances of a sensory event (e.g., color, position or pitch) which guides sequence learning. The strength of the population representation of each event is a function of elapsed time since sequence onset. We propose and test in simulations a simple learning rule that detects a mismatch between the expected and realized timing of events and adapts the activation strengths in order to compensate for the movement time needed to achieve the desired effect. The simulation results show that the effector-specific memory representation can be robustly recalled. We discuss the impact of the fast, activation-based learning that the DNF framework provides for robotics applications.

We tested in a robotics experiment a dynamic neural field model for learning a precisely timed musical sequence. Based on neuro-plausible processing mechanisms, the model implements the idea that order and relative timing of events are stored in an integrated representation whereas the onset of sequence production is controlled by a separate process. Dynamic neural fields provide a rigorous theoretical framework to analyze and implement the necessary neural computations that bridge gaps between sensation and action in order to mediate working memory, action planing, and decision making. The robot first memorizes a short musical sequence performed by a human teacher by watching color coded keys on a screen, and then tries to execute the piece of music on a keyboard from memory without any external cues. The experimental results show that the robot is able to correct in very few demonstration-execution cycles initial sequencing and timing errors., The work received financial support from FCT - Fundação para a Ciência e Tecnologia within the Project Scope: PEst- OE/EEI/UI0319/2014, the Research Centers for Mathematics and Algoritmi through the FCT Pluriannual Funding Program, PhD and Post-doctoral Grants (SFRH/BD/41179/2007, SFRH/BD/48529/2008 and SFRH/BPD/71874/2010, financed by POPH-QREN-Type 4.1-Advanced Training, co-funded by the European Social Fund and national funds from MEC), and Project NETT: Neural Engineering Transformative Technologies, EU-FP7 ITN (nr.289146).

Humans are experts in cooperating in a smooth and proactive manner. Action and intention understanding are critical components of efficient joint action. In the context of the EU Integrated Project JAST [16] we have developed an anthropomorphic robot endowed with these cognitive capacities. This project and respective robot (ARoS) is the focus of the video. More specifically, the results illustrate crucial cognitive capacities for efficient and successful human-robot collaboration such as goal inference, error detection and anticipatory action selection. Results were considered one of the ICT "success stories", JAST: Joint-Action Science and Technology” (Ref. IST-2-003747-IP), FCT FCOMP-01-0124-FEDER-022674”.

Recent evidence suggests that the neural mechanisms underlying memory for serial order and interval timing of sequential events are closely linked. We present a dynamic neural field model which exploits the existence and stability of multi-bump solutions with a gradient of activation to store serial order. The activation gradient is achieved by applying a state-dependent threshold accommodation process to the firing rate function. A field dynamics of lateral inhibition type is used in combination with a dynamics for the baseline activity to recall the sequence from memory. We show that depending on the time scale of the baseline dynamics the precise temporal structure of the original sequence may be retrieved or a proactive timing of events may be achieved, Fundação para a Ciência e a Tecnologia (FCT) - Bolsa SFRH/BD/41179/2007