DeepPilot: A CNN for Autonomous Drone Racing

Rojas-Perez, L. Oyuki; Martínez-Carranza, José

doi:10.3390/s20164524

Cited by 42 publications

(9 citation statements)

References 26 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, other endto-end systems generally require an inner-loop controller and inertial information to be executed. For instance, [154] trains an end-to-end CNN to directly predict roll, pitch, yaw, and altitude from camera images. Similarly, [155] uses a neural network to predict commands directly from vision.…”

Section: Sensorsmentioning

confidence: 99%

Autonomous Drone Racing: A Survey

Hanover¹,

Loquercio²,

Bauersfeld³

et al. 2023

Preprint

View full text Add to dashboard Cite

Section: Sensorsmentioning

confidence: 99%

Autonomous Drone Racing: A Survey

Hanover¹,

Loquercio²,

Bauersfeld³

et al. 2023

Preprint

View full text Add to dashboard Cite

“…Furthermore, the CNN is utilized in autonomous drone racing, capable of beating a drone controlled by human as proposed in [24]. Moreover, the CNN is used to detect sidewalk area and implemented in a drone to fly autonomously, to deliver products, without disturbing the traffic flow as presented in [25].…”

Section: Related Workmentioning

confidence: 99%

An Improved Deep Convolutional Neural Network-Based Autonomous Road Inspection Scheme Using Unmanned Aerial Vehicles

2021

View full text Add to dashboard Cite

Recent advancements in the field of machine learning (ML) provide opportunity to conduct research on autonomous devices for a variety of applications. Intelligent decision-making is a critical task for self-driving systems. An attempt is made in this study to use a deep learning (DL) approach for the early detection of road cracks, potholes, and the yellow lane. The accuracy is not sufficient after training with the default model. To enhance accuracy, a convolutional neural network (CNN) model with 13 convolutional layers, a softmax layer as an output layer, and two fully connected layers (FCN) are constructed. In order to achieve the deeper propagation and to prevent saturation in the training phase, mish activation is employed in the first 12 layers with a rectified linear unit (ReLU) activation function. The upgraded CNN model performs better than the default CNN model in terms of accuracy. For the varied situation, a revised and enriched dataset for road cracks, potholes, and the yellow lane is created. The yellow lane is detected and tracked in order to move the unmanned aerial vehicle (UAV) autonomously by following yellow lane. After identifying a yellow lane, the UAV performs autonomous navigation while concurrently detecting road cracks and potholes using the robot operating system within the UAV. The performance model is benchmarked using performance measures, such as accuracy, sensitivity, F1-score, F2-score, and dice-coefficient, which demonstrate that the suggested technique produces better outcomes.

show abstract

“…The use of deep learning has revolutionised the development of autonomous vehicles due to their robustness and versatility in providing solutions for autonomous drone racing, for example, gating detection, relative positioning [19][20][21][22][23], flight commands [8,24,25], actions [2], speed, and even the direction of the drone [4,19]. In addition, deep learning makes it possible to transfer the knowledge acquired in simulation environments to the real world [21,26].…”

Section: Related Workmentioning

confidence: 99%

Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera

Rojas-Perez

Martínez-Carranza

2021

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

DeepPilot: A CNN for Autonomous Drone Racing

Cited by 42 publications

References 26 publications

Autonomous Drone Racing: A Survey

Autonomous Drone Racing: A Survey

An Improved Deep Convolutional Neural Network-Based Autonomous Road Inspection Scheme Using Unmanned Aerial Vehicles

Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera

Contact Info

Product

Resources

About