RESUMO
In this study, we investigate the application of generative models to assist artificial agents, such as delivery drones or service robots, in visualising unfamiliar destinations solely based on textual descriptions. We explore the use of generative models, such as Stable Diffusion, and embedding representations, such as CLIP and VisualBERT, to compare generated images obtained from textual descriptions of target scenes with images of those scenes. Our research encompasses three key strategies: image generation, text generation, and text enhancement, the latter involving tools such as ChatGPT to create concise textual descriptions for evaluation. The findings of this study contribute to an understanding of the impact of combining generative tools with multi-modal embedding representations to enhance the artificial agent's ability to recognise unknown scenes. Consequently, we assert that this research holds broad applications, particularly in drone parcel delivery, where an aerial robot can employ text descriptions to identify a destination. Furthermore, this concept can also be applied to other service robots tasked with delivering to unfamiliar locations, relying exclusively on user-provided textual descriptions.
RESUMO
Recent advances have shown for the first time that it is possible to beat a human with an autonomous drone in a drone race. However, this solution relies heavily on external sensors, specifically on the use of a motion capture system. Thus, a truly autonomous solution demands performing computationally intensive tasks such as gate detection, drone localisation, and state estimation. To this end, other solutions rely on specialised hardware such as graphics processing units (GPUs) whose onboard hardware versions are not as powerful as those available for desktop and server computers. An alternative is to combine specialised hardware with smart sensors capable of processing specific tasks on the chip, alleviating the need for the onboard processor to perform these computations. Motivated by this, we present the initial results of adapting a novel smart camera, known as the OpenCV AI Kit or OAK-D, as part of a solution for the ADR running entirely on board. This smart camera performs neural inference on the chip that does not use a GPU. It can also perform depth estimation with a stereo rig and run neural network models using images from a 4K colour camera as the input. Additionally, seeking to limit the payload to 200 g, we present a new 3D-printed design of the camera's back case, reducing the original weight 40%, thus enabling the drone to carry it in tandem with a host onboard computer, the Intel Stick compute, where we run a controller based on gate detection. The latter is performed with a neural model running on an OAK-D at an operation frequency of 40 Hz, enabling the drone to fly at a speed of 2 m/s. We deem these initial results promising toward the development of a truly autonomous solution that will run intensive computational tasks fully on board.
Assuntos
Algoritmos , Redes Neurais de Computação , Computadores , Humanos , Movimento (Física)RESUMO
Autonomous Drone Racing (ADR) was first proposed in IROS 2016. It called for the development of an autonomous drone capable of beating a human in a drone race. After almost five years, several teams have proposed different solutions with a common pipeline: gate detection; drone localization; and stable flight control. Recently, Deep Learning (DL) has been used for gate detection and localization of the drone regarding the gate. However, recent competitions such as the Game of Drones, held at NeurIPS 2019, called for solutions where DL played a more significant role. Motivated by the latter, in this work, we propose a CNN approach called DeepPilot that takes camera images as input and predicts flight commands as output. These flight commands represent: the angular position of the drone's body frame in the roll and pitch angles, thus producing translation motion in those angles; rotational speed in the yaw angle; and vertical speed referred as altitude h. Values for these 4 flight commands, predicted by DeepPilot, are passed to the drone's inner controller, thus enabling the drone to navigate autonomously through the gates in the racetrack. For this, we assume that the next gate becomes visible immediately after the current gate has been crossed. We present evaluations in simulated racetrack environments where DeepPilot is run several times successfully to prove repeatability. In average, DeepPilot runs at 25 frames per second (fps). We also present a thorough evaluation of what we called a temporal approach, which consists of creating a mosaic image, with consecutive camera frames, that is passed as input to the DeepPilot. We argue that this helps to learn the drone's motion trend regarding the gate, thus acting as a local memory that leverages the prediction of the flight commands. Our results indicate that this purely DL-based artificial pilot is feasible to be used for the ADR challenge.