Abstract
Accurate identification of transportation mode distribution is essential for effective urban planning. Recent advancements in machine learning have spurred research on automated Transportation Mode Detection (TMD). While existing TMD methods predominantly employ standard flat classification methods, this paper introduces HiClass4MD, a novel hierarchical approach. By leveraging the misclassification errors from standard flat classifier, HiClass4MD learns the class hierarchy for transportation modes. Although hierarchical met-rics initially indicated performance improvements when applied to real-world GPS trajectories dataset, a subsequent evaluation using conventional metrics revealed inconsistent results. While decision trees benefited marginally, other classifiers exhibited no significant gains or even degraded. This study highlights the complexity of applying hierarchical classification to TMD and underscores the need for further investigation into the factors influencing its effectiveness. © 2024 IEEE.

Abstract
Arbitrary, inconsistent, or faulty decision-making raises serious concerns, and preventing unfair models is an increasingly important challenge in Machine Learning. Data often reflect past discriminatory behavior, and models trained on such data may reflect bias on sensitive attributes, such as gender, race, or age. One approach to developing fair models is to preprocess the training data to remove the underlying biases while preserving the relevant information, for example, by correcting biased labels. While multiple label noise correction methods are available, the information about their behavior in identifying discrimination is very limited. In this work, we develop an empirical methodology to systematically evaluate the effectiveness of label noise correction techniques in ensuring the fairness of models trained on biased datasets. Our methodology involves manipulating the amount of label noise and can be used with fairness benchmarks but also with standard ML datasets. We apply the methodology to analyze six label noise correction methods according to several fairness metrics on standard OpenML datasets. Our results suggest that the Hybrid Label Noise Correction [20] method achieves the best trade-off between predictive performance and fairness. Clustering-Based Correction [14] can reduce discrimination the most, however, at the cost of lower predictive performance.

Abstract
Forest fires are becoming increasingly common, and they are devastating, fueled by the effects of global warming, such as a dryer climate, dryer vegetation, and higher temperatures. Vegetation management through selective removal is a preventive measure which creates discontinuities that will facilitate fire containment and reduce its intensity and rate of spread. However, such a method requires vast amounts of biomass fuels to be removed, over large areas, which can only be achieved through mechanized means, such as through using forestry mulching machines. This dangerous job is also highly dependent on skilled workers, making it an ideal case for novel autonomous robotic systems. This article presents the development of a universal perception, control, and navigation system for forestry machines. The selection of hardware (sensors and controllers) and data-integration and -navigation algorithms are central components of this integrated system development. Sensor fusion methods, operating using ROS, allow the distributed interconnection of all sensors and actuators. The results highlight the system's robustness when applied to the mulching machine, ensuring navigational and operational accuracy in forestry operations. This novel technological solution enhances the efficiency of forest maintenance while reducing the risk exposure to forestry workers.

Abstract
Energy Communities (ECS) and Self- consumption structures are receiving significant attention in Europe due to their potential contribution to a sustainable energy transition and the decarbonization process of the energy system. They are considered a powerful instrument to involve end-consumers in active participation in the energy system by becoming self-producers of renewable electricity and increasing their awareness of their potential contribution by adapting their energy behavior to the global or local power system needs. An EC can also contribute to alleviating energy poverty, which occurs when low incomes and poorly efficient buildings and appliances place a high proportion of energy costs on households. The main driver would be the reduction in energy costs obtained if some members agree to share their surplus electricity at a lower price with vulnerable members. Similarly, a renewable EC (REC) can facilitate access to energy assets by sharing the investments among the community members and exploiting existing complementarities. For example, vulnerable members could share their roofs with others to install solar panels in exchange for low-cost electricity. RECs can also help vulnerable members by reducing the barriers to accessing subsidies for building efficiency investments thanks to collective community initiatives, easing information dissemination and helping with bureaucratic processes.

Abstract
In the present paper, we propose a control approach to perform docking of an autonomous surface vehicle (ASV) while avoiding surrounding obstacles. This control architecture is composed of two sequential controllers. The first outputs a feasible trajectory between the vessel's initial and target state while avoiding obstacles. This trajectory also minimizes the vehicle velocity while performing the maneuvers to increase the safety of onboard passengers. The second controller performs trajectory tracking while accounting for the actuator's physical limits (extreme actuation values and the rate of change). The method's performance is tested on simulation, as it enables a reliable ground truth method to validate the control architecture proposed.

Abstract
In the field of intelligent autonomous robots, integrating optimization techniques with classical control theory methods for mobile robot control is an increasingly prominent area of research. The combination enhances robots' ability to perform their tasks more efficiently, reliably, and safely. This paper addresses the development of a path and motion planning framework for omnidirectional robots, leveraging B-Splines and Trajectory Tracking with Model Predictive Control. The proposed framework is evaluated through software-in-the-loop tests using two distinct dynamical models and sets of hyperparameters. Final validation is conducted by implementing the framework within a ROS environment and performing field tests on a robotic platform. The results demonstrate that the robot can reliably track trajectories at its actuation limits, and the proposed framework enables the robot to increase its velocity up to 50% when compared to a PID path-following controller.