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.

Indium oxide octahedral nanopowders were obtained from an ionic precursor compound after an oxidation process conducted under a low-oxygen atmosphere. This method was found to produce contamination-free indium oxide nanomaterial with very similar morphological and crystalline properties to the one produced by vapor-phase transport, but at significantly lower temperatures and higher yield. The as-synthesized indium oxide was mixed to an organic vehicle and microdrop deposited to form a film bridging the interdigitated silver electrodes patterned on top of a flexible, polyimide (Kapton^®), substrate. The gas sensing properties of the flexible chemoresistors towards ammonia vapors, hydrogen, and nitrogen dioxide were investigated. It was found that these sensors were remarkably sensitive to nitrogen dioxide at a low operating temperature of 150 °C. These results are consistent with the performance of vapor-phase transport synthesized indium oxide octahedra sensors on rigid, ceramic substrates. Therefore, the results presented here pave the way for the mass production of inexpensive gas sensors onto flexible substrates via additive manufacturing.

Many sensors are developed over flexible substrates to be used as wearables, which does not guarantee that they will actually withstand being bent. This work evaluates the gas sensing performance of metal oxide devices of three different types, before and after having undergone automated, repetitive bending tests. These tests were aimed at demonstrating that the fabricated sensors were actually flexible, which cannot be taken for granted beforehand. The active layer in these sensors consisted of WO₃ nanowires (NWs) grown directly over a Kapton foil by means of the aerosol-assisted chemical vapor deposition. Their response to different H₂ concentrations was measured at first. Then, they were cyclically bent, and finally, their response to H₂ was measured again. Sensors based on pristine WO₃-NWs over Ag electrodes and on Pd-decorated NWs over Au electrodes maintained their performance after having been bent. Ag electrodes covered with Pd-decorated NWs became fragile and lost their usefulness. To summarize, two different types of truly flexible metal oxide gas sensor were fabricated, whereas a third one was not flexible, despite being grown over a flexible substrate following the same method. Finally, we recommend that one standard bending test procedure should be established to clearly determine the flexibility of a sensor considering its intended application.

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.

Indium oxide was synthesized through an oxidation process starting from an ionic precursor compound. Synthesized indium oxide was used to fabricate gas sensors, under the same conditions, in two types of substrates; a rigid one, alumina substrate and a flexible, polyimide (Kapton®). Half of those gas sensors were doped with silver nanoparticles, through sputtering, and tested by immersing in a flow of NO ₂ gas.

Here we review recent results on the synthesis of single-crystalline metal oxide nanomaterials and their integration in resistive gas sensing devices. Emphasis is put on the integration of such nanomaterials in a wide spectrum of transducing platforms, ranging from standard ceramic to silicon MEMS or flexible polymeric. Some strategies for achieving higher selectivity are discussed, which are followed by a discussion on the development of advanced operation techniques for achieving more stable and faster response to gases. Finally, some aspects that remain open for research are identified.