NR5G-SAM: A SLAM Framework for Field Robot Applications Based on 5G New Radio.

Robot localization is a crucial task in robotic systems and is a pre-requisite for navigation. In outdoor environments, Global Navigation Satellite Systems (GNSS) have aided towards this direction, alongside laser and visual sensing. Despite their application in the field, GNSS suffers from limited availability in dense urban and rural environments. Light Detection and Ranging (LiDAR), inertial and visual methods are also prone to drift and can be susceptible to outliers due to environmental changes and illumination conditions. In this work, we propose a cellular Simultaneous Localization and Mapping (SLAM) framework based on 5G New Radio (NR) signals and inertial measurements for mobile robot localization with several gNodeB stations. The method outputs the pose of the robot along with a radio signal map based on the Received Signal Strength Indicator (RSSI) measurements for correction purposes. We then perform benchmarking against LiDAR-Inertial Odometry Smoothing and Mapping (LIO-SAM), a state-of-the-art LiDAR SLAM method, comparing performance via a simulator ground truth reference. Two experimental setups are presented and discussed using the sub-6 GHz and mmWave frequency bands for communication, while the transmission is based on down-link (DL) signals. Our results show that 5G positioning can be utilized for radio SLAM, providing increased robustness in outdoor environments and demonstrating its potential to assist in robot localization, as an additional absolute source of information when LiDAR methods fail and GNSS data is unreliable.

Human-Aware Collaborative Robots in the Wild: Coping with Uncertainty in Activity Recognition.

This study presents a novel approach to cope with the human behaviour uncertainty during Human-Robot Collaboration (HRC) in dynamic and unstructured environments, such as agriculture, forestry, and construction. These challenging tasks, which often require excessive time, labour and are hazardous for humans, provide ample room for improvement through collaboration with robots. However, the integration of humans in-the-loop raises open challenges due to the uncertainty that comes with the ambiguous nature of human behaviour. Such uncertainty makes it difficult to represent high-level human behaviour based on low-level sensory input data. The proposed Fuzzy State-Long Short-Term Memory (FS-LSTM) approach addresses this challenge by fuzzifying ambiguous sensory data and developing a combined activity recognition and sequence modelling system using state machines and the LSTM deep learning method. The evaluation process compares the traditional LSTM approach with raw sensory data inputs, a Fuzzy-LSTM approach with fuzzified inputs, and the proposed FS-LSTM approach. The results show that the use of fuzzified inputs significantly improves accuracy compared to traditional LSTM, and, while the fuzzy state machine approach provides similar results than the fuzzy one, it offers the added benefits of ensuring feasible transitions between activities with improved computational efficiency.

The variability of the serve toss in tennis under the influence of artificial crosswind.

This study was made to analyze the variability and stability of the serve toss in tennis, on the x (side-to-side), y (back-to-front) and z (vertical) axes, with 12 experienced players under the influence of crosswind (induced aerodynamic flow) produced by an industrial ventilator. The players were analyzed individually after serving at maximum speed and accuracy to the intersection point of the centre line and service line ("T "point). The results allow us to conclude that the experienced players tend to stabilize the vertical dimension of the service (z axis). Additionally, this study confirms the invariability of the player height ratio: height of impact (1:1.5) in experienced players even when constrained by the "artificial crosswind. "Given the above, the vertical dimension of the tennis serve is assumed as a constant feature, which is guaranteed in the remaining varying dimensions (y and x axes) of the ball toss. Thus, the variability should be seen as part of the solution and not as something to be avoided by players and coaches. Key PointsAnalysis of the tennis serve variability under the effect of artificial crosswindTwelve experienced tennis players performed a set of 20 free serves (without wind constraints), and four other sets of 20 serves under different practice conditions (with different crosswind intensities)The players tend to stabilize in the z axis and vary in the y- (back-to-front) and x-axes (side-to-side) during the ball toss tennis serve in all the practice conditions (with and without crosswind)THE MAINTENANCE OF A PLAYER HEIGHT RATIO: impact height of approximately 1:1.5 in experienced players, even when constrained by "artificial crosswind".

Benchmarking for Strain Evaluation in CFRP Laminates Using Computer Vision: Machine Learning versus Deep Learning.

The strengthening of concrete structures with laminates of Carbon-Fiber-Reinforced Polymers (CFRP) is a widely adopted technique. retained The application is more effective if pre-stressed CFRP laminates are adopted. The measurement of the strain level during the pre-stress application usually involves laborious and time-consuming applications of instrumentation. Thus, the development of expedited approaches to accurately measure the pre-stressed application in the laminates represents an important contribution to the field. This paper proposes and benchmarks contact-free architecture for measuring the strain level of CFRP laminate based on computer vision. The main objective is to provide a solution that might be economically feasible, automated, easy to use, and accurate. The architecture is fed by digitally deformed synthetic images, generated based on a low-resolution camera. The adopted methods range from traditional machine learning to deep learning. Furthermore, dropout and cross-validation methods for quantifying traditional machine learning algorithms and neural networks are used to efficiently provide uncertainty estimates. ResNet34 deep learning architecture provided the most accurate results, reaching a root mean square error (RMSE) of 0.057‱ for strain prediction. Finally, it is important to highlight that the architecture presented is contact-free, automatic, cost-effective, and measures directly on the laminate surfaces, which allows them to be widely used in the application of pre-stressed laminates.

The ARCANE Project: How an Ecological Dynamics Framework Can Enhance Performance Assessment and Prediction in Football.

This paper discusses how an ecological dynamics framework can be implemented to interpret data, design practice tasks and interpret athletic performance in collective sports, exemplified here by research ideas within the Augmented peRCeption ANalysis framEwork for Football (ARCANE) project promoting an augmented perception of football teams for scientists and practitioners. An ecological dynamics rationale can provide an interpretation of athletes' positional and physiological data during performance, using new methods to assess athletes' behaviours in real-time and, to some extent, predict health and performance outcomes. The proposed approach signals practical applications for coaches, sports analysts, exercise physiologists and practitioners through merging a large volume of data into a smaller set of variables, resulting in a deeper analysis than typical measures of performance outcomes of competitive games.

Distance and slope constraints: adaptation and variability in golf putting.

The main objective of this study is to understand the adaptation to external constraints and the effects of variability in a golf putting task. We describe the adaptation of relevant variables of golf putting to the distance to the hole and to the addition of a slope. The sample consisted of 10 adult male (33.80 ± 11.89 years), volunteers, right handed and highly skilled golfers with an average handicap of 10.82. Each player performed 30 putts at distances of 2, 3 and 4 meters (90 trials in Condition 1). The participants also performed 90 trials, at the same distances, with a constraint imposed by a slope (Condition 2). The results indicate that the players change some parameters to adjust to the task constraints, namely the duration of the backswing phase, the speed of the club head and the acceleration at the moment of impact with the ball. The effects of different golf putting distances in the no-slope condition on different kinematic variables suggest a linear adjustment to distance variation that was not observed when in the slope condition.

Accuracy of pattern detection methods in the performance of golf putting.

The authors present a comparison of the classification accuracy of 5 pattern detection methods in the performance of golf putting. The detection of the position of the golf club was performed using a computer vision technique followed by the estimation algorithm Darwinian particle swarm optimization to obtain a kinematical model of each trial. The estimated parameters of the models were subsequently used as sample of five classification algorithms: (a) linear discriminant analysis, (b) quadratic discriminant analysis, (c) naive Bayes with normal distribution, (d) naive Bayes with kernel smoothing density estimate, and (e) least squares support vector machines. Beyond testing the performance of each classification method, it was also possible to identify a putting signature that characterized each golf player. It may be concluded that these methods can be applied to the study of coordination and motor control on the putting performance, allowing for the analysis of the intra- and interpersonal variability of motor behavior in performance contexts.