This thesis investigates how a robot can use action generation mechanisms to recognize the action of an observed actor in an on-line manner i.e., before the completion of the action. Towards this end, Dynamic Movement Primitives (DMP), an action generation method proposed for imitation, are modified to recognize the actions of an actor. Specifically, a human actor performed three different reaching actions to two different objects. Three DMP&#039 / s, each corresponding to a different reaching action, were trained using this data. The proposed method used an object-centered coordinate system to define the variables for the action, eliminating the difference between the actor and the robot. During testing, the robot simulated action trajectories by its learned DMPs and compared the resulting trajectories against the observed one. The error between the simulated and the observed trajectories were integrated into a recognition signal, over which recognition was done. The proposed method was applied on the iCub humanoid robot platform using an active motion capture device for sensing. The results showed that the system was able to recognize actions with high accuracy as they unfold in time. Moreover, the feasibility of the approach is demonstrated in an interactive game between the robot and a human.

In this thesis the action learning and generation problem on a humanoid robot is studied. Our aim is to realize action learning, generation and recognition in one system and our inspiration source is the mirror neuron hypothesis which suggests that action learning, generation and recognition share the same neural circuitry. Dynamic Movement Primitives, an efficient action learning and generation approach, are modified in order to fulfill this aim. The system we developed (1) can learn from multiple demonstrations, (2) can generalize to different conditions, (3) generates actions in a closed-loop and online fashion and (4) can be used for online action recognition. These claims are supported by experiments and the applicability of the developed system in real world is demonstrated through implementing it on a humanoid robot.

<p>The situated approach in cognitive science and artificial intelligence (AI) has argued since the mid-1980s that intelligent behaviour emerges as a result of a close coupling between agent and environment. Lately, many researchers have emphasized that in addition to the physical environment, the social environment must not be neglected. In this thesis we will focus on the nature of social situatedness, and the aim of this dissertation is to investigate its role and relevance for natural and artificial intelligence.</p><p>This thesis brings together work from separate areas, presenting different perspectives on the role and mechanisms social situatedness. More specifically, we will analyse Vygotsky's cognitive development theory, studies of primate (and avian) intelligence, and last, but not least, work in contemporary socially situated AI. These, at a first glance, quite different fields have a lot in common since they particularly stress the importance of social embeddedness for the development of individual intelligence.</p><p>Combining these separate perspectives, we analyse the remaining differences between natural and artificial social situatedness. Our conclusion is that contemporary socially artificial intelligence research, although heavily inspired by empirical findings in human infants, tends to lack the developmental dimension of situatedness. Further we discuss some implications for research in cognitive science and AI.</p>

This thesis covers the study of an actively assisted passive walker with discontinuous and impulsive actuation. The dynamics of the passive and active portions are derived, and a comprehensive mathematical model is proposed. An actuation method is also proposed to study the use of multiple discrete actuation events in a walking gait. Two key cases are considered: actuation at the stance point and at the EA point of a non-kneed walker. An experimental walker was designed that is capable of passive walking and has an experimental implementation of the proposed actuation system. A thorough characterization of the model is then performed, with experimental validation to show that: at high ramp angles, energy injection results in an increase in BOA of ~38% on a stable walking gait at a Ct of 0.086, and at low ramp angles, injection results in a stride length increase of ~29% at a Ct of 0.06.

This thesis presents a new human-like upper limb and hand motion generating method. The work is based on Functional Principal Component Analysis and Quadratic Programming. The human-like motion generating problem is formulated in a framework of minimizing the difference of the dynamic profile of the optimal trajectory and the known types of trajectory. Statistical analysis is applied to the pre-captured human motion records to work in a low dimensional space. A novel PCA FPCA hybrid motion recognition method is proposed. This method is implemented on human grasping data to demonstrate its advantage in human motion recognition. One human grasping hierarchy is also proposed during the study. The proposed method of generating human-like upper limb and hand motion explores the ability to learn the motion kernels from human demonstration. Issues in acquiring motion kernels are also discussed. The trajectory planning method applies different weight on the extracted motion kernels to approximate the kinematic constraints of the task. Multiple means of evaluation are implemented to illustrate the quality of the generated optimal human-like trajectory compared to the real human motion records.

Localization is an important problem that must be resolved in order for a robot to make an estimation of its location based on observation and odometry updates. Relying on artificial landmarks such as the lines, circles, and goalposts in the robot soccer domain, current robot localization requires prior knowledge and suffers from uncertainty problems due to partial observation, and thus is less generalizable compared to human beings, who refer to their surroundings for complimentary information. To improve the certainty of the localization model, we propose a framework that recognizes orientation by actively using natural landmarks from the off-field surroundings, extracting these visual features from raw images. Our approach involves identifying visual features and natural landmarks, training with localization information to understand the surroundings, and prediction based on matching of features. This approach can increase the precision of robot orientation and improve localization accuracy by eliminating uncertain hypotheses, and in addition, it is also a general approach that can be extended and applied to other localization problems as well. / text

The development of a humanoid robot that mimics human motion requires extensive programming as well as understanding the motion limitations of the robot. Programming the countless possibilities for a robot’s response to observed human motion can be time consuming. To simplify this process, this thesis presents a new approach for mimicking captured human motion data through the development of a composition routine. This routine is built upon a behavior-based framework and is coupled with optimization by calculus to determine the appropriate weightings of predetermined motion behaviors. The completion of this thesis helps to fill a void in human/robot interactions involving mimicry and behavior-based design. Technological advancements in the way computers and robots identify human motion and determine for themselves how to approximate that motion have helped make possible the mimicry of observed human subjects. In fact, many researchers have developed humanoid systems that are capable of mimicking human motion data; however, these systems do not use behavior-based design. This thesis will explain the framework and theory behind our optimal behavior composition algorithm and the selection of sinusoidal motion primitives that make up a behavior library. This algorithm breaks captured motion data into various time intervals, then optimally weights the defined behaviors to best approximate the captured data. Since this routine does not reference previous or following motion sequences, discontinuities may exist between time intervals. To address this issue, the addition of a PI controller to regulate and smooth out the transitions between time intervals will be shown. The effectiveness of using the optimal behavior composition algorithm to create an approximated motion that mimics capture motion data will be demonstrated through an example configuration of hardware and a humanoid robot platform. An example of arm motion mimicry will be presented and includes various image sequences from the mimicry as well as trajectories containing the joint positions for both the human and the robot.

Šokis ir aerobika yra judesių programų pavyzdžiai - jos susideda iš tam tikra tvarka surikiuotų, pakartotinai naudojamų komponenčių. Norint efektyviai modeliuoti tokias programas, reikalinga formali žmogaus judesių notacija. Pasinaudoję esamomis priemonėmis (3D modeliavimo įrankiai, OGRE grafikos variklis, H-Anim) ir sukūrę savas, realizavome procedūrinių humanoido animacijų veikimo schemą. Ji leidžia sudaryti žmogaus judesių programą ir yra nesunkiai suprantama net ir tiems, kurie neturi animacijos ar trimačio modeliavimo patirties. Procedūrinės animacijos užrašomos XML formatu. Jas pavaizduoja mūsų peržiūros programa. Formatas leidžia abstrahuoti judesius į "procedūras", juos apjungti į sekas ir kaupti judesių bibliotekas. Turint pavienių judesių komponentes, procedūrinės animacijos kūrimas, pildymas ar keitimas yra žymiai paprastesnis ir lankstesnis, be to, tokia animacija yra nepriklausoma nuo humanoido modelio geometrijos. / Dance and aerobics are examples of movement programs – they consist of reusable components laid out in particular order. Efficient modeling of such programs requires the usage of some formal movement notation. With the help of existing tools and standards (3D modeling packages, OGRE graphics engine, H-Anim), as well as utilizing the ones we designed ourselves, we have implemented procedural humanoid animation schema. It allows for creating human movement programs and is easy to grasp even for those with no experience in animation or 3D modeling. Procedural animations are written in XML and visualized by our viewer software. Using our format, one can abstract movements into "procedures", combine them into sequences and store them in movement libraries. With all the individual movements at hand, creating, extending and modifying a procedural animation is much more simple and flexible. Moreover, this kind of animation is independent of model's geometry.

In the field of robotics there is a great interest in developing strategies and algorithms to reproduce human-like behavior. One can think of human-like machines that may replace humans in hazardous working areas, perform enduring assembly tasks, serve the elderly and handicapped, etc. The main challenges in the development of such robots are, first, to construct sophisticated electro-mechanical humanoids and, second, to plan and control human-like motor patterns. A promising idea for motion planning and control is to reparameterize any somewhat coordinated motion in terms of virtual holonomic constraints, i.e. trajectories of all degrees of freedom of the mechanical system are described by geometric relations among the generalized coordinates. Imposing such virtual holonomic constraints on the system dynamics allows to generate synchronized motor patterns by feedback control. In fact, there exist consistent geometric relations in ordinary human movements that can be used advantageously. In this thesis the virtual constraints approach is extended to a wider and rigorous use for analyzing, planning and reproducing human-like motions based on mathematical tools previously utilized for very particular control problems. It is often the case that some desired motions cannot be achieved by the robot due to limitations in available actuation power. This constraint rises the question of how to modify the mechanical design in order to achieve better performance. An underactuated planar two-link robot is used to demonstrate that springs can complement the actuation in parallel to an ordinary motor. Motion planning is carried out for the original robot dynamics while the springs are treated as part of the control action with a torque profile suited to the preplanned trajectory. Another issue discussed in this thesis is to find stable and unstable (hybrid) limit cycles for passive dynamic walking robots without integrating the full set of differential equations. Such procedure is demonstrated for the compass-gait biped by means of optimization with a reduced number of initial conditions and parameters to search. The properties of virtual constraints and reduced dynamics are exploited to solve this problem.

This thesis was motivated by a study of how robots can be taught by humans, with an emphasis on allowing persons without programming skills to teach robots. The focus of this thesis was to investigate what criteria could or should be used by a robot to evaluate whether a human teacher is (or potentially could be) a good teacher in robot learning by demonstration. In effect, choosing the teacher that can maximize the benefit to the robot using learning by imitation/demonstration. The study approached this topic by taking a technology snapshot in time to see if a representative example of research laboratory robot technology is capable of assessing teaching quality. With this snapshot, this study evaluated how humans observe teaching quality to attempt to establish measurement metrics that can be transferred as rules or algorithms that are beneficial from a robot's point of view. To evaluate teaching quality, the study looked at the teacher-student relationship from a human-human interaction perspective. Two factors were considered important in defining a good teacher: engagement and immediacy. The study gathered more literature reviews relating to further detailed elements of engagement and immediacy. The study also tried to link physical effort as a possible metric that could be used to measure the level of engagement of the teachers. An investigatory experiment was conducted to evaluate which modality the participants prefer to employ in teaching a robot if the robot can be taught using voice, gesture demonstration, or physical manipulation. The findings from this experiment suggested that the participants appeared to have no preference in terms of human effort for completing the task. However, there was a significant difference in human enjoyment preferences of input modality and a marginal difference in the robot's perceived ability to imitate. A main experiment was conducted to study the detailed elements that might be used by a robot in identifying a 'good' teacher. The main experiment was conducted in two subexperiments. The first part recorded the teacher's activities and the second part analysed how humans evaluate the perception of engagement when assessing another human teaching a robot. The results from the main experiment suggested that in human teaching of a robot (human-robot interaction), humans (the evaluators) also look for some immediacy cues that happen in human-human interaction for evaluating the engagement.