Traditionally robots have been preprogrammed to execute specific tasks. Thisapproach works well in industrial settings where robots have to execute highlyaccurate movements, such as when welding. However, preprogramming a robot isalso expensive, error prone and time consuming due to the fact that every featuresof the task has to be considered. In some cases, where a robot has to executecomplex tasks such as playing the ball-in-a-cup game, preprogramming it mighteven be impossible due to unknown features of the task. With all this in mind,this thesis examines the possibility of combining a modern learning framework,known as Learning from Demonstrations (LfD), to first teach a robot how toplay the ball-in-a-cup game by demonstrating the movement for the robot, andthen have the robot to improve this skill by itself with subsequent ReinforcementLearning (RL). The skill the robot has to learn is demonstrated with kinestheticteaching, modelled as a dynamic movement primitive, and subsequently improvedwith the RL algorithm Policy Learning by Weighted Exploration with the Returns.Experiments performed on the industrial robot KUKA LWR4+ showed that robotsare capable of successfully learning a complex skill such as playing the ball-in-a-cupgame. / Traditionellt sett har robotar blivit förprogrammerade för att utföra specifika uppgifter.Detta tillvägagångssätt fungerar bra i industriella miljöer var robotar måsteutföra mycket noggranna rörelser, som att svetsa. Förprogrammering av robotar ärdock dyrt, felbenäget och tidskrävande eftersom varje aspekt av uppgiften måstebeaktas. Dessa nackdelar kan till och med göra det omöjligt att förprogrammeraen robot att utföra komplexa uppgifter som att spela bollen-i-koppen spelet. Medallt detta i åtanke undersöker den här avhandlingen möjligheten att kombinera ettmodernt ramverktyg, kallat inläraning av demonstrationer, för att lära en robothur bollen-i-koppen-spelet ska spelas genom att demonstrera uppgiften för denoch sedan ha roboten att själv förbättra sin inlärda uppgift genom att användaförstärkande inlärning. Uppgiften som roboten måste lära sig är demonstreradmed kinestetisk undervisning, modellerad som dynamiska rörelseprimitiver, ochsenare förbättrad med den förstärkande inlärningsalgoritmen Policy Learning byWeighted Exploration with the Returns. Experiment utförda på den industriellaKUKA LWR4+ roboten visade att robotar är kapabla att framgångsrikt lära sigspela bollen-i-koppen spelet

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.

What is the difference between intention and action? To start answering this complex question, we have created a serious game that allows us to capture a large quantity of experimental data and study human behavior. In the game, users catch flies, presented to the left or to the right of the screen, by dragging the tongue of a frog across a touchscreen monitor. The movement of interest has a predefined starting point (the frog) and necessarily transits through a via-point (a narrow corridor) before it proceeds to the chosen left/right direction. Meanwhile, the game collects data about the movement performed by the player. This work is focused on the analysis of such movements. We try to find criteria that will allow us to predict (as early as possible) the direction (left/right) chosen by the player. This is done by analyzing kinematic information (e.g. trajectory, velocity profile, etc.). Also, processing such data according to the dynamical movement primitives approach, allows us to find further criteria that support a classification of human movement. Our preliminary results show that individually considered, participants tend to create and use stereotypical behaviors that can be used to formulate predictions about the subjects’ intention to reach in one direction or the other, early after the onset of the movement.

This thesis aims to parameterize and generalize functions for robotic use. The goal is to simplify the usage of robot arms. This thesis explores robot functionalities within the theme of simple cooking tasks. The functions explored are cutting objects, stirring bowls and pick and place. An environment where objects can be moved around is created and each individual task can be described as a function with parameters. In addition to this DMP (Dynamic Movement Primitives) is incorporated into the functions for future usage in mimicking human motion when performing tasks. The result of actions being parameterized and general in their definitions makes them robust and easy to use in an environment where objects are not always located in the same positions. The incorporation of the DMP adds to the generality of the functions, being able to use the same setup without modifications for objects of different sizes as well as having trajectory inputs for robot execution.

Stretching som uppvärmningsrutin inför idrottsaktiviteter anses ha både skadeförebyggande och prestationshöjande effekter. Studier antyder att statisk stretching kan ha negativ inverkan på prestationen, särskilt explosiva aktiviteter som hopp och sprintlöpning. Syftet med studien var att undersöka effekten av statisk stretching (SS) respektive dynamisk (DR) rörlighets-uppvärmningsprotokoll på prestationen vid sprintlöpning över 200 meter samt inverkan av muskellängd/rörelseomfång på eventuella effekter. Elva träningsvana löpare, 20-35 år, sju män och fyra kvinnor genomförde vid två tillfällen maximal 200-meterslöpning. Löpningarna föregicks vid ena tillfället av SS och det andra av DR i en randomiserad ordning. Tiden mättes med ett portabelt fotocellsystem. Deltagarna utgjorde sina egna kontroller och skillnaden i löptid mellan SS och DR analyserades parvis (Wilcoxon signed rank test). Korrelation mellan löptid och deltagarnas ROM i nedre extremiteten, mätt med goniometer analyserades (Kendall’s Tau B). Tendens till snabbare löptider visades efter DR (1,01%, p=0,077) jämfört med SS. Skillnader, dock ej signifikanta var störst första 100 meter (2,78%) och omvänt avslutande 100 meter(-0,40%). Ett samband antyddes mellan hur snabba löparna var och effekten av SS-DR (Tau B=0,382), där resultaten för männen, som generellt var snabbare visade signifikant samband (Tau B=0,905, p=0,003). Inga samband återfanns mellan ROM/muskellängd och prestation. Signifikant samband sågs dock mellan duration vid stretching och löptid (Tau B=0,48-0,56, p=0,021-0,042). Studien fann i linje med tidigare forskning tendenser till snabbare löptider vid DR jämfört med SS. Eventuella effekter av stretching kan vara små men av betydelse för snabba löpare på distanser upp till 200 meter. Fortsatt forskning på området bör inkludera homogena grupper där slumpmässiga effekter på prestationen minimeras. Utifrån resultaten föreslås att DR inkluderas i uppvärmningen framför SS.

The ability to learn is essential for robots to function and perform services within a dynamic human environment. Robot programming by demonstration facilitates learning through a human teacher without the need to develop new code for each task that the robot performs. In order for learning to be generalizable, the robot needs to be able to grasp the underlying structure of the task being learned. This requires appropriate knowledge abstraction and representation. The goal of this thesis is to develop a learning by imitation system that abstracts knowledge of human demonstrations of a task and represents the abstracted knowledge in a hierarchical framework. The learning by imitation system is capable of performing both action and object recognition based on video stream data at the lower level of the hierarchy, while the sequence of actions and object states observed is reconstructed at the higher level of the hierarchy in order to form a coherent representation of the task. Furthermore, error recovery capabilities are included in the learning by imitation system to improve robustness to unexpected situations during task execution. The first part of the thesis focuses on motion learning to allow the robot to both recognize the actions for task representation at the higher level of the hierarchy and to perform the actions to imitate the task. In order to efficiently learn actions, the actions are segmented into meaningful atomic units called motion primitives. These motion primitives are then modeled using dynamic movement primitives (DMPs), a dynamical system model that can robustly generate motion trajectories to arbitrary goal positions while maintaining the overall shape of the demonstrated motion trajectory. The DMPs also contain weight parameters that are reflective of the shape of the motion trajectory. These weight parameters are clustered using affinity propagation (AP), an efficient exemplar clustering algorithm, in order to determine groups of similar motion primitives and thus, performing motion recognition. The approach of DMPs combined with APs was experimentally verified on two separate motion data sets for its ability to recognize and generate motion primitives. The second part of the thesis outlines how the task representation is created and used for imitating observed tasks. This includes object and object state recognition using simple computer vision techniques as well as the automatic construction of a Petri net (PN) model to describe an observed task. Tasks are composed of a sequence of actions that have specific pre-conditions, i.e. object states required before the action can be performed, and post-conditions, i.e. object states that result from the action. The PNs inherently encode pre-conditions and post-conditions of a particular event, i.e. action, and can model tasks as a coherent sequence of actions and object states. In addition, PNs are very flexible in modeling a variety of tasks including tasks that involve both sequential and parallel components. The automatic PN creation process has been tested on both a sequential two block stacking task and a three block stacking task involving both sequential and parallel components. The PN provides a meaningful representation of the observed tasks that can be used by a robot to imitate the tasks. Lastly, error recovery capabilities are added to the learning by imitation system in order to allow the robot to readjust the sequence of actions needed during task execution. The error recovery component is able to deal with two types of errors: unexpected, but known situations and unexpected, unknown situations. In the case of unexpected, but known situations, the learning system is able to search through the PN to identify the known situation and the actions needed to complete the task. This ability is useful not only for error recovery from known situations, but also for human robot collaboration, where the human unexpectedly helps to complete part of the task. In the case of situations that are both unexpected and unknown, the robot will prompt the human demonstrator to teach how to recover from the error to a known state. By observing the error recovery procedure and automatically extending the PN with the error recovery information, the situation encountered becomes part of the known situations and the robot is able to autonomously recover from the error in the future. This error recovery approach was tested successfully on errors encountered during the three block stacking task.

The ability to learn is essential for robots to function and perform services within a dynamic human environment. Robot programming by demonstration facilitates learning through a human teacher without the need to develop new code for each task that the robot performs. In order for learning to be generalizable, the robot needs to be able to grasp the underlying structure of the task being learned. This requires appropriate knowledge abstraction and representation. The goal of this thesis is to develop a learning by imitation system that abstracts knowledge of human demonstrations of a task and represents the abstracted knowledge in a hierarchical framework. The learning by imitation system is capable of performing both action and object recognition based on video stream data at the lower level of the hierarchy, while the sequence of actions and object states observed is reconstructed at the higher level of the hierarchy in order to form a coherent representation of the task. Furthermore, error recovery capabilities are included in the learning by imitation system to improve robustness to unexpected situations during task execution. The first part of the thesis focuses on motion learning to allow the robot to both recognize the actions for task representation at the higher level of the hierarchy and to perform the actions to imitate the task. In order to efficiently learn actions, the actions are segmented into meaningful atomic units called motion primitives. These motion primitives are then modeled using dynamic movement primitives (DMPs), a dynamical system model that can robustly generate motion trajectories to arbitrary goal positions while maintaining the overall shape of the demonstrated motion trajectory. The DMPs also contain weight parameters that are reflective of the shape of the motion trajectory. These weight parameters are clustered using affinity propagation (AP), an efficient exemplar clustering algorithm, in order to determine groups of similar motion primitives and thus, performing motion recognition. The approach of DMPs combined with APs was experimentally verified on two separate motion data sets for its ability to recognize and generate motion primitives. The second part of the thesis outlines how the task representation is created and used for imitating observed tasks. This includes object and object state recognition using simple computer vision techniques as well as the automatic construction of a Petri net (PN) model to describe an observed task. Tasks are composed of a sequence of actions that have specific pre-conditions, i.e. object states required before the action can be performed, and post-conditions, i.e. object states that result from the action. The PNs inherently encode pre-conditions and post-conditions of a particular event, i.e. action, and can model tasks as a coherent sequence of actions and object states. In addition, PNs are very flexible in modeling a variety of tasks including tasks that involve both sequential and parallel components. The automatic PN creation process has been tested on both a sequential two block stacking task and a three block stacking task involving both sequential and parallel components. The PN provides a meaningful representation of the observed tasks that can be used by a robot to imitate the tasks. Lastly, error recovery capabilities are added to the learning by imitation system in order to allow the robot to readjust the sequence of actions needed during task execution. The error recovery component is able to deal with two types of errors: unexpected, but known situations and unexpected, unknown situations. In the case of unexpected, but known situations, the learning system is able to search through the PN to identify the known situation and the actions needed to complete the task. This ability is useful not only for error recovery from known situations, but also for human robot collaboration, where the human unexpectedly helps to complete part of the task. In the case of situations that are both unexpected and unknown, the robot will prompt the human demonstrator to teach how to recover from the error to a known state. By observing the error recovery procedure and automatically extending the PN with the error recovery information, the situation encountered becomes part of the known situations and the robot is able to autonomously recover from the error in the future. This error recovery approach was tested successfully on errors encountered during the three block stacking task.

No description available.