RESUMEN
Artificial Intelligence (AI) and automation are fostering more sustainable and effective solutions for a wide spectrum of agricultural problems. Pest management is a major challenge for crop production that can benefit from machine learning techniques to detect and monitor specific pests and diseases. Traditional monitoring is labor intensive, time demanding, and expensive, while machine learning paradigms may support cost-effective crop protection decisions. However, previous studies mainly relied on morphological images of stationary or immobilized animals. Other features related to living animals behaving in the environment (e.g., walking trajectories, different postures, etc.) have been overlooked so far. In this study, we developed a detection method based on convolutional neural network (CNN) that can accurately classify in real-time two tephritid species (Ceratitis capitata and Bactrocera oleae) free to move and change their posture. Results showed a successful automatic detection (i.e., precision rate about 93%) in real-time of C. capitata and B. oleae adults using a camera sensor at a fixed height. In addition, the similar shape and movement patterns of the two insects did not interfere with the network precision. The proposed method can be extended to other pest species, needing minimal data pre-processing and similar architecture.
RESUMEN
Torque and force signals data were acquired from a load-cell sensor during a robotic welding process, in presence of collisions between the tool and the workpiece edges outlined in part in "Haptic-based touch detection for collaborative robots in welding applications" [1]. The dataset is composed from 15 tests captured during a tele-operated welding robot performing a 1G ASME/AWS (i.e., PA ISO) welding process. The raw data files have been provided. These data can be used to correlate torque signal features with collision events, to improve algorithms of collision detection/avoidance and to develop reliable real-time haptic feedback to the welder. This dataset can also be used to study the torque signal variation in different welding positions (e.g., 2G, 3G, 2F, etc.). Dataset is provided as raw data and in MATLAB files.