Luis Montesano

The iCub humanoid robot: An open-systems platform for research in cognitive development

We describe a humanoid robot platform--the iCub--which was designed to support collaborative research in cognitive development through autonomous exploration and social interaction. The motivation for this effort is the conviction that significantly greater impact can be leveraged by adopting an open systems policy for software and hardware development. This creates the need for a robust humanoid robot that offers rich perceptuo-motor capabilities with many degrees of freedom, a cognitive capacity for learning and development, a software architecture that encourages reuse & easy integration, and a support infrastructure that fosters collaboration and sharing of resources. The iCub satisfies all of these needs in the guise of an open-system platform which is freely available and which has attracted a growing community of users and developers. To date, twenty iCubs each comprising approximately 5000 mechanical and electrical parts have been delivered to several research labs in Europe and to one in the USA.

Learning Object Affordances: From Sensory--Motor Coordination to Imitation

Affordances encode relationships between actions, objects, and effects. They play an important role on basic cognitive capabilities such as prediction and planning. We address the problem of learning affordances through the interaction of a robot with the environment, a key step to understand the world properties and develop social skills. We present a general model for learning object affordances using Bayesian networks integrated within a general developmental architecture for social robots. Since learning is based on a probabilistic model, the approach is able to deal with uncertainty, redundancy, and irrelevant information. We demonstrate successful learning in the real world by having an humanoid robot interacting with objects. We illustrate the benefits of the acquired knowledge in imitation games.

Metric-based iterative closest point scan matching for sensor displacement estimation

This paper addresses the scan matching problem for mobile robot displacement estimation. The contribution is a new metric distance and all the tools necessary to be used within the iterative closest point framework. The metric distance is defined in the configuration space of the sensor, and takes into account both translation and rotation error of the sensor. The new scan matching technique ameliorates previous methods in terms of robustness, precision, convergence, and computational load. Furthermore, it has been extensively tested to validate and compare this technique with existing methods

Metric-Based Scan Matching Algorithms for Mobile Robot Displacement Estimation

This paper presents a metric-based matching algorithm to estimate the robot planar displacement by matching dense two-dimensional range scans. The contribution is a geometric distance that takes into account the translation and orientation of the sensor at the same time. This result is used in the two steps of the matching - estimation process. The correspondences between scans are established with this measure and the minimization of the error is also carried out in terms of this distance. As a result, the translation and rotation are compensated in this framework simultaneously. In fact, this is the contribution with respect to previous work that addressed only translation or translation and rotation but separately. The new technique has been implemented and tested on a real vehicle. The experiments illustrate how it is more robust and accurate than prior techniques. At the end of the paper, we give an extension of our distance measure to 3D range-data matching problems.

Affordance-based imitation learning in robots

In this paper we build an imitation learning algorithm for a humanoid robot on top of a general world model provided by learned object affordances. We consider that the robot has previously learned a task independent affordance-based model of its interaction with the world. This model is used to recognize the demonstration by another agent (a human) and infer the task to be learned. We discuss several important problems that arise in this combined framework, such as the influence of an inaccurate model in the recognition of the demonstration. We illustrate the ideas in the paper with some experimental results obtained with a real robot.

Towards an Intelligent Wheelchair System for Users With Cerebral Palsy

This paper describes and evaluates an intelligent wheelchair, adapted for users with cognitive disabilities and mobility impairment. The study focuses on patients with cerebral palsy, one of the most common disorders affecting muscle control and coordination, thereby impairing movement. The wheelchair concept is an assistive device that allows the user to select arbitrary local destinations through a tactile screen interface. The device incorporates an automatic navigation system that drives the vehicle, avoiding obstacles even in unknown and dynamic scenarios. It provides the user with a high degree of autonomy, independent from a particular environment, i.e., not restricted to predefined conditions. To evaluate the rehabilitation device, a study was carried out with four subjects with cognitive impairments, between 11 and 16 years of age. They were first trained so as to get acquainted with the tactile interface and then were recruited to drive the wheelchair. Based on the experience with the subjects, an extensive evaluation of the intelligent wheelchair was provided from two perspectives: 1) based on the technical performance of the entire system and its components and 2) based on the behavior of the user (execution analysis, activity analysis, and competence analysis). The results indicated that the intelligent wheelchair effectively provided mobility and autonomy to the target population.

Probabilistic scan matching for motion estimation in unstructured environments

This paper presents a probabilistic scan matching algorithm to estimate the robot planar displacement by matching dense two-dimensional range scans. The general framework follows an iterative process of two steps: (i) computation of correspondences between scans, and (ii) estimation of the relative displacement. The contribution is a probabilistic modelling of this process that takes into account all the uncertainties involved: the uncertainty of the displacement of the sensor and the measurement noises. Furthermore, it also considers all the possible correspondences resulting from these uncertainties. This technique has been implemented and tested on a real vehicle. The experiments illustrate how the performances of this method are better than previous geometric ones in terms of robustness, accuracy and convergence.

Learning grasping affordances from local visual descriptors

In this paper we study the learning of affordances through self-experimentation. We study the learning of local visual descriptors that anticipate the success of a given action executed upon an object. Consider, for instance, the case of grasping. Although graspable is a property of the whole object, the grasp action will only succeed if applied in the right part of the object. We propose an algorithm to learn local visual descriptors of good grasping points based on a set of trials performed by the robot. The method estimates the probability of a successful action (grasp) based on simple local features. Experimental results on a humanoid robot illustrate how our method is able to learn descriptors of good grasping points and to generalize to novel objects based on prior experience.

On the Usage of Linear Regression Models to Reconstruct Limb Kinematics from Low Frequency EEG Signals

Several works have reported on the reconstruction of 2D/3D limb kinematics from low-frequency EEG signals using linear regression models based on positive correlation values between the recorded and the reconstructed trajectories. This paper describes the mathematical properties of the linear model and the correlation evaluation metric that may lead to a misinterpretation of the results of this type of decoders. Firstly, the use of a linear regression model to adjust the two temporal signals (EEG and velocity profiles) implies that the relevant component of the signal used for decoding (EEG) has to be in the same frequency range as the signal to be decoded (velocity profiles). Secondly, the use of a correlation to evaluate the fitting of two trajectories could lead to overly-optimistic results as this metric is invariant to scale. Also, the correlation has a non-linear nature that leads to higher values for sinus/cosinus-like signals at low frequencies. Analysis of these properties on the reconstruction results was carried out through an experiment performed in line with previous studies, where healthy participants executed predefined reaching movements of the hand in 3D space. While the correlations of limb velocity profiles reconstructed from low-frequency EEG were comparable to studies in this domain, a systematic statistical analysis revealed that these results were not above the chance level. The empirical chance level was estimated using random assignments of recorded velocity profiles and EEG signals, as well as combinations of randomly generated synthetic EEG with recorded velocity profiles and recorded EEG with randomly generated synthetic velocity profiles. The analysis shows that the positive correlation results in this experiment cannot be used as an indicator of successful trajectory reconstruction based on a neural correlate. Several directions are herein discussed to address the misinterpretation of results as well as the implications on previous invasive and non-invasive works.

Continuous decoding of movement intention of upper limb self-initiated analytic movements from pre-movement EEG correlates

BackgroundBrain-machine interfaces (BMI) have recently been integrated within motor rehabilitation therapies by actively involving the central nervous system (CNS) within the exercises. For instance, the online decoding of intention of motion of a limb from pre-movement EEG correlates is being used to convert passive rehabilitation strategies into active ones mediated by robotics. As early stages of upper limb motor rehabilitation usually focus on analytic single-joint mobilizations, this paper investigates the feasibility of building BMI decoders for these specific types of movements.MethodsTwo different experiments were performed within this study. For the first one, six healthy subjects performed seven self-initiated upper-limb analytic movements, involving from proximal to distal articulations. For the second experiment, three spinal cord injury patients performed two of the previously studied movements with their healthy elbow and paralyzed wrist. In both cases EEG neural correlates such as the event-related desynchronization (ERD) and movement related cortical potentials (MRCP) were analyzed, as well as the accuracies of continuous decoders built using the pre-movement features of these correlates (i.e., the intention of motion was decoded before movement onset).ResultsThe studied movements could be decoded in both healthy subjects and patients. For healthy subjects there were significant differences in the EEG correlates and decoding accuracies, dependent on the moving joint. Percentages of correctly anticipated trials ranged from 75% to 40% (with chance level being around 20%), with better performances for proximal than for distal movements. For the movements studied for the SCI patients the accuracies were similar to the ones of the healthy subjects.ConclusionsThis paper shows how it is possible to build continuous decoders to detect movement intention from EEG correlates for seven different upper-limb analytic movements. Furthermore we report differences in accuracies among movements, which might have an impact on the design of the rehabilitation technologies that will integrate this new type of information. The applicability of the decoders was shown in a clinical population, with similar performances between healthy subjects and patients.