Learning Grasp Affordances from Vision

Monimutkaisissa ja muuttuvissa ympäristöissä työskentelevät robotit tarvitsevat kykyä manipuloida ja tarttua esineisiin. Tämä työ tutkii robottitarttumisen ja robottitartuntapis-teiden koneoppimisen aiempaa tutkimusta ja nykytilaa. Nykyaikaiset menetelmät käydään läpi, ja Le:n koneoppimiseen pohjautuva luokitin toteutetaan, koska se tarjoaa parhaan onnistumisprosentin tutkituista menetelmistä ja on muokattavissa sopivaksi käytettävissä olevalle robotille. Toteutettu menetelmä käyttää intensititeettikuvaan ja syvyyskuvaan po-hjautuvia ominaisuuksi luokitellakseen potentiaaliset tartuntapisteet. Tämän toteutuksen tulokset esitellään.

ContinuousMultimodal Global Optimization with Differential Evolution-Based Methods

Metaheuristic methods have become increasingly popular approaches in solving global optimization problems. From a practical viewpoint, it is often desirable to perform multimodal optimization which, enables the search of more than one optimal solution to the task at hand. Population-based metaheuristic methods offer a natural basis for multimodal optimization. The topic has received increasing interest especially in the evolutionary computation community. Several niching approaches have been suggested to allow multimodal optimization using evolutionary algorithms. Most global optimization approaches, including metaheuristics, contain global and local search phases. The requirement to locate several optima sets additional requirements for the design of algorithms to be effective in both respects in the context of multimodal optimization. In this thesis, several different multimodal optimization algorithms are studied in regard to how their implementation in the global and local search phases affect their performance in different problems. The study concentrates especially on variations of the Differential Evolution algorithm and their capabilities in multimodal optimization. To separate the global and local search search phases, three multimodal optimization algorithms are proposed, two of which hybridize the Differential Evolution with a local search method. As the theoretical background behind the operation of metaheuristics is not generally thoroughly understood, the research relies heavily on experimental studies in finding out the properties of different approaches. To achieve reliable experimental information, the experimental environment must be carefully chosen to contain appropriate and adequately varying problems. The available selection of multimodal test problems is, however, rather limited, and no general framework exists. As a part of this thesis, such a framework for generating tunable test functions for evaluating different methods of multimodal optimization experimentally is provided and used for testing the algorithms. The results demonstrate that an efficient local phase is essential for creating efficient multimodal optimization algorithms. Adding a suitable global phase has the potential to boost the performance significantly, but the weak local phase may invalidate the advantages gained from the global phase.

Promoting Programming Learning. Engagement, Automatic Assessment with Immediate Feedback in Visualizations

The skill of programming is a key asset for every computer science student. Many studies have shown that this is a hard skill to learn and the outcomes of programming courses have often been substandard. Thus, a range of methods and tools have been developed to assist students’ learning processes. One of the biggest fields in computer science education is the use of visualizations as a learning aid and many visualization based tools have been developed to aid the learning process during last few decades. Studies conducted in this thesis focus on two different visualizationbased tools TRAKLA2 and ViLLE. This thesis includes results from multiple empirical studies about what kind of effects the introduction and usage of these tools have on students’ opinions and performance, and what kind of implications there are from a teacher’s point of view. The results from studies in this thesis show that students preferred to do web-based exercises, and felt that those exercises contributed to their learning. The usage of the tool motivated students to work harder during their course, which was shown in overall course performance and drop-out statistics. We have also shown that visualization-based tools can be used to enhance the learning process, and one of the key factors is the higher and active level of engagement (see. Engagement Taxonomy by Naps et al., 2002). The automatic grading accompanied with immediate feedback helps students to overcome obstacles during the learning process, and to grasp the key element in the learning task. These kinds of tools can help us to cope with the fact that many programming courses are overcrowded with limited teaching resources. These tools allows us to tackle this problem by utilizing automatic assessment in exercises that are most suitable to be done in the web (like tracing and simulation) since its supports students’ independent learning regardless of time and place. In summary, we can use our course’s resources more efficiently to increase the quality of the learning experience of the students and the teaching experience of the teacher, and even increase performance of the students. There are also methodological results from this thesis which contribute to developing insight into the conduct of empirical evaluations of new tools or techniques. When we evaluate a new tool, especially one accompanied with visualization, we need to give a proper introduction to it and to the graphical notation used by tool. The standard procedure should also include capturing the screen with audio to confirm that the participants of the experiment are doing what they are supposed to do. By taken such measures in the study of the learning impact of visualization support for learning, we can avoid drawing false conclusion from our experiments. As computer science educators, we face two important challenges. Firstly, we need to start to deliver the message in our own institution and all over the world about the new – scientifically proven – innovations in teaching like TRAKLA2 and ViLLE. Secondly, we have the relevant experience of conducting teaching related experiment, and thus we can support our colleagues to learn essential know-how of the research based improvement of their teaching. This change can transform academic teaching into publications and by utilizing this approach we can significantly increase the adoption of the new tools and techniques, and overall increase the knowledge of best-practices. In future, we need to combine our forces and tackle these universal and common problems together by creating multi-national and multiinstitutional research projects. We need to create a community and a platform in which we can share these best practices and at the same time conduct multi-national research projects easily.

Kumppanuusohjelman strateginen johtaminen - Monitapaustutkimus puolustushallinnossa

Puolustushallinnossa syntyi 2000-luvun alussa strateginen aie keskittyä ydintoimintoihin, ulkoistaa pääosa tukitoiminnoista ja saavuttaa kustannussäästöjä, jotka voitaisiin kohdentaa ydintoimintoihin. Puolustusministeriö perusti ulkoistamisen hallinnoimiseksi kumppanuusohjelman, mihin kuului lähes alusta alkaen kuusi hanketta, jotka ovat nyt toteuttamisvaiheessa. Näistä valittiin neljä tähän tutkimukseen: maavoimien materiaalin kunnossapito, puolustusvoimien ruokahuolto, puolustusvoimien vaatetushuolto ja puolustushallinnon talous- ja henkilöstöhallinto. Kumppanuusohjelman strategisen johtamisen tutkimus perustuupuolustusministeriön ja puolustusvoimien asiakirja-aineistoihin sekä puolustushallinnon ylimmän johdon ja hankejohtajien haastatteluihin. Kumppanuusohjelmaa ja -hankkeita on seurattu vuodesta 2000 vuoden 2010 kevääseen asti. Tarkastelu kohdistuu strategiaprosessiin ja strategian sisältöön ”puolustushallinnon konsernissa”, johon kuuluvat tässä tutkimuksessa puolustusministeriö, pääesikunta ja puolustushaarat. Tutkimuksen tulokset tukevat viitekehyksessä esitettyjä näkökohtia. Laajan kumppanuusohjelman hallinta edellyttää hyvää strategisen johtamisen otetta. Selkeät päämäärät ja tavoitteet luovat perustan strategiaprosessille. Kumppanuusohjelman strategia muotoutui tarkastelujakson aikana niin strategiaprosessien kuin strategian sisällön suhteen. Toimiva ohjausjärjestelmä on puolustushallinnon avaintoimintoja strategisessa johtamisessa. Resurssiperusteinen strategia osoittautui tärkeäksi ulkoistamisissa ja sosiaalinen pääoma, erityisesti yhteisymmärrys osoittautui tärkeäksi tekijäksi konsernijohtamisessa. Kumppanuusohjelman strategisen johtamisen toimivuuden kehittämiseksi kartoitettiin tekijöitä, jotka muodostuivat tehokkaan strategisen johtamisen esteiksi. Esteitä kartoitettiin kumppanuusohjelmasta ja -hankkeista. Tutkimuksen tärkein kontribuutio kohdistuu strategisen johtamisen kehittämiseen. Se on mahdollista hankkimalla konsernin johtotasoilla yhteisymmärryskehittämisohjelmasta ennen ohjelman käynnistämistä, ottamalla huomioon strategisen johtamisen perusteet, ottamalla käyttöön jatkuva strategiaprosessi ja turvaamalla riittävä osaaminen kumppanuusohjelmassa ja -hankkeissa.

Epälineaaristen regressiomenetelmien vertaaminen robottikäden otemallinnuksessa

Tässä työssä verrattiin monikerrosperseptronin, radiaalikantafunktioverkon, tukivektoriregression ja relevanssivektoriregression soveltuvuutta robottikäden otemallinnukseen. Menetelmille ohjelmoitiin koeympäristö Matlabiin, jossa mallit koestettiin kolmiulotteisella kappaledatalla. Koejärjestely sisälsi kaksi vaihetta. Kokeiden ensimmäisessä vaiheessa menetelmille haettiin sopivat parametrit ja toisessa vaiheessa menetelmät koestettiin. Kokeilla kerättiin dataa menetelmien keskinäiseen vertailuun. Vertailussa huomioitiin laskentanopeus, koulutusaika ja tarkkuus. Tukivektoriregressio löydettiin potentiaaliseksi vaihtoehdoksi mallintamiseen. Tukivektoriregression koetuloksia analysoitiin muita menetelmiä enemmän hyvien koetulosten takia.

Tactile-Proprioceptive Robotic Grasping

Robotic grasping has been studied increasingly for a few decades. While progress has been made in this field, robotic hands are still nowhere near the capability of human hands. However, in the past few years, the increase in computational power and the availability of commercial tactile sensors have made it easier to develop techniques that exploit the feedback from the hand itself, the sense of touch. The focus of this thesis lies in the use of this sense. The work described in this thesis focuses on robotic grasping from two different viewpoints: robotic systems and data-driven grasping. The robotic systems viewpoint describes a complete architecture for the act of grasping and, to a lesser extent, more general manipulation. Two central claims that the architecture was designed for are hardware independence and the use of sensors during grasping. These properties enables the use of multiple different robotic platforms within the architecture. Secondly, new data-driven methods are proposed that can be incorporated into the grasping process. The first of these methods is a novel way of learning grasp stability from the tactile and haptic feedback of the hand instead of analytically solving the stability from a set of known contacts between the hand and the object. By learning from the data directly, there is no need to know the properties of the hand, such as kinematics, enabling the method to be utilized with complex hands. The second novel method, probabilistic grasping, combines the fields of tactile exploration and grasp planning. By employing well-known statistical methods and pre-existing knowledge of an object, object properties, such as pose, can be inferred with related uncertainty. This uncertainty is utilized by a grasp planning process which plans for stable grasps under the inferred uncertainty.

Ulkomaalaisen yrityksen verkostosuhteet Venäjällä

Tutkimuksen tavoitteena on konkreettisen yritysverkoston avulla selvittää, minkälaisia ovat ulkomaalaisen yrityksen potentiaaliset kumppanit ja yritysten väliset suhteet Venäjällä. Toisena tavoitteena on kuvata käytännön työelämään sopivalla menetelmällä riittävän kokonaisvaltaisesti yritysverkoston kumppanit sekä kumppaneiden ja kärkiyrityksen väliset suhteet. Samalla tarkastellaan yritysten välisten suhteiden riskejä. Selvitysmenetelmällä pyritään nopeuteen ja ketteryyteen ja sen tavoitteena on lisätä ulkomaisen johdon käsitystä yritysverkostosta johdon päätöksentekoa varten. Tutkimus jakaantuu teoria tarkasteluun ja yhden Venäjällä toimivan ulkomaisen yrityksen osto-osaston verkostoa selvittävään empiiriseen osaan. Teoriatarkastelussa selvitetään erilaisia lähestymistapoja ja laajempia viitekehyksiä yritysverkostojen tutkimukseen. Teoriatarkastelun perusteella valittiin viitekehykset yrityskumppaneiden ja yritysten välisen suhteen sekä riskien arviointiin. Empiirisen osan tutkimus toteutettiin haastattelukyselytutkimuksena perustuen näihin viitekehyksiin. Yrityskumppaneita ja yritysten välisiä suhteita tarkastellaan tilastollisin menetelmin ja riskejä arvioidaan laadullisella tutkimusotteella. Tutkimustulokset vastaavat monelta osin liiketoimintakulttuurista ja –ympäristöstä saatua kokemukseen ja tutkimustietoon perustuvaa käsitystä. Verkostoitumisen kulmakivet ovat hyvin toimivat ja määritellyt vaihdannan liiketoiminta- ja tukiprosessit, hyvin tunnetut kumppanit ja tälle perustalle rakennetut sosiaaliset suhteet sekä liiketoimintaympäristöön ja –kulttuuriin soveltuvat yhteistyökompetenssit. Tutkitun yritysverkoston yhteistyösuhteet voidaan jakaa hierarkkiseen organisaatiokumppanuuteen, toimittajakumppanuuteen, luottamukseen perustuvaan markkinaehtoiseen suhteeseen ja opportunistiseen markkinasuhteeseen. Hyviä yhteistyökumppaneita ja –suhteita löytyy taustaltaan erilaisista toimittajista. Tutkimuksessa käytetyt viitekehykset toimivat hyvin erityisesti yrityskumppanin arvioinnissa. Yritysten välisen suhteen arviointiin käytetyn viitekehyksen ongelmat liittyivät lähinnä erilaiseen liiketoimintakulttuuriin ja käsitykseen yritysten välisestä strategisesta suhteesta. Riskit liittyivät toimitussuhteeseen useammin kuin omaan organisaatioon tai toimittajaan.

Qualitative Characteristics and Quantitative Measures of Solution's Reliability in Discrete Optimization: Traditional Analytical Approaches, Innovative Computational Methods and Applicability

The purpose of this thesis is twofold. The first and major part is devoted to sensitivity analysis of various discrete optimization problems while the second part addresses methods applied for calculating measures of solution stability and solving multicriteria discrete optimization problems. Despite numerous approaches to stability analysis of discrete optimization problems two major directions can be single out: quantitative and qualitative. Qualitative sensitivity analysis is conducted for multicriteria discrete optimization problems with minisum, minimax and minimin partial criteria. The main results obtained here are necessary and sufficient conditions for different stability types of optimal solutions (or a set of optimal solutions) of the considered problems. Within the framework of quantitative direction various measures of solution stability are investigated. A formula for a quantitative characteristic called stability radius is obtained for the generalized equilibrium situation invariant to changes of game parameters in the case of the H¨older metric. Quality of the problem solution can also be described in terms of robustness analysis. In this work the concepts of accuracy and robustness tolerances are presented for a strategic game with a finite number of players where initial coefficients (costs) of linear payoff functions are subject to perturbations. Investigation of stability radius also aims to devise methods for its calculation. A new metaheuristic approach is derived for calculation of stability radius of an optimal solution to the shortest path problem. The main advantage of the developed method is that it can be potentially applicable for calculating stability radii of NP-hard problems. The last chapter of the thesis focuses on deriving innovative methods based on interactive optimization approach for solving multicriteria combinatorial optimization problems. The key idea of the proposed approach is to utilize a parameterized achievement scalarizing function for solution calculation and to direct interactive procedure by changing weighting coefficients of this function. In order to illustrate the introduced ideas a decision making process is simulated for three objective median location problem. The concepts, models, and ideas collected and analyzed in this thesis create a good and relevant grounds for developing more complicated and integrated models of postoptimal analysis and solving the most computationally challenging problems related to it.

Roles of leadership in complex environments : Enhancing Knowledge Flows in Organisational Constellations through Practice-Based Innovation Processes

Global challenges, complexity and continuous uncertainty demand development of leadership approaches, employees and multi-organisation constellations. Current leadership theories do not sufficiently address the needs of complex business environments. First of all, before successful leadership models can be applied in practice, leadership needs to shift from the industrial age to the knowledge era. Many leadership models still view leadership solely through the perspective of linear process thinking. In addition, there is not enough knowledge or experience in applying these newer models in practice. Leadership theories continue to be based on the assumption that leaders possess or have access to all the relevant knowledge and capabilities to decide future directions without external advice. In many companies, however, the workforce consists of skilled professionals whose work and related interfaces are so challenging that the leaders cannot grasp all the linked viewpoints and cross-impacts alone. One of the main objectives of this study is to understand how to support participants in organisations and their stakeholders to, through practice-based innovation processes, confront various environments. Another aim is to find effective ways of recognising and reacting to diverse contexts, so companies and other stakeholders are better able to link to knowledge flows and shared value creation processes in advancing joint value to their customers. The main research question of this dissertation is, then, to seek understanding of how to enhance leadership in complex environments. The dissertation can, on the whole, be characterised as a qualitative multiple-case study. The research questions and objectives were investigated through six studies published in international scientific journals. The main methods applied were interviews, action research and a survey. The empirical focus was on Finnish companies, and the research questions were examined in various organisations at the top levels (leaders and managers) and bottom levels (employees) in the context of collaboration between organisations and cooperation between case companies and their client organisations. However, the emphasis of the analysis is the internal and external aspects of organisations, which are conducted in practice-based innovation processes. The results of this study suggest that the Cynefin framework, complexity leadership theory and transformational leadership represent theoretical models applicable to developing leadership through practice-based innovation. In and of themselves, they all support confronting contemporary challenges, but an implementable method for organisations may be constructed by assimilating them into practice-based innovation processes. Recognition of diverse environments, their various contexts and roles in the activities and collaboration of organisations and their interest groups is ever-more important to achieving better interaction in which a strategic or formal status may be bypassed. In innovation processes, it is not necessarily the leader who is in possession of the essential knowledge; thus, it is the role of leadership to offer methods and arenas where different actors may generate advances. Enabling and supporting continuous interaction and integrated knowledge flows is of crucial importance, to achieve emergence of innovations in the activities of organisations and various forms of collaboration. The main contribution of this dissertation relates to applying these new conceptual models in practice. Empirical evidence on the relevance of different leadership roles in practice-based innovation processes in Finnish companies is another valuable contribution. Finally, the dissertation sheds light on the significance of combining complexity science with leadership and innovation theories in research.

Collaborative Customer Relationship Management in Business-to-Business Firm's Strategy

The objective of this thesis is to study the presence of collaborative customer relationship management in a firm’s strategy. In addition the thesis explains specific implementations of collaborative CRM, and CRM in general, by each case company. The sample consists of five Finnish business-to-business companies through applying multiple-case study method. The data is collected through face-to-face interviews with employees knowledgeable of the case company’s CRM processes. The qualitative data is analyzed through coding and shows that two out of five case companies have adopted and are using collaborative CRM in their strategy and operations. These case companies see collaborative CRM as an important driver for the company, through customer focus and market orientation. The rest of the case companies are either in the process of moving towards collaborative CRM or have given little consideration to it. The results show that collaborative CRM is in use, and that each company modifies it to meet their exact aspirations. The major challenge in the process is to fully grasp the importance of a shared vision that can translate into collaborative efforts in CRM and business strategy.

Becoming Locals in a Borderland of Exiles. Sense of Place in the Stories of Lithuania Minor Dwellers

This thesis deals with sense of place, the relation that we construct with our dwelling and the surrounding environment. The topic belongs to the field of human geography. Sense of place is deeply intertwined with the ideas of feeling at home and having a place where to return. I argue that narratives of life experience help us relate to the places we inhabit, go through, leave. My analysis concerns Lithuania Minor, the Lithuanian region lying by the border with Kaliningrad, and focuses in particular on Vilkyškiai, a village in the municipality of Pagėgiai. Most of the area’s original population disappeared in the war. After 1945, people from all over the country and the USSR settled here. This raised the prickly question of who belongs to the borderland. Refugees, migrants and settlers allow us to observe closely the development of sense of place and its main constituents. Through this analysis, I challenge the idea of people’s natural rights to places and shows how time, engagement in local-based cultural activities and recollection help foreigners become locals. To grasp the locals’ sense of place, I collected open, light-structured interviews and applied some elements of semantic analysis to interpret the materials. From my research, it emerges that the cultivation of the region’s cultural heritage and the practice of storytelling were crucial in making the respondents feel at home. Leaving aside all legalistic claims concerning the issue, I suggest that people belong to the land they dwell. I believe that their sense of place deserves consideration from the State and the other actors seeing them as migrants.

Contemporary marketing in the high-tech industry: Perceptions of Finnish IT marketing professionals

Over the last 30 years, new technologies and globalization have radically changed the way in which marketing is conducted. However, whereas their effects on business in general have been widely discussed, the focus of the effects on marketing remains without clear recognition. Global research has been made to shed light onto the issue, but it has widely concentrated on the views of executives as well as the consumer markets. In addition, a research gap is existent in applying the concept of marketing change in a specific business-to-business (B2B) industry. Therefore, the main research question this study seeks to answer is: “How is contemporary marketing conducted in the high-technology industry?” In this research, the researcher considers the specific industry of high-technology. However, as the industry is comprised of differing markets, the focus will be given to one of the industry’s prime sectors – the information technology (IT) markets, where companies offer other firms products or services manufactured with advanced technology. The growing IT-market is considered of critical importance in the economies of technologically ready countries such as Finland, where this research is also conducted. Through multiple case studies the researcher aims to describe how the changes in technology, customer engagement and future trends have shaped the way in which successful high-tech marketing is conducted in today’s marketplace. Then, results derived from the empirical research are presented to the reader with links to existing literature. As a conclusion, a generalized framework is constructed to depict and ideal marketer-customer relationship, with emphasis on dynamic, two-way communication and its supporting elements of customer analytics, change adaptation, strategic customer communication and organizational support. From a managerial point of view, the research may provide beneficial information as contemporary marketing can yield profitable outcomes if managed correctly. As a new way to grasp competitive advantage, strategic marketing is much more data-driven and customer-focused than ever before. The study can also prove to be relevant for the academic communities, while its results may act as inspiring for new focus on the education trends of future marketers. This study was limited to the internal activities done at the high-tech industry, leaving out the considerations for co-marketing, marketing via business partners or marketing at other B2B-industries.

Show me your brain! Stories of interdisciplinary knowledge creation in practice. Experiences and observations from Aalto Design Factory, Finland.

This dissertation centres on the themes of knowledge creation, interdisciplinarity and knowledge work. My research approaches interdisciplinary knowledge creation (IKC) as practical situated activity. I argue that by approaching IKC from the practice-based perspective makes it possible to “deconstruct” how knowledge creation actually happens, and demystify its strong intellectual, mentalistic and expertise-based connotations. I have rendered the work of the observed knowledge workers into something ordinary, accessible and routinized. Consequently this has made it possible to grasp the pragmatic challenges as well the concrete drivers of such activity. Thus the effective way of organizing such activities becomes a question of organizing and leading effective everyday practices. To achieve that end, I have conducted ethnographic research of one explicitly interdisciplinary space within higher education, Aalto Design Factory in Helsinki, Finland, where I observed how students from different disciplines collaborated in new product development projects. I argue that IKC is a multi-dimensional construct that intertwines a particular way of doing; a way of experiencing; a way of embodied being; and a way of reflecting on the very doing itself. This places emphasis not only the practices themselves, but also on the way the individual experiences the practices, as this directly affects how the individual practices. My findings suggest that in order to effectively organize and execute knowledge creation activities organizations need to better accept and manage the emergent diversity and complexity inherent in such activities. In order to accomplish this, I highlight the importance of understanding and using a variety of (material) objects, the centrality of mundane everyday practices, the acceptance of contradictions and negotiations well as the role of management that is involved and engaged. To succeed in interdisciplinary knowledge creation is to lead not only by example, but also by being very much present in the very everyday practices that make it happen.