Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.
Accurate localization in autonomous robots enables effective decision-making within their operating environment. Various methods have been developed to address this challenge, encompassing traditional techniques, fiducial marker utilization, and machine learning approaches. This work proposes a deep-learning solution employing Convolutional Neural Networks (CNN) to tackle the localization problem, specifically in the context of the RobotAtFactory 4.0 competition. The proposed approach leverages transfer learning from the pre-trained VGG16 model to capitalize on its existing knowledge. To validate the effectiveness of the approach, a simulated scenario was employed. The experimental results demonstrated an error within the millimeter scale and rapid response times in milliseconds. Notably, the presented approach offers several advantages, including a consistent model size regardless of the number of training images utilized and the elimination of the need to know the absolute positions of the fiducial markers.
Worldwide, coral reefs are rapidly declining due to increased sea water temperatures and other environmental stresses (Figure 1). To counter the extinction of major coral reef building species on the island of Bonaire, the non-profit organization Reef Renewal Foundation Bonaire is restoring degraded reef sites using corals that are grown in local nurseries. In these nurseries, corals are propagated on artificial trees using fragmentation. After 6-8 months of growth in the nursery, the corals are transplanted to degraded reef sites around the island. Over the years more than 21.000 corals have been outplanted to reef restoration sites in this way. These corals show high survivorship under natural reef conditions but remain under threat by environmental disturbances, such as increased water temperatures, diseases, and competition with macroalgae. A promising intervention to increase reef persistence and resilience is to manipulate the coral-associated microbiome. At present, the composition of the microbiome in nursery-reared and outplanted corals on Bonaire is unknown. The aim of the current project is to identify and isolate naturally occurring beneficial bacteria that may stimulate the resilience of these corals. Our key objectives are: 1) to assess the presence of functionally beneficial bacteria in corals in nursery and restoration sites on Bonaire using metagenomic screening. 2) to design culture strategies to isolate these functionally beneficial bacteria. In the future, a selection of these beneficial bacteria can be applied to the corals to increase their resilience against environmental disturbances.
Digital innovations in the field of immersive Augmented Reality (AR) can be a solution to offer adults who are mentally, physically or financially unable to attend sporting events such as premier league football a stadium and match experience. This allows them to continue to connect with their social networks. In the intended project, AR content will be further developed with the aim of evoking the stadium experience of home matches as much as possible. The extent to which AR enriches the experience is then tested in an experiment, in which the experience of a football match with and without AR enrichment is measured in a stadium setting and in a home setting. The experience is measured with physiological signals. In addition, a subjective experience measure is also being developed and benchmarked (the experience impact score). Societal issueInclusion and health: The joint experience of (top) sports competitions forms a platform for vulnerable adults, with a limited social capital, to build up and maintain the social networks that are so necessary for them. AR to fight against social isolation and loneliness.
The growing demand for both retrofitting and refitting, driven by an aging global fleet and decarbonization efforts, including the need to accommodate alternative fuels such as LNG, methanol, and ammonia, offers opportunities for sustainability. However, they also pose challenges, such as emissions generated during these processes and the environmental impacts associated with the disposal of old components. The region Rotterdam and Drechtsteden form a unique Dutch maritime ecosystem of port logistics, shipbuilding, offshore operations, and innovation facilities, supported by Europe’s largest port and world-class infrastructure connecting global trade routes. The Netherlands’ maritime sector, including the sector concentrated in Zuid-Holland, is facing competition from subsidized Asian companies, leading to a steep decline in Europe’s shipbuilding market share from 45% in the 1980s to just 4% in 2023. Nonetheless, the shift toward climate-neutral ships presents economic opportunities for Dutch maritime companies. Thus, developing CE approaches to refitting is essential for promoting sustainability and addressing the pressing environmental and competitive challenges facing the sector and has led companies in the sector to establish the Open Joint Industry Project (OJIP) called Circolab of which this PD forms the core.
