Human–robot collaboration has gained attention in the field of manufacturing and assembly tasks, necessitating the development of adaptable and user-friendly forms of interaction. To address this demand, collaborative robots (cobots) have emerged as a viable solution. Deep Learning has played a pivotal role in enhancing robot capabilities and facilitating their perception and understanding of the environment. This study proposes the integration of cobots and Deep Learning to assist users in assembly tasks such as part handover and storage. The proposed system includes an object classification system to categorize and store assembly elements, a voice recognition system to classify user commands, and a hand-tracking system for close interaction. Tests were conducted for each isolated system and for the complete application as used by different individuals, yielding an average accuracy of 91.25%. The integration of Deep Learning into cobot applications has significant potential for transforming industries, including manufacturing, healthcare, and assistive technologies. This work serves as a proof of concept for the use of several neural networks and a cobot in a collaborative task, demonstrating communication between the systems and proposing an evaluation approach for individual and integrated systems.

In order to improve agriculture productivity, autonomous navigation algorithms are being developed so that robots can navigate along agricultural environments to automatize tasks that are currently performed by hand. This work uses machine vision techniques such as the Otsu’s method, blob detection, and pixel counting to detect the center of the row. Additionally, a commutable control is implemented to autonomously navigate a vineyard. Experimental trials were conducted in an actual vineyard to validate the algorithm. In these trials show that the algorithm can successfully guide the robot through the row without any collisions. This algorithm offers a computationally efficient solution for vineyard row navigation, employing a 2D camera and the Otsu’s thresholding technique to ensure collision-free operation.

Fruit detection and counting is a key component of data-driven resource management and yield estimation in greenhouses. This work presents a novel infrared-based approach to capsicum counting in greenhouses that takes advantage of the light penetration of infrared (IR) imaging to enhance detection under challenging lighting conditions. The proposed capsicum counting pipeline integrates the YOLO11 detection model for capsicum identification and the BoT-SORT multi-object tracker to track detections across a video stream, enabling accurate fruit counting. The detector model is trained on a dataset of 1000 images, with 11,916 labeled capsicums, captured with an OAK-D pro camera mounted on a mobile robot inside a capsicum greenhouse. On the IR test set, the YOLO11m model achieved an F1-score of 0.82, while the tracker obtained a multiple object tracking accuracy (MOTA) of 0.85, correctly counting 67 of 70 capsicums in a representative greenhouse row. The results demonstrate the effectiveness of this IR-based approach in automating fruit counting in greenhouse environments, offering potential applications in yield estimation.

The rising demand for adaptable and user-friendly forms of interaction in the field of manufacturing and assembly tasks has led to increased attention on human-robot collaboration. Collaborative robots (cobots) have emerged as a promising solution to address this demand. In this study, we propose the integration and application of cobots along with a pre-trained deep learning model to assist users in assembly activities, specifically part handover and storage. The human-robot interaction is facilitated through a hand tracking system that enables a close approach to the user's hand. Testing on the system yielded 99% accuracy. The incorporation of deep learning models in cobot applications holds substantial potential for industry transformation, with implications spanning manufacturing, healthcare, and assistive technologies. This research serves as a compelling proof of concept, showcasing the effective implementation of deep learning models to facilitate close human-robot interactions.

A pendulum with two segments can be used to study the behavior of a human-like system which considers motion at the ankles and hips. Stability of such a system can be achieved by means of joints’ torques provided by the muscles, but this approach may be energetically taxing. Other methods have been suggested to act concurrently and take advantage of the passive dynamics of the system. One such approach is described as the Kapitza’s pendulum where upright stabilization of a pendulum may be achieved by the application of a vertical periodical oscillation at its base. This work studies the effect of the Kapitza’s oscillation on a two-segment inverted pendulum with anthropomorphic characteristics. It shows that the Kapitza’s effect is sufficient to stabilize the system in an upright posture. The system was analyzed numerically by solving its Dynamic Model under different conditions. While the results presented mirror those previously reported, this work finds a larger region of stability when compared to the available literature. This is likely due to the effect of the top heavy-pendulum and its inertial properties. Additionally, under this study the effect of the joint visco-elastic parameters is made evident: while they generally tend to help stabilize the system, they sometimes hinder stability, specifically under low frequency - high amplitude oscillations. Future studies should include a more accurate model of the time-varying characteristics of the joints’ visco-elastic parameters and human range of motion.