This paper describes a framework that allows a user to synthesize human motion while retaining control of its qualitative properties. The user paints a timeline with annotations — likewalk, run or jump — from a vocabulary which is freely chosen by the user. The system then assembles frames from a motion database so that the final motion performs the specified actions at specified times. The motion can also be forced to pass through particular configurations at particular times, and to go to a particular position and orientation. Annotations can be painted positively (for example, must run), negatively (for example, may not run backwards) orasa don’t-care. The system uses a novel search method, based around dynamic programming at several scales, to obtain a solution efficiently so that authoring is interactive. Our results demonstrate that the method can generate smooth, natural-looking motion. The annotation vocabulary can be chosen to fit the application, and allows specification of composite motions (run andjump simultaneously, for example). The process requires a collection of motion data that has been annotated with the chosen vocabulary. This paper also describes an effective tool, based around repeated use of support vector machines, that allows a user to annotate a large collection of motions quickly and easily so that they may be used with the synthesis algorithm.

This paper focuses on the role of emotion and expressive behavior in regulating social interaction between humans and expressive anthropomorphic robots, either in communicative or teaching scenarios. We present the scientific basis underlying our humanoid robot's emotion models and expressive behavior, and then show how these scientific viewpoints have been adapted to the current implementation. Our robot is also able to recognize affective intent through tone of voice, the implementation of which is inspired by the scientific findings of the developmental psycholinguistics community. We first evaluate the robot's expressive displays in isolation. Next, we evaluate the robot's overall emotive behavior (i.e. the coordination of the affective recognition system, the emotion and motivation systems, and the expression system) as it socially engages nave human subjects face-to-face.

Abstract. We present a new method for representing human movement compactly, in terms of a linear superimposition of simpler movements termed primitives. This method is a part of a larger research project aimed at modeling motor control and imitation using the notion of perceptuo-motor primitives, a basis set of coupled perceptual and motor routines. In our model, the perceptual system is biased by the set of motor behaviors the agent can execute, so it automatically classifies observed movements into its executable repertoire. In this paper, we describe a method for automatically deriving a set of primitives directly from human movement data. We used data from a psychophysical experiment on human imitation to derive a set of primitives, and then used those primitives as a basis for superposition and sequencing to reconstruct the original movements. We performed principal component analysis on segments from these data, resulting in a set of basis vectors. Next we clustered in the space of projections of segments onto the eigenvectors, to obtain a set of frequently used movements. To validate the approach experimentally, we used the movement obtained by expanding the cluster points in terms of the eigenvectors as a sequence of via points to control a humanoid dynamic simulation. We also developed an error metric to measure the effectiveness of the process. 1

Imitation is a powerful mechanism whereby knowledge may be transferred between agents (both biological and artificial). Key problems on the topic of imitation have emerged in various areas close to artificial intelligence, including the cognitive and social sciences, animal behavior, robotics, human--computer interaction, embodied intelligence, software engineering, programming by example and machine learning. Artificial systems used to study imitation can both test models of imitation derived from observational or neurobiological data on imitation in animals and then apply them to different kinds of nonbiological systems ranging from robots to software agents. A crucial problem in imitation is the correspondence problem, mapping action sequences of the demonstrator and the imitator agent. This problem becomes particularly obvious when the two agents do not share the same embodiment and affordances. This paper describes a new general imitation mechanism called Action Learning for Imitation via Correspondence between embodiments (ALICE) that specifically addresses the correspondence problem. The mechanism is implemented and its efficacy illustrated on the "chessworld" testbed that was created to study imitation from an agent-based perspective, i.e., by a particular agent in a particular environment.

This thesis presents a perceptual system for a humanoid robot that integrates abilities such as object localization and recognition with the deeper developmental machinery required to forge those competences out of raw physical experiences. It shows that a robotic platform can build up and maintain a system for object localization, segmentation, and recognition, starting from very little. What the robot starts with is a direct solution to achieving figure/ground separation: it simply `pokes around' in a region of visual ambiguity and watches what happens. If the arm passes through an area, that area is recognized as free space. If the arm collides with an object, causing it to move, the robot can use that motion to segment the object from the background. Once the robot can acquire reliable segmented views of objects, it learns from them, and from then on recognizes and segments those objects without further contact. Both low-level and high-level visual features can also be learned in this way, and examples are presented for both: orientation detection and affordance recognition, respectively.

Mimesis theory is one of the primitive skill of imitative learning, which is regarded as an origin of human intelligence because imitation is fundamental function for communication and symbol manipulation. When the mimesis is adopted as learning method for humanoids, convenience for designing full body behavior would decrease because bottom-up learning approaches from robot side and topdown teaching approaches from user side involved each other. Therefore, we propose a behavior acquisition and understanding system for humanoids based on the mimesis theory. This system is able to abstract observed others' behaviors into symbols, to recognize others' behavior using the symbols, and to generate motion patterns using the symbols. In this paper, we mention the integration of mimesis loop, and confirmation of the feasibility on virtual humanoids.

It is needed for humanoid to acquire not only just a trajectory but also aim of the behavior and sym-bolic information during behavior development. We have proposed the mimesis system as a frame-work of synchronous learning model for behav-ior acquisition and symbol emergence. However, the motion elements which are fundamental rep-resentation of behavior have stood on the unsuit-able assumption that they are given without taking robots ' embodiment and dynamics into considera-tion. In this paper, the design theory of motion el-ements with consideration of the embodiment are shown, and novel methods of realization of the mimesis for real humanoids is proposed.

We propose that the development of causality can be seen as a primitive for understanding and constructing complex systems either biological or artificial. Furthermore, we put forward a view of development in terms of the control of complexity. Although some of these elements are at the moment speculative or barely outlined, the theoretical test and verification are part of the ongoing research. On the artificial side, we will show how developmental principles are used within the architecture of a humanoid robot. The reference problem is the ontogenesis of sensori-motor coordination. Visual, acoustic and inertial cues constitute the sensory repertoire of the robot; computation, in the form of mappings, represents its brain activity. The continuous and meaningful adaptation during the natural interaction of the robot with the environment is one of the key aspects of the implementation.

This paper reports that the superposition of a small set of behaviors, learned via teleoperation, can lead to robust completion of a simple articulated reach-and-grasp task. The results support the hypothesis that a set of learned behaviors can be combined to generate new behaviors of a similar type. This, in turn, supports the hypothesis that a robot can learn to interact purposefully with its environment through a developmental acquisition of sensory-motor coordination. Teleoperation can bootstrap the process by enabling the robot to observe its own sensory responses to actions that lead to specific outcomes within an environment. It is shown that a reach-and-grasp task, learned by an articulated robot through a small number of teleoperated trials, can be performed autonomously with success in the face of significant variations in the environment and perturbations of the goal. In particular, teleoperation of the robot to reach and grasp an object at nine different locations in its workspace enabled robust autonomous performance of the task anywhere within the workspace. Superpositioning was performed using the Verbs and Adverbs algorithm that was developed originally for the graphical animation of articulated characters. The work was performed on Robonaut, the NASA space-capable humanoid at Johnson Space Center.

Abstract — In this paper, we present a novel method for learning robot tasks from multiple demonstrations. Each demonstrated task is decomposed into subtasks that allow for segmentation and classification of the input data. The demonstrated tasks are then merged into a flexible task model, describing the task goal and its constraints. The two main contributions of the paper are the state generation and contraints identification methods. We also present a task level planner, that is used to assemble a task plan at run-time, allowing the robot to choose the best strategy depending on the current world state. I.