Driving Innovation in Robotics and Manufacturing

To address the challenge of off-road vehicle traversability through dense vegetated environments such as orchards, vineyards, and forests, we explore the potential of a multispectral camera. The data provided in the near-infrared wavelengths open the door to new scientific approaches based on the spectral emissions of vegetation. The initial results of our work are described in this article.

This article presents a new hybrid approach (H-CCPP) for optimizing coverage path planning for agricultural robots. Unlike previous methods, H-CCPP improves processing speed, explores diverse driving directions, and integrates row-skip patterns for both simple and complex fields. It automatically determines entry and exit points and was rigorously evaluated on a dataset of 30 French fields, showing superior performance in minimizing slope costs while maintaining efficiency in other key metrics. Future research will focus on improving headland coverage, integrating real-world experiments, handling obstacles, and optimizing multirobot coordination.

The article explores methods to improve predictive maintenance by enhancing data preparation for Remaining Useful Life (RUL) predictions. The study compares the traditional "capping" approach, which limits RUL values, with a new "filtering" method that focuses exclusively on data from the degradation phase, excluding normal operation data. While capping reduces errors in the normal operation phase, it distorts predictions during the degradation phase. In contrast, the filtering approach improves accuracy by training the model solely on degradation data, resulting in more precise RUL estimates. The findings highlight the importance of selecting relevant data to improve the performance and reliability of predictive maintenance models.