Thesis (MScEng)--Stellenbosch University, 2011. / ENGLISH ABSTRACT: RoboCup promotes research in robotics and multi-robot systems (MRS). The RoboCup Small Size League (SSL), in particular, offers an entry level opportunity to take part in this field of study. This thesis presents a starting phase for research in robotics and MRS at Stellenbosch University. It includes the full documentation of the mechanical, electronic and software design of an omni-directional soccer robot for RoboCup SSL. The robot is also meant to operate as a hardware and software development platform for research in MRS. The platform was therefore designed with high-level programming language compatibility, a wide range of connectivity, and modularity in mind. The robot uses a single board computer (SBC) running a Linux operating system to accomplish these objectives. Moreover, a driver class library was written in C++ as a software application interface (API) for future development on the robot platform. The robot was also developed with a particular focus on a distributed control architecture. "Player" was implemented as the middleware, which can be used for communication between multiple robots in a distributed environment. Additionally, three tests were performed to demonstrate the functionality of the prototype: a PI speed control test, a direction accuracy test and a static communication test using the middleware. Recommendations for possible future work are also given. / AFRIKAANSE OPSOMMING: RoboCup bevorder navorsing in robotika en multi-robot-stelsels (MRS). Die RoboCup Klein Liga (KL) bied in die besonder die geleentheid om op intreevlak navorsing te doen in hierdie veld. Hierdie tesis verteenwoordig die eerste fase van navorsing in robotika en MRS by Stellenbosch Universiteit. Dit sluit die volledige dokumentasie van die meganiese, elektroniese en sagteware-ontwerp van ’n omnidireksionele sokker-robot vir die KL in. Die robot is ook veronderstel om te dien as ’n hardeware- en sagteware-ontwikkelingsplatform vir navorsing in MRS. Die platform is dus ontwerp met ’n verskeidenheid van uitbreingsmoontlikhede en modulariteit in gedagte asook die moontlikheid om gebruik te maak van ’n hoë-vlak programmeertaal. Om hierdie doelwitte te bereik, maak die robot gebruik van ’n enkel-bord-rekenaar met ’n Linux bedryfstelsel. Verder was ’n sagteware drywer in C++ geskryf om te dien as ’n sagteware-koppelvlak vir toekomstige ontwikkeling op die robot platform. Die robot is ook ontwikkel met die besondere fokus op ’n gedesentraliseerde beheerstels. Player was geïmplementeer as die middelware, wat gebruik kan word vir kommunikasie tussen verskeie robotte in ’n gedesentralliseerde beheerstelsel. Daar is drie toetse uitgevoer om die funksionaliteit van die prototipe te demonstreer, ’n PI spoed beheer toets, ’n rigting akkuraatheidstoets en ’n statiese kommunikasie toets deur van die middelware gebruik te maak. Aanbevelings vir moontlike toekomstige werk word ook verskaf.

Thesis (MEng)--Stellenbosch University, 2014. / ENGLISH ABSTRACT: The RoboCup offers a research platform to advance robotics and multi-robot cooperation in dynamic environments. This project builds on work previously done to develop a research platform for multi-robot cooperation at Stellenbosch University. This thesis describes the development of an active ball handling system for a robot in the RoboCup Small Size League (SSL). This was achieved by building on the work done in the previous projects. The hardware for the kicker and dribbler mechanisms on the robot were implemented and tested to characterise their capabilities. The kicker was characterised to control the speed at which a ball is kicked and the dribbler for optimal control over a ball. More accurate movement was required and the Proportional Integral and Derivative (PID) controllers for translational and rotational movement on the robot were improved. The test results show an improvement in straight line trajectory tracking when compared to those of the previous controllers. Dribble control sensors were implemented on the robot for successful dribbling by the robot. This resulted in a significant improvement to the dribbling ability of the robot when these sensors are used. This dribbling ability was compared to the dribbling ability of the robot when no feedback was received from the sensors. Lastly a proposed curved trajectory tracking algorithm was tested by combining translational and rotational movement of the robot. This algorithm showed the capabilities of the robot to follow a curved trajectory with the improved translational and rotational controllers. / AFRIKAANSE OPSOMMING: Die RoboCup bied ’n navorsingsplatvorm om robotika en multi-robot samewerking in ’n dinamiese omgewing te bevorder. Hierdie projek bou voort op werk wat reeds gedoen is om ’n navorsingsplatvorm vir multi-robot samewerking aan die Universiteit van Stellenbosch te ontwikkel. Hierdie tesis beskryf die ontwikkeling van ’n aktiewe balhanteringsstelsel vir ’n robot in die RoboCup Klein Liga (KL). Dit is bereik deur voort te bou op die werk wat in vorige projekte gedoen is. Die hardeware vir die skopper- en dribbelmeganismes is geïmplementeer en getoets om hulle vermoëns te karakteriseer. Die skopper is gekenmerk deur die spoed waarteen ’n bal geskop word en die dribbler vir optimale beheer oor ’n bal. Meer akkurate beweging was nodig en die PID-beheerders vir translasie- en rotasiebeweging in die robot is verbeter. Die resultate van die toetse toon ’n verbetering in reguitlynbeweging in vergelyking met dié van die vorige beheerders. Dribbelbeheersensors is in die robot geïmplementeer vir suksesvolle dribbelbeweging deur die robot. Gevolglik is daar ’n aansienlike verbetering in die dribbelvermoë van die robot wanneer hierdie sensors gebruik word. Hierdie dribbelvermoë is vergelyk met die dribbelvermoë wanneer die robot geen terugvoer van die sensors ontvang nie. Laastens is ’n voorgestelde algoritme vir die robot om ’n geboë trajek te volg, getoets. Dit is bereik deur die translasie- en die rotasiebeweging van die robot te kombineer. Hierdie algoritme het die vermoë van die robot om ’n geboë baan te laat volg deur gebruik te maak van die verbeterde translasie- en rotasiebeheerders.

Agent-based systems usually operate in real-time, stochastic and dynamic environments. Many theoretical and applied techniques have been applied to the investigation of agent architecture with respect to communication, cooperation, and learning, in order to provide a framework for implementing artificial intelligence and computing techniques. Intelligent agents are required to be able to adapt and learn in uncertain environments via communication and collaboration (in both competitive and cooperative situations). The ability of reasoning and learning is one fundamental feature for intelligent agents. Due to the inherent complexity, however, it is difficult to verify the properties of the complex and dynamic environments a priori. Since analytic techniques are inadequate for solving these problems, reinforcement learning (RL) has appeared as a popular approach by mapping states to actions, so as to maximise the long-term rewards. Computer simulation is needed to replicate an experiment for testing and verifying the efficiency of simulation-based optimisation techniques. In doing so, a simulation testbed called robot soccer is used to test the learning algorithms in the specified scenarios. This research involves the investigation of simulation-based optimisation techniques in agent-based systems. Firstly, a hybrid agent teaming framework is presented for investigating agent team architecture, learning abilities, and other specific behaviors. Secondly, the novel reinforcement learning algorithms to verify goal-oriented agents; competitive and cooperative learning abilities for decision-making are developed. In addition, the function approximation technique known as tile coding (TC), is used to avoid the state space growing exponentially with the curse of dimensionality. Thirdly, the underlying mechanism of eligibility traces is analysed in terms of on-policy algorithm and off-policy algorithm, accumulating traces and replacing traces. Fourthly, the "design of experiment" techniques, such as Simulated Annealing method and Response Surface methodology, are integrated with reinforcement learning techniques to enhance the performance. Fifthly, a methodology is proposed to find the optimal parameter values to improve convergence and efficiency of the learning algorithms. Finally, this thesis provides a serious full-fledged numerical analysis on the efficiency of various RL techniques.

Action planning has been used in the field of robotics for solving long-running tasks. In the robot architectures field, it is also known as the deliberative layer. However, there is still a gap between the symbolic representation on the one hand and the low-level control and sensor representation on the other. In addition, the definition of a planning problem for a complex, real-world robot is not trivial. The planning process could become intractable as its search spaces become large. As the defined planning problem determines the complexity and the computationability for solving the problem, it should contain only relevant states. In this work, a novel approach which amalgamates Description Logic (DL) reasoning with Hierarchical Task Network (HTN) planning is introduced. The planning domain description as well as fundamental HTN planning concepts are represented in DL and can therefore be subject to DL reasoning; from these representations, concise planning problems are generated for HTN planning. The method is presented through an example in the robot navigation domain. In addition, a case study of the RoboCup@Home domain is given. As proof of concept, a well-known planning problem that often serves as a benchmark, namely that of the blocks-world, is modeled and solved using this approach. An analysis of the performance of the approach has been conducted and the results show that this approach yields significantly smaller planning problem descriptions than those generated by current representations in HTN planning.

This work describes a design of an agent model for robotic soccer based on the DEVS formalism. There is also presented a design of own DEVS simulator (based on classic DEVS simulator) for parallel realtime simulations. Functionality of the simulator and the model is shown on an example of a soccer client for RoboCup Soccer Server. Based on this client, there is also presented a design of a library for easier creation of soccer clients for RoboCup.

No description available.

Communication between humans and interactive robots will benefit if people have a clear mental model of the robots' intent and awareness. The aim with this thesis was to investigate how human-robot interaction is affected by manipulation of social cues on the robot. The research questions were: How do social cues affect mental models of the Pepper robot, and how can a participatory design method be used for investigating how the Pepper robot could communicate intent and awareness? The hypothesis for the second question was that nonverbal cues would be preferred over verbal cues. An existing standard platform was used, Softbank's Pepper, as well as state-of-the-art tasks from the RoboCup@Home challenge. The rule book and observations from the 2018 competition were thematically coded and the themes created eight scenarios. A participatory design method called PICTIVE was used in a design study, where five student participants went through three phases, label, sketch and interview, to create a design for how the robot should communicate intent and awareness. The use of PICTIVE was a suitable way to extract a lot of design ideas. However, not all scenarios were optimal for the task. The design study confirmed the use of mediating physical attributes to alter the mental model of a humanoid robot to reach common ground. Further, it did not confirm the hypothesis that nonverbal cues would be preferred over verbal cues, though it did show that verbal cues would not be enough. This, however, needs to be further tested in live interactions.

Für mobile autonome Roboter ist ein solides Modell der Umwelt eine wichtige Voraussetzung um die richtigen Entscheidungen zu treffen. Die gängigen existierenden Verfahren zur Weltmodellierung basieren auf dem Bayes-Filter und verarbeiten Informationen mit Hidden Markov Modellen. Dabei wird der geschätzte Zustand der Welt (Belief) iterativ aktualisiert, indem abwechselnd Sensordaten und das Wissen über die ausgeführten Aktionen des Roboters integriert werden; alle Informationen aus der Vergangenheit sind im Belief integriert. Wenn Sensordaten nur einen geringen Informationsgehalt haben, wie zum Beispiel Peilungsmessungen, kommen sowohl parametrische Filter (z.B. Kalman-Filter) als auch nicht-parametrische Filter (z.B. Partikel-Filter) schnell an ihre Grenzen. Das Problem ist dabei die Repräsentation des Beliefs. Es kann zum Beispiel sein, dass die gaußschen Modelle beim Kalman-Filter nicht ausreichen oder Partikel-Filter so viele Partikel benötigen, dass die Rechendauer zu groß wird. In dieser Dissertation stelle ich ein neues Verfahren zur Weltmodellierung vor, das Informationen nicht sofort integriert, sondern erst bei Bedarf kombiniert. Das Verfahren wird exemplarisch auf verschiedene Anwendungsfälle aus dem RoboCup (autonome Roboter spielen Fußball) angewendet. Es wird gezeigt, wie vierbeinige und humanoide Roboter ihre Position und Ausrichtung auf einem Spielfeld sehr präzise bestimmen können. Grundlage für die Lokalisierung sind bildbasierte Peilungsmessungen zu Objekten. Für die Roboter-Ausrichtung sind dabei Feldlinien eine wichtige Informationsquelle. In dieser Dissertation wird ein Verfahren zur Erkennung von Feldlinien in Kamerabildern vorgestellt, das ohne Kalibrierung auskommt und sehr gute Resultate liefert, auch wenn es starke Schatten und Verdeckungen im Bild gibt. / For autonomous mobile robots, a solid world model is an important prerequisite for decision making. Current state estimation techniques are based on Hidden Markov Models and Bayesian filtering. These methods estimate the state of the world (belief) in an iterative manner. Data obtained from perceptions and actions is accumulated in the belief which can be represented parametrically (like in Kalman filters) or non-parametrically (like in particle filters). When the sensor''s information gain is low, as in the case of bearing-only measurements, the representation of the belief can be challenging. For instance, a Kalman filter''s Gaussian models might not be sufficient or a particle filter might need an unreasonable number of particles. In this thesis, I introduce a new state estimation method which doesn''t accumulate information in a belief. Instead, perceptions and actions are stored in a memory. Based on this, the state is calculated when needed. The system has a particular advantage when processing sparse information. This thesis presents how the memory-based technique can be applied to examples from RoboCup (autonomous robots play soccer). In experiments, it is shown how four-legged and humanoid robots can localize themselves very precisely on a soccer field. The localization is based on bearings to objects obtained from digital images. This thesis presents a new technique to recognize field lines which doesn''t need any pre-run calibration and also works when the field lines are partly concealed and affected by shadows.