We present an approach to teach incrementally human gestures to a humanoid robot. The learning process consists of first projecting the movement data in a latent space and encoding the resulting signals in a Gaussian Mixture Model (GMM). We compare the performance of two incremental training procedures against a batch training procedure. Qualitative and quantitative evaluations are performed on data acquired from motion sensors attached to a human demonstrator and data acquired by kinesthetically demonstrating the task to the robot. We present experiments to show that these different modalities can be used to teach incrementally basketball officials ’ signals to a HOAP-3 humanoid robot. 1.

According to the motor theories of perception, the motor systems of an observer are actively involved in the perception of actions when these are performed by a demonstrator. In this paper we review our computational architecture, HAMMER (Hierarchical Attentive Multiple Models for Execution and Recognition), where the motor control systems of a robot are organised in a hierarchical, distributed manner, and can be used in the dual role of (a) competitively selecting and executing an action, and (b) perceiving it when perfomed by a demonstrator. We subsequently demonstrate that such arrangement can provide a principled method for the top-down control of attention during action perception, resulting in significant performance gains. We assess these performance gains under a variety of resource allocation strategies.

Within this paper, an approach for teaching a humanoid robot is presented that will enable the robot to learn typical tasks required in everyday household environments. Our approach, called Programming by Demonstration, which is implemented and successfully used in our institute to teach a robot system is presented. Firstly, we concentrate on an analysis of human actions and action sequences that can be identified when watching a human demonstrator. Secondly, sensor aid systems are introduced which augment the robot’s perception capabilities while watching a human’s demonstration and the robot’s the problem solution strategies and to transfer them onto the robot system.

Abstract—Our work aims at developing a robust discriminant controller for robot programming by demonstration. It addresses two core issues of imitation learning, namely “what to imitate ” and “how to imitate”. This paper presents a method by which a robot extracts the goals of a demonstrated task and determines the imitation strategy that satis es best these goals. The method is validated in a humanoid platform, taking inspiration of an in uential experiment from developmental psychology. I.

This paper addresses the problem of body mapping in robotic imitation where the demonstrator and imitator may not share the same embodiment [degrees of freedom (DOFs), body morphology, constraints, affordances, and so on]. Body mappings are formalized using a unified (linear) approach via correspondence matrices, which allow one to capture partial, mirror symmetric, one-to-one, one-to-many, many-to-one, and many-to-many associations between various DOFs across dissimilar embodiments. We show how metrics for matching state and action aspects of behavior can be mathematically determined by such correspondence mappings, which may serve to guide a robotic imitator. The approach is illustrated and validated in a number of simulated 3-D robotic examples, using agents described by simple kinematic models and different types of correspondence mappings.

Learning by demonstration can be a powerful and natural tool for developing robot control policies. That is, instead of tedious hand-coding, a robot may learn a control policy by interacting with a teacher. In this work we present an algorithm for learning by demonstration in which the teacher operates in two phases. The teacher first demonstrates the task to the learner. The teacher next critiques learner performance of the task. This critique is used by the learner to update its control policy. In our implementation we utilize a 1-Nearest Neighbor technique which incorporates both training dataset and teacher critique. Since the teacher critiques performance only, they do not need to guess at an effective critique for the underlying algorithm. We argue that this method is particularly well-suited to human teachers, who are generally better at assigning credit to performances than to algorithms. We have applied this algorithm to the simulated task of a robot intercepting a ball. Our results demonstrate improved performance with teacher critiquing, where performance is measured by both execution success and efficiency.

Abstract — We present a strategy whereby a robot acquires the capability to learn by imitation following a developmental pathway consisting on three levels: (i) sensory-motor coordination, (ii) world interaction, (iii) imitation. With these stages, the system is able to learn tasks by imitating human demonstrators. We describe results of the different developmental stages, involving perceptual and motor skills, implemented in our humanoid robot, Baltazar. At each stage, the system’s attention is drawn towards different entities: its own body and later on, objects and people. Our main contributions are the general architecture and the implementation of all the necessary modules until imitation capabilities are eventually acquired by the robot. Also several other contributions are made at each level: learning of sensory-motor maps for redundant robots, a novel method for learning how to grasp objects and a framework for learning task description from observation for program-level imitation. Finally, vision is used extensively as the sole sensing modality (sometimes in a simplified setting) avoiding the need for special data-acquisition hardware. Index Terms — Humanoid Robots, development, imitation I.

This chapter reviews several approaches to the problem of learning by imitation in robotics. We start by describing several cognitive processes identified in the literature as necessary for imitation. We then proceed by surveying different approaches to this problem, placing particular emphasys on methods whereby an agent first learns about its own body dynamics by means of self-exploration and then uses this knowledge about its own body to recognize the actions being performed by other agents. This general approach is related to the motor theory of perception, particularly to the mirror neurons found in primates. We distinguish three fundamental classes of methods, corresponding to three abstraction levels at which imitation can be addressed. As such, the methods surveyed herein exhibit behaviors that range from raw sensory-motor trajectory matching to high-level abstract task replication. We also discuss the impact that knowledge about the world and/or the demonstrator can have on the particular behaviors exhibited.

In this paper we present a robot control architecture for learning by imitation which takes inspiration from recent discoveries in action observation/execution experiments with humans and other primates. The architecture implements two basic processing principles: 1) imitation is primarily directed toward reproducing the goal/end state of an observed action sequence, and 2) the required capacity to understand the motor intention of another agent is based on motor simulation. The control architecture is validated in a robot system imitating in a goal-directed manner a grasping and placing sequence displayed by a human model. During imitation, skill transfer occurs by learning and representing appropriate goal-directed sequences of motor primitives. After having established computational links between the representations of goal and means, further knowledge about the meaning of objects is transferred (“where to place specific objects”). The robustness of the goal-directed organization of the controller is tested in the presence of incomplete visual information and changes in environmental constraints.

Knowledge sharing, either implicit or explicit, is crucial during development as evidenced by many studies into the transfer of knowledge by teachers via gaze following and learning by imitation. In the future, the teacher of one robot may be a more experienced robot. There are many new difficulties, however, with regard to knowledge transfer among robots that develop embodiment-specific knowledge through individual solo interaction with the world. This is especially true for heterogeneous robots, where perceptual and motor capabilities may differ. In this paper, we propose to leverage similarity, in the form of a physically shared context, to learn models of the differences between two robots. The second contribution we make is to analyze the cost and accuracy of several methods for the establishment of the physically shared context with respect to such modeling. We demonstrate the efficacy of the proposed methods in a simulated domain involving shared attention of an object. 1.