Artificial intelligence (AI) has smoothly penetrated in a number of monitoring and control applications including the agriculture. However, research efforts towards low-power sensing devices with fully-functional AI on board are still fragmented. In this work, we present an embedded system enriched with the AI ensuring the continuous analysis and in-situ prediction of the growth dynamics of plant leaves. The embedded solution is grounded on a low-power embedded sensing system with a Graphics Processing Unit (GPU) and is able to run the neural networks-based AI on board. We use a Recurrent Neural Network (RNN) called the Long-Short Term Memory network (LSTM) as a core of AI in our system. The proposed approach guarantees the system autonomous operation for 180 days using a standard Li-ion battery. We rely on the state-of-the-art mobile graphical chips for ‘smart’ analysis and control of autonomous devices. This pilot study opens up wide vista for a variety of intelligent monitoring applications, especially in the agriculture domain. Also, we share with the research community the Tomato Growth dataset.

Artificial Intelligence (AI) has been recently applied to a number of sensing scenarios for realizing the prediction, control and/or recognition tasks. However, its integration to embedded systems is still limited. We propose a low-power sensing system with the AI on board with a special focus on the application in agriculture. For this reason we designed a Convolutional Neural Network (CNN) which achieves 83% of average Intersection over Union (IoU) score on the test dataset and 97% of seeds recognition accuracy on the validation dataset. The proposed solution is able to perform the seeds recognition, and germination detection through the images processing. For training the CNN we collect a dataset of images of seed germination process at different stages. The entire system is assessed in an industrial facility. The experimental results demonstrate that the proposed system opens up wide vista for smart applications in the context of Internet of Things requiring the intelligent and autonomous operation from ’things’.

The Hogweed of Sosnowskyi (lat. Heracleum Sosnowskyi) is poisonous for humans, dangerous for farming crops, and local ecosystems. This plant is fast-growing and has already spread all over Eurasia: from Germany to the Siberian part of Russia, and its distribution expands year-by-year. In-situ detection of this harmful plant is a tremendous challenge for many countries. Meanwhile,there are no automatic systems for detection and localization of hogweed. In this work, we report on an approach for fast and accurate detection of hogweed. The approach includes the Unmanned Aerial Vehicle (UAV) with an embedded system on board running various Fully Convolutional Neural Networks (FCNN). We propose the optimal architecture of FCNN for the embedded system relying on the trade-off between the detection quality and frame rate. We propose a model that achieves ROC AUC 0.96 in the hogweed segmentation task, which can process 4K frames at 0.46 FPS on NVIDIA Jetson Nano. The developed system can recognize the hogweed on the scale of individual plants and leaves. This system opens up a wide vista for obtaining comprehensive and relevant data about the spreading of harmful plants allowing for the elimination of their expansion.

Aerial drones can be used for a number of monitoring and control applications. Most of existing drone control platforms are quite primitive in terms of body-machine interface. They are usually a variation of a hand-held remote controller or ground control station. However, in a number of line-of-sight scenarios it would be more convenient to use the human gestures and voice for the drone control. In this work, we present an approach for instantaneous control of drones based on human voice and gestures. The proposed solution includes wearable sensors and embedded artificial intelligence. We use a microphone and an Inertial Measurement Unit (IMU) for capturing the human voice and the hand movements. Primary control is implemented by a voice recognition unit based on Recurrent Neural Network (RNN) while the secondary control is implemented by the gesture recognition system based on Convolutional Neural Network (CNN). For implementing the embedded intelligence, we use a low-power embedded system with a graphical processing unit able to run pre-trained neural networks on board of the drone. As a result, the system can perform different speech and gesture recognition tasks real-time.

Aircraft perform flight in multiple regimes with different speeds, Angles of Attack (AoA), sideslip angles, and at different altitudes. Designers usually choose the airfoil having the best performance for the cruise mode only or being able to stay suboptimal for all the flight regimes. It leads to a reduction in the maximum lift-to-drag ratio for certain regimes, as well as deterioration in the overall performance. That is why the adaptive wing with its ability to stay optimal for any of the flight regimes is a promising technology which could significantly improve the performance and maneuverability of the aircraft during the flight. In this work, we assess the performance of the wing with the traditional and adaptive mechanization of the flap and slat using computer simulation followed by the experiments in the wind tunnel environment. This work also provides the design of an adaptive wing with an adaptive flap and slat. All the investigations were performed for the two-dimensional airfoil under different Reynolds numbers and AoA. This paper demonstrates that an adaptive wing improves the lift-to-drag ratio and maneuverability of the aircraft for different flight regimes. The application of the adaptive wing mechanization could improve the lift-to-drag ratio by 20%-30% for certain regimes, thereby improving the range and time of operation.

The number of real-world Internet of Things (IoT) deployments continuously and steadily increases while the capabilities of single IoT devices cannot yet be exploited for the purpose of Artificial Intelligence. Indeed, computation complexity and energy consumption are the constraining requirements for the development and implementation of truly intelligent IoT devices with AI. In this paper we present an experimental study where we perform the observation of time of execution, overheating, Central Processing Unit (CPU) load and power consumption using an embedded system by itself and embedded system with an external low-power Graphics Processing Unit (GPU) able to run the pre-trained neural networks for object detection. We report on the series of experiments conducted on the neural networks with different depth and input size. Experimental results demonstrate high potential of AI application on the IoT devices.