From the article: "To extend the lifetime of products, an agent is connected to the product. This agent has several roles. It depends on the phase of the lifecycle what these roles will be. One of the roles in the usage or recycling phase is to negotiate for buying spare parts in case a part of the product is broken. The same agent can also decide to offer spare parts to other agents to reuse working parts of a broken product. To accomplish this idea, a marketplace for agents has to be set up, where the auctions can take place. To support this concept, blockchain technology has been used. Blockchains are a new type of technology, known from bitcoins, but there are other cases where blockchains can be used. Blockchain is known for its decentralisation, transparency and for making trustful transactions. In this paper the working of different types of blockchains will be briefly explained and determined if they can be useful for online auctions by agents. A prototype of the marketplace using blockchains has been built."
LINK
Dit proefschrift heeft als onderwerp de toepassing van agenttechnologie in productie en productondersteuning. Onder een agent verstaan we in deze context een autonoom opererende software entiteit die gemaakt is om een zeker doel te realiseren en daartoe met de omgeving comuniceert en zelfstandig acties kan uitvoeren. In moderne productiesystemen streeft men ernaar om de tijd van ontwerp tot productie zo kort mogelijk te houden en de productie af te stemmen op de wensen van de individuele eindgebruiker. Vooral dit laatste streven past niet in het concept van massaproductie. Een methode moet gezocht worden om kleine hoeveelheden of zelfs unieke producten tegen een lage kostprijs te fabriceren. Om dit te verwezenlijken zijn voor dit onderzoek speciale goedkope productieplatforms ontwikkeld. Deze hercongureerbare productiemachines noemen we equiplets. Een verzameling van deze equiplets in een gridopstelling geplaatst en gekoppeld met een snelle netwerkverbinding is in staat om een aantal verschillende producten tegelijk te produceren. Dit noemen we exibele parallelle productie. Voor de softwareinfrastructuur is agenttechnologie toegepast. Twee typen agenten spelen hierin een hoofdrol. Een productagent is verantwoordelijk voor de totstandkoming van een enkel product. De productiemachines worden voorgesteld door zogenoemde equipletagenten. De productagent weet wat er moet gebeuren voor het maken van een product terwijl de equipletagent weet hoe een of meer productiestappen moeten worden uitgevoerd. Het hier voorgesteld concept verschilt in veel opzichten van standaard massaproductie. Elk product in wording volgt zijn eigen, mogelijk unieke pad langs de equiplets, de productie wordt per product gescheduled en niet per batch en er is geen sprake van een productielijn. Dit proefschrift stelt de softwarearchitectuur voor en beschrijft oplossingen voor de routeplanning waarbij het aantal wisselingen tussen equiplets geminimaliseerd is, een scheduling die gebaseerd is op schedulingschema's zoals toegepast in real-time operating systems en een op autonome voertuigen gebaseerd transportsysteem. Bij al deze oplossingen speelt de productagent een belangrijke rol. (uit de samenvatting van het proefschrift) SIKS Dissertation Series No. 2014-31 The research reported in this thesis has been carried out under the auspices of SIKS, the Dutch Research School for Information and Knowledge Systems.
Key to reinforcement learning in multi-agent systems is the ability to exploit the fact that agents only directly influence only a small subset of the other agents. Such loose couplings are often modelled using a graphical model: a coordination graph. Finding an (approximately) optimal joint action for a given coordination graph is therefore a central subroutine in cooperative multi-agent reinforcement learning (MARL). Much research in MARL focuses on how to gradually update the parameters of the coordination graph, whilst leaving the solving of the coordination graph up to a known typically exact and generic subroutine. However, exact methods { e.g., Variable Elimination { do not scale well, and generic methods do not exploit the MARL setting of gradually updating a coordination graph and recomputing the joint action to select. In this paper, we examine what happens if we use a heuristic method, i.e., local search, to select joint actions in MARL, and whether we can use outcome of this local search from a previous time-step to speed up and improve local search. We show empirically that by using local search, we can scale up to many agents and complex coordination graphs, and that by reusing joint actions from the previous time-step to initialise local search, we can both improve the quality of the joint actions found and the speed with which these joint actions are found.
LINK
-Chatbots are being used at an increasing rate, for instance, for simple Q&A conversations, flight reservations, online shopping and news aggregation. However, users expect to be served as effective and reliable as they were with human-based systems and are unforgiving once the system fails to understand them, engage them or show them human empathy. This problem is more prominent when the technology is used in domains such as health care, where empathy and the ability to give emotional support are most essential during interaction with the person. Empathy, however, is a unique human skill, and conversational agents such as chatbots cannot yet express empathy in nuanced ways to account for its complex nature and quality. This project focuses on designing emotionally supportive conversational agents within the mental health domain. We take a user-centered co-creation approach to focus on the mental health problems of sexual assault victims. This group is chosen specifically, because of the high rate of the sexual assault incidents and its lifetime destructive effects on the victim and the fact that although early intervention and treatment is necessary to prevent future mental health problems, these incidents largely go unreported due to the stigma attached to sexual assault. On the other hand, research shows that people feel more comfortable talking to chatbots about intimate topics since they feel no fear of judgment. We think an emotionally supportive and empathic chatbot specifically designed to encourage self-disclosure among sexual assault victims could help those who remain silent in fear of negative evaluation and empower them to process their experience better and take the necessary steps towards treatment early on.
Zuyd University of Applied Sciences (ZUYD) and partners will develop photoflow chemistry reaction set-ups that will be powered with light as sustainable energy source, and as such contribute to the transition of the current chemical industry to a climate neutral one. To develop these reaction set-ups, a consortium of partners from the Dutch, Belgian and German chemical and high-tech ecosystems will cover all aspects related to required hardware, e.g. transparent reactors and energy-efficient light sources, automation and multiphase reactions. The mix of partners from academia (University of Amsterdam: the Noël group), an applied research organization (TNO), Center of Expertise CHILL, ZUYD, the Brightlands Chemelot Campus and multiple companies (Beartree Automation, Chemtrix, Creaflow, Ecosynth, De Heer, Innosyn, Mettler-Toledo, Peschl Ultraviolet and Swagelok Nederland) ensures an efficient and integrated development along technology readiness levels (TRL) ranging from two/three to five/six. Together we will answer the overarching question: With which advanced reaction set-up(s) can we efficiently perform and further optimize multiphase solution-based photochemical reactions that require gas and/or solid reagents, and efficiently showcase our capabilities? The development of the advanced reaction set-ups will allow us to answer our research question: How far can we extend the applicability of photoflow transformations beyond the current commercial state-of-the-art by the use of advanced reaction set-ups? Dissemination of several demonstrator transformations using our advanced set-ups will showcase capabilities of Light-Up partners and speed up the uptake of photoflow chemistry in industry. We will develop the next generation of advanced reaction set-ups for photoflow chemistry by combining the knowledge of the chemical and high-tech sectors, and facilitating knowledge exchange between sectors, to contribute to a climate neutral industry.
Due to the exponential growth of ecommerce, the need for automated Inventory management is crucial to have, among others, up-to-date information. There have been recent developments in using drones equipped with RGB cameras for scanning and counting inventories in warehouse. Due to their unlimited reach, agility and speed, drones can speed up the inventory process and keep it actual. To benefit from this drone technology, warehouse owners and inventory service providers are actively exploring ways for maximizing the utilization of this technology through extending its capability in long-term autonomy, collaboration and operation in night and weekends. This feasibility study is aimed at investigating the possibility of developing a robust, reliable and resilient group of aerial robots with long-term autonomy as part of effectively automating warehouse inventory system to have competitive advantage in highly dynamic and competitive market. To that end, the main research question is, “Which technologies need to be further developed to enable collaborative drones with long-term autonomy to conduct warehouse inventory at night and in the weekends?” This research focusses on user requirement analysis, complete system architecting including functional decomposition, concept development, technology selection, proof-of-concept demonstrator development and compiling a follow-up projects.
