A GIM-Based Biomimetic Learning Approach for Motion Generation of a Multi-Joint Robotic Fish

In this paper, we propose a biomimetic learning approach for motion generation of a multi-joint robotic fish. Based on a multi-joint robotic fish model, two basic Carangiform swimming patterns, namely ＂cruise＂ and ＂C sharp turning＂, are extracted as training samples from the observations of real fish swimming. A General Internal Model （GIM）, which is an imitation of Central Pattern Generator （CPG） in nerve systems, is adopted to learn and to regenerate coordinated fish behaviors. By virtue of the universal function approximation ability and the temporal/spatial scalabilities of GIM, the proposed learning approach is able to generate the same or similar fish swimming patterns by tuning two parameters. The learned swimming patterns are implemented on a multi-joint robotic fish in experiments. The experiment results verify the effectiveness of the biomimetic learning approach in generating and modifying locomotion patterns for the robotic fish.     

Visually guided gait modifications for stepping over an obstacle: a bio-inspired approach

There is an increasing interest in conceiving robotic systems that are able to move and act in an unstructured and not predefined environment, for which autonomy and adaptability are crucial features. In nature, animals are autonomous biological systems, which often serve as bio-inspiration models, not only for their physical and mechanical properties, but also their control structures that enable adaptability and autonomy—for which learning is (at least) partially responsible. This work proposes a system which seeks to enable a quadruped robot to online learn to detect and to avoid stumbling on an obstacle in its path. The detection relies in a forward internal model that estimates the robot’s perceptive information by exploring the locomotion repetitive nature. The system adapts the locomotion in order to place the robot optimally before attempting to step over the obstacle, avoiding any stumbling. Locomotion adaptation is achieved by changing control parameters of a central pattern generator (CPG)-based locomotion controller. The mechanism learns the necessary alterations to the stride length in order to adapt the locomotion by changing the required CPG parameter. Both learning tasks occur online and together define a sensorimotor map, which enables the robot to learn to step over the obstacle in its path. Simulation results show the feasibility of the proposed approach.     

Learning Probabilistic Features for Robotic Navigation Using Laser Sensors

SLAM is a popular task used by robots and autonomous vehicles to build a map of an unknown environment and, at the same time, to determine their location within the map. This paper describes a SLAM-based, probabilistic robotic system able to learn the essential features of different parts of its environment. Some previous SLAM implementations had computational complexities ranging from O(Nlog(N)) to O(N²), where N is the number of map features. Unlike these methods, our approach reduces the computational complexity to O(N) by using a model to fuse the information from the sensors after applying the Bayesian paradigm. Once the training process is completed, the robot identifies and locates those areas that potentially match the sections that have been previously learned. After the training, the robot navigates and extracts a three-dimensional map of the environment using a single laser sensor. Thus, it perceives different sections of its world. In addition, in order to make our system able to be used in a low-cost robot, low-complexity algorithms that can be easily implemented on embedded processors or microcontrollers are used.     

Sensorimotor experience enhances automatic imitation of robotic action

Recent research in cognitive neuroscience has found that observation of human actions activates the 'mirror system' and provokes automatic imitation to a greater extent than observation of non-biological movements. The present study investigated whether this human bias depends primarily on phylogenetic or ontogenetic factors by examining the effects of sensorimotor experience on automatic imitation of non-biological robotic, stimuli. Automatic imitation of human and robotic action stimuli was assessed before and after training. During these test sessions, participants were required to execute a pre-specified response (e.g. to open their hand) while observing a human or robotic hand making a compatible (opening) or incompatible (closing) movement. During training, participants executed opening and closing hand actions while observing compatible (group CT) or incompatible movements (group IT) of a robotic hand. Compatible, but not incompatible, training increased automatic imitation of robotic stimuli (speed of responding on compatible trials, compared with incompatible trials) and abolished the human bias observed at pre-test. These findings suggest that the development of the mirror system depends on sensorimotor experience, and that, in our species, it is biased in favour of human action stimuli because these are more abundant than non-biological action stimuli in typical developmental environments.     

A real-time spiking cerebellum model for learning robot control

We describe a neural network model of the cerebellum based on integrate-and-fire spiking neurons with conductance-based synapses. The neuron characteristics are derived from our earlier detailed models of the different cerebellar neurons. We tested the cerebellum model in a real-time control application with a robotic platform. Delays were introduced in the different sensorimotor pathways according to the biological system. The main plasticity in the cerebellar model is a spike-timing dependent plasticity (STDP) at the parallel fiber to Purkinje cell connections. This STDP is driven by the inferior olive (IO) activity, which encodes an error signal using a novel probabilistic low frequency model. We demonstrate the cerebellar model in a robot control system using a target-reaching task. We test whether the system learns to reach different target positions in a non-destructive way, therefore abstracting a general dynamics model. To test the system's ability to self-adapt to different dynamical situations, we present results obtained after changing the dynamics of the robotic platform significantly (its friction and load). The experimental results show that the cerebellar-based system is able to adapt dynamically to different contexts.     

Intact automatic imitation of human and robot actions in autism spectrum disorders

The existence of a specialized imitation module in humans is hotly debated. Studies suggesting a specific imitation impairment in individuals with autism spectrum disorders (ASD) support a modular view. However, the voluntary imitation tasks used in these studies (which require socio-cognitive abilities in addition to imitation for successful performance) cannot support claims of a specific impairment. Accordingly, an automatic imitation paradigm (a 'cleaner' measure of imitative ability) was used to assess the imitative ability of 16 adults with ASD and 16 non-autistic matched control participants. Participants performed a prespecified hand action in response to observed hand actions performed either by a human or a robotic hand. On compatible trials the stimulus and response actions matched, while on incompatible trials the two actions did not match. Replicating previous findings, the Control group showed an automatic imitation effect: responses on compatible trials were faster than those on incompatible trials. This effect was greater when responses were made to human than to robotic actions ('animacy bias'). The ASD group also showed an automatic imitation effect and a larger animacy bias than the Control group. We discuss these findings with reference to the literature on imitation in ASD and theories of imitation.     

Designing an assistive robot for older adults: The ROBADOM project

ObjectiveThe ROBADOM project was devoted to the design of a “robot butler”, capable of providing verbal and non-verbal interactions and feedbacks for assisting older adults at home. In this article we focused on the following issues: (1) study the social context for designing social robot; define the robot appearance and investigate the perceptions and attitudes of older adults towards an assistive robot; (2) examine the perception of the expressivity of the robot, the social signals showing the end-user engagement level and the role of agent embodiment during the interaction between older adults and a robot.MethodThe design of the studies involved both qualitative and experimental methods.Results & DiscussionSmall robots with some traits between human/animal and machine were appreciated by the participants. As regards services, cognitive stimulation, reminder and object localization were positively rated. Although the participants considered an assistive robot as useful, they were not yet ready to adopt it. The expressions of the robot were perceived differently in older and young adults. Thus, a robotic system dedicated to older adults should be tailored to the specific characteristics of this population. We also identified social signals as indicators of the user's engagement level during interaction. Finally, the issue of the added valued of a robotic system in comparison to a laptop was raised by our participants. Therefore, various issues (technological development, human-robot interaction, social context…) are to be explored before testing the impact of the robot at home.     

Virtual Reality Based Support System for Layout Planning and Programming of an Industrial Robotic Work Cell

Traditional robotic work cell design and programming are considered inefficient and outdated in current industrial and market demands. In this research, virtual reality (VR) technology is used to improve human-robot interface, whereby complicated commands or programming knowledge is not required. The proposed solution, known as VR-based Programming of a Robotic Work Cell (VR-Rocell), consists of two sub-programmes, which are VR-Robotic Work Cell Layout (VR-RoWL) and VR-based Robot Teaching System (VR-RoT). VR-RoWL is developed to assign the layout design for an industrial robotic work cell, whereby VR-RoT is developed to overcome safety issues and lack of trained personnel in robot programming. Simple and user-friendly interfaces are designed for inexperienced users to generate robot commands without damaging the robot or interrupting the production line. The user is able to attempt numerous times to attain an optimum solution. A case study is conducted in the Robotics Laboratory to assemble an electronics casing and it is found that the output models are compatible with commercial software without loss of information. Furthermore, the generated KUKA commands are workable when loaded into a commercial simulator. The operation of the actual robotic work cell shows that the errors may be due to the dynamics of the KUKA robot rather than the accuracy of the generated programme. Therefore, it is concluded that the virtual reality based solution approach can be implemented in an industrial robotic work cell.     

Brain Response to a Humanoid Robot in Areas Implicated in the Perception of Human Emotional Gestures

Background

The humanoid robot WE4-RII was designed to express human emotions in order to improve human-robot interaction. We can read the emotions depicted in its gestures, yet might utilize different neural processes than those used for reading the emotions in human agents.

Methodology

Here, fMRI was used to assess how brain areas activated by the perception of human basic emotions (facial expression of Anger, Joy, Disgust) and silent speech respond to a humanoid robot impersonating the same emotions, while participants were instructed to attend either to the emotion or to the motion depicted.

Principal Findings

Increased responses to robot compared to human stimuli in the occipital and posterior temporal cortices suggest additional visual processing when perceiving a mechanical anthropomorphic agent. In contrast, activity in cortical areas endowed with mirror properties, like left Broca''s area for the perception of speech, and in the processing of emotions like the left anterior insula for the perception of disgust and the orbitofrontal cortex for the perception of anger, is reduced for robot stimuli, suggesting lesser resonance with the mechanical agent. Finally, instructions to explicitly attend to the emotion significantly increased response to robot, but not human facial expressions in the anterior part of the left inferior frontal gyrus, a neural marker of motor resonance.

Conclusions

Motor resonance towards a humanoid robot, but not a human, display of facial emotion is increased when attention is directed towards judging emotions.

Significance

Artificial agents can be used to assess how factors like anthropomorphism affect neural response to the perception of human actions.     

Homo imitans? Seven reasons why imitation couldn't possibly be associative

Many comparative and developmental psychologists believe that we are Homo imitans; humans are more skilled and prolific imitators than other animals, because we have a special, inborn ‘intermodal matching’ mechanism that integrates representations of others with representations of the self. In contrast, the associative sequence learning (ASL) model suggests that human infants learn to imitate using mechanisms that they share with other animals, and the rich resources provided by their sociocultural environments. This article answers seven objections to the ASL model: (i) it presents evidence that newborns do not imitate; (ii) argues that infants receive a plentiful supply of the kind of experience necessary for learning to imitate; (iii) suggests that neither infants nor adults can imitate elementally novel actions; (iv) explains why non-human animals have a limited capacity for imitation; (v) discusses the goal-directedness of imitation; (vi) presents evidence that improvement in imitation depends on visual feedback; and (vii) reflects on the view that associative theories steal ‘the soul of imitation’. The empirical success of the ASL model indicates that the mechanisms which make imitation possible, by aligning representations of self with representations of others, have been tweaked by cultural evolution, not built from scratch by genetic evolution.     

A learning-based markerless approach for full-body kinematics estimation in-natura from a single image

We present a supervised machine learning approach for markerless estimation of human full-body kinematics for a cyclist from an unconstrained colour image. This approach is motivated by the limitations of existing marker-based approaches restricted by infrastructure, environmental conditions, and obtrusive markers. By using a discriminatively learned mixture-of-parts model, we construct a probabilistic tree representation to model the configuration and appearance of human body joints. During the learning stage, a Structured Support Vector Machine (SSVM) learns body parts appearance and spatial relations. In the testing stage, the learned models are employed to recover body pose via searching in a test image over a pyramid structure. We focus on the movement modality of cycling to demonstrate the efficacy of our approach. In natura estimation of cycling kinematics using images is challenging because of human interaction with a bicycle causing frequent occlusions. We make no assumptions in relation to the kinematic constraints of the model, nor the appearance of the scene. Our technique finds multiple quality hypotheses for the pose. We evaluate the precision of our method on two new datasets using loss functions. Our method achieves a score of 91.1 and 69.3 on mean Probability of Correct Keypoint (PCK) measure and 88.7 and 66.1 on the Average Precision of Keypoints (APK) measure for the frontal and sagittal datasets respectively. We conclude that our method opens new vistas to robust user-interaction free estimation of full body kinematics, a prerequisite to motion analysis.     

Observing the observer (II): deciding when to decide

In a companion paper [1], we have presented a generic approach for inferring how subjects make optimal decisions under uncertainty. From a Bayesian decision theoretic perspective, uncertain representations correspond to "posterior" beliefs, which result from integrating (sensory) information with subjective "prior" beliefs. Preferences and goals are encoded through a "loss" (or "utility") function, which measures the cost incurred by making any admissible decision for any given (hidden or unknown) state of the world. By assuming that subjects make optimal decisions on the basis of updated (posterior) beliefs and utility (loss) functions, one can evaluate the likelihood of observed behaviour. In this paper, we describe a concrete implementation of this meta-Bayesian approach (i.e. a Bayesian treatment of Bayesian decision theoretic predictions) and demonstrate its utility by applying it to both simulated and empirical reaction time data from an associative learning task. Here, inter-trial variability in reaction times is modelled as reflecting the dynamics of the subjects' internal recognition process, i.e. the updating of representations (posterior densities) of hidden states over trials while subjects learn probabilistic audio-visual associations. We use this paradigm to demonstrate that our meta-Bayesian framework allows for (i) probabilistic inference on the dynamics of the subject's representation of environmental states, and for (ii) model selection to disambiguate between alternative preferences (loss functions) human subjects could employ when dealing with trade-offs, such as between speed and accuracy. Finally, we illustrate how our approach can be used to quantify subjective beliefs and preferences that underlie inter-individual differences in behaviour.     

View-Invariant Visuomotor Processing in Computational Mirror Neuron System for Humanoid

Mirror neurons are visuo-motor neurons found in primates and thought to be significant for imitation learning. The proposition that mirror neurons result from associative learning while the neonate observes his own actions has received noteworthy empirical support. Self-exploration is regarded as a procedure by which infants become perceptually observant to their own body and engage in a perceptual communication with themselves. We assume that crude sense of self is the prerequisite for social interaction. However, the contribution of mirror neurons in encoding the perspective from which the motor acts of others are seen have not been addressed in relation to humanoid robots. In this paper we present a computational model for development of mirror neuron system for humanoid based on the hypothesis that infants acquire MNS by sensorimotor associative learning through self-exploration capable of sustaining early imitation skills. The purpose of our proposed model is to take into account the view-dependency of neurons as a probable outcome of the associative connectivity between motor and visual information. In our experiment, a humanoid robot stands in front of a mirror (represented through self-image using camera) in order to obtain the associative relationship between his own motor generated actions and his own visual body-image. In the learning process the network first forms mapping from each motor representation onto visual representation from the self-exploratory perspective. Afterwards, the representation of the motor commands is learned to be associated with all possible visual perspectives. The complete architecture was evaluated by simulation experiments performed on DARwIn-OP humanoid robot.     

Learning Priors for Bayesian Computations in the Nervous System

Our nervous system continuously combines new information from our senses with information it has acquired throughout life. Numerous studies have found that human subjects manage this by integrating their observations with their previous experience (priors) in a way that is close to the statistical optimum. However, little is known about the way the nervous system acquires or learns priors. Here we present results from experiments where the underlying distribution of target locations in an estimation task was switched, manipulating the prior subjects should use. Our experimental design allowed us to measure a subject''s evolving prior while they learned. We confirm that through extensive practice subjects learn the correct prior for the task. We found that subjects can rapidly learn the mean of a new prior while the variance is learned more slowly and with a variable learning rate. In addition, we found that a Bayesian inference model could predict the time course of the observed learning while offering an intuitive explanation for the findings. The evidence suggests the nervous system continuously updates its priors to enable efficient behavior.     

Learning to Estimate Dynamical State with Probabilistic Population Codes

Tracking moving objects, including one’s own body, is a fundamental ability of higher organisms, playing a central role in many perceptual and motor tasks. While it is unknown how the brain learns to follow and predict the dynamics of objects, it is known that this process of state estimation can be learned purely from the statistics of noisy observations. When the dynamics are simply linear with additive Gaussian noise, the optimal solution is the well known Kalman filter (KF), the parameters of which can be learned via latent-variable density estimation (the EM algorithm). The brain does not, however, directly manipulate matrices and vectors, but instead appears to represent probability distributions with the firing rates of population of neurons, “probabilistic population codes.” We show that a recurrent neural network—a modified form of an exponential family harmonium (EFH)—that takes a linear probabilistic population code as input can learn, without supervision, to estimate the state of a linear dynamical system. After observing a series of population responses (spike counts) to the position of a moving object, the network learns to represent the velocity of the object and forms nearly optimal predictions about the position at the next time-step. This result builds on our previous work showing that a similar network can learn to perform multisensory integration and coordinate transformations for static stimuli. The receptive fields of the trained network also make qualitative predictions about the developing and learning brain: tuning gradually emerges for higher-order dynamical states not explicitly present in the inputs, appearing as delayed tuning for the lower-order states.     

In Good Company? Perception of Movement Synchrony of a Non-Anthropomorphic Robot

Recent technological developments like cheap sensors and the decreasing costs of computational power have brought the possibility of robotic home companions within reach. In order to be accepted it is vital for these robots to be able to participate meaningfully in social interactions with their users and to make them feel comfortable during these interactions. In this study we investigated how people respond to a situation where a companion robot is watching its user. Specifically, we tested the effect of robotic behaviours that are synchronised with the actions of a human. We evaluated the effects of these behaviours on the robot’s likeability and perceived intelligence using an online video survey. The robot used was Care-O-bot3, a non-anthropomorphic robot with a limited range of expressive motions. We found that even minimal, positively synchronised movements during an object-oriented task were interpreted by participants as engagement and created a positive disposition towards the robot. However, even negatively synchronised movements of the robot led to more positive perceptions of the robot, as compared to a robot that does not move at all. The results emphasise a) the powerful role that robot movements in general can have on participants’ perception of the robot, and b) that synchronisation of body movements can be a powerful means to enhance the positive attitude towards a non-anthropomorphic robot.     

Dynamical systems for predictive control of autonomous robots

Summary Regularities in the environment are accessible to an autonomous agents as reproducible relations between actions and perceptions and can be exploited by unsupervised learning. Our approach is based on the possibility to perform and to verify predictions about perceivable consequences of actions. It is implemented as a three-layer neural network that combines predictive perception, internal-state transitions and action selection into a loop which closes via the environment. In addition to minimizing prediction errors, the goal of network adaptation comprises also an optimization of the minimization rate such that new behaviors are favored over already learned ones, which would result in a vanishing improvement of predictability. Previously learned behaviors are reactivated or continued if triggering stimuli are available and an externally or otherwise given reward overcompensates the decay of the learning rate. In the model, behavior learning and learning behavior are brought about by the same mechanism, namely the drive to continuously experience learning success. Behavior learning comprises representation and storage of learned behaviors and finally their inhibition such that a further exploration of the environment is possible. Learning behavior, in contrast, detects the frontiers of the manifold of learned behaviors and provides estimates of the learnability of behaviors leading outwards the field of expertise. The network module has been implemented in a Khepera miniature robot. We also consider hierarchical architectures consisting of several modules in one agent as well as groups of several agents, which are controlled by such networks.     

A probabilistic methodology for integrating knowledge and experiments on biological networks.

Biological systems are traditionally studied by focusing on a specific subsystem, building an intuitive model for it, and refining the model using results from carefully designed experiments. Modern experimental techniques provide massive data on the global behavior of biological systems, and systematically using these large datasets for refining existing knowledge is a major challenge. Here we introduce an extended computational framework that combines formalization of existing qualitative models, probabilistic modeling, and integration of high-throughput experimental data. Using our methods, it is possible to interpret genomewide measurements in the context of prior knowledge on the system, to assign statistical meaning to the accuracy of such knowledge, and to learn refined models with improved fit to the experiments. Our model is represented as a probabilistic factor graph, and the framework accommodates partial measurements of diverse biological elements. We study the performance of several probabilistic inference algorithms and show that hidden model variables can be reliably inferred even in the presence of feedback loops and complex logic. We show how to refine prior knowledge on combinatorial regulatory relations using hypothesis testing and derive p-values for learned model features. We test our methodology and algorithms on a simulated model and on two real yeast models. In particular, we use our method to explore uncharacterized relations among regulators in the yeast response to hyper-osmotic shock and in the yeast lysine biosynthesis system. Our integrative approach to the analysis of biological regulation is demonstrated to synergistically combine qualitative and quantitative evidence into concrete biological predictions.     

Moving just like you: motor interference depends on similar motility of agent and observer

Recent findings in neuroscience suggest an overlap between brain regions involved in the execution of movement and perception of another's movement. This so-called "action-perception coupling" is supposed to serve our ability to automatically infer the goals and intentions of others by internal simulation of their actions. A consequence of this coupling is motor interference (MI), the effect of movement observation on the trajectory of one's own movement. Previous studies emphasized that various features of the observed agent determine the degree of MI, but could not clarify how human-like an agent has to be for its movements to elicit MI and, more importantly, what 'human-like' means in the context of MI. Thus, we investigated in several experiments how different aspects of appearance and motility of the observed agent influence motor interference (MI). Participants performed arm movements in horizontal and vertical directions while observing videos of a human, a humanoid robot, or an industrial robot arm with either artificial (industrial) or human-like joint configurations. Our results show that, given a human-like joint configuration, MI was elicited by observing arm movements of both humanoid and industrial robots. However, if the joint configuration of the robot did not resemble that of the human arm, MI could longer be demonstrated. Our findings present evidence for the importance of human-like joint configuration rather than other human-like features for perception-action coupling when observing inanimate agents.