Søk i SINTEF

Fractured reservoir simulation plays a crucial role in understanding various subsurface geo-energy recovery and storage processes, including shale gas/oil extraction, enhanced geothermal systems, and CO₂ sequestration in basaltic rocks. However, such simulations often entail significant...

This study aims to provide recommendations for addressing the gaps in the existing regulatory and legal frameworks, including the international and national regulations, rules, and standards for developing Maritime Autonomous Surface Ships (MASSs) for the Short Sea Shipping (SSS). The methodological...

Background The centrality of human resources in the provision of healthcare suggests that Human Resource (HR) management and the use of Human Resource analytics – use of digital data to better understand, assess, plan and organize the workforce - can play an important role in this. However, data...

We investigate the active manipulation of objects using model-free and long-horizon DRL (Deep Reinforcement Learning) to achieve target shapes. Our proposed approach uses visual observations consisting of segmented images, to mitigate the sim-to-real gap. We address a long-horizon manipulation task...

Fish behaviour affects the performance of selection devices in fishing gears. Traditionally, fish behaviour in relation to selection devices is assessed by direct observation. However, this approach has limitations, and the observations are not explicitly incorporated in the selectivity models...

Bycatch of threatened flatfish species is a major concern in mixed-species bottom-set gillnet fisheries in the Yellow Sea, China. Therefore, we tested floated gillnets against standard bottom-set gillnets to reduce bycatch by exploiting difference in species-specific fish behavior. Our results...

The fusion of low-cost RGB and depth cameras has improved Visual Odometry’s performance significantly especially when encountering feature sparsity and rotational dynamics. However, established Red, Green, Blue, and Depth (RGB-D) methods still lose tracking or accumulate large drift when confronted...

We present a novel vision-based, 6-DoF grasping framework based on Deep Reinforcement Learning (DRL) that is capable of directly synthesizing continuous 6-DoF actions in cartesian space. Our proposed approach uses visual observations from an eye-in-hand RGB-D camera, and we mitigate the sim-to-real...

The ongoing legislative push to mitigate the environmental impact of strong greenhouse gases creates a need for liquid-filled High Voltage (HV) and Extra High Voltage (EHV) terminations. The exceptionally long expected lifetime of many such components requires that on-line condition monitoring is...