Abstract

Abstract
Nowadays, the robotic welding joint estimation, or weld seam tracking, has improved according to the new developments on computer vision technologies. Typically, the advances are focused on solving inaccurate procedures that advent from the manual positioning of the metal parts in welding workstations, especially in SMEs. Robotic arms, endowed with the appropriate perception capabilities, are a viable solution in this context, aiming for enhancing the production system agility whilst not increasing the production set-up time and costs. In this regard, this paper proposes a local perception pipeline to estimate joint welding points using small-sized/low-cost 3D cameras, following an eyes-on-hand approach. A metrological 3D camera comparison between Intel Realsene D435, D415, and ZED Mini is also discussed, proving that the proposed pipeline associated with standard commercial 3D cameras is viable for welding operations in an industrial environment.

Abstract
There are currently several techniques for automatic calibration of inertial sensors. This paper describes a subset of these algorithms that could be used in a manipulator and should allow for its prompt use. A robotic manipulator specifically developed for the study of over-sensored systems is used to realistically test the performance of the implemented methods. The results of these methods show that the accelerometers and the gyroscopes were properly calibrated. However, the magnetometers suffer from variable interferences and therefore could not be calibrated.

Abstract
The recent Covid-19 pandemic and the fact that wearing masks in public is now mandatory in several countries, created challenges in the use of face recognition systems (FRS). In this work, we address the challenge of masked face recognition (MFR) and focus on evaluating the verification performance in FRS when verifying masked vs unmasked faces compared to verifying only unmasked faces. We propose a methodology that combines the traditional triplet loss and the mean squared error (MSE) intending to improve the robustness of an MFR system in the masked-unmasked comparison mode. The results obtained by our proposed method show improvements in a detailed step-wise ablation study. The conducted study showed significant performance gains induced by our proposed training paradigm and modified triplet loss on two evaluation databases.

Abstract
By using Dynamic Binary Translation, instruction traces from pre-compiled applications can be offloaded, at runtime, to FPGA-based accelerators, such as Coarse-Grained Loop Accelerators, in a transparent way. However, scheduling onto coarse-grain accelerators is challenging, with two of current known issues being the density of computations that can be mapped, and the effects of memory accesses on performance. Using an in-house framework for analysis of instruction traces, we explore the effect of different window sizes when applying list scheduling, to map the window operations to a coarse-grain loop accelerator model that has been previously experimentally validated. For all window sizes, we vary the number of ALUs and memory ports available in the model, and comment how these parameters affect the resulting latency. For a set of benchmarks taken from the PolyBench suite, compiled for the 32-bit MicroBlaze softcore, we have achieved an average iteration speedup of 5.10x for a basic block repeated 5 times and scheduled with 8 ALUs and memory ports, and an average speedup of 5.46x when not considering resource constraints. We also identify which benchmarks contribute to the difference between these two speedups, and breakdown their limiting factors. Finally, we reflect on the impact memory dependencies have on scheduling.

Abstract
Reinforcement Learning is at the core of a recent revolution in Artificial Intelligence. Simultaneously, we are witnessing the emergence of a new field: Quantum Machine Learning. In the context of these two major developments, this work addresses the interplay between Quantum Computing and Reinforcement Learning. Learning by interaction is possible in the quantum setting using the concept of oraculization of environments. The paper extends previous oracular instances to address more general stochastic environments. In this setting, we developed a novel quantum algorithm for near-optimal decision-making based on the Reinforcement Learning paradigm known as Sparse Sampling. The proposed algorithm exhibits a quadratic speedup compared to its classical counterpart. To the best of the authors' knowledge, this is the first quantum planning algorithm exhibiting a time complexity independent of the number of states of the environment, which makes it suitable for large state space environments, where planning is otherwise intractable.