Vision Aided Navigation of a Quad-Rotor for Autonomous Wind-Farm Inspection

Durdevic, Petar; Ortiz-Arroyo, Daniel; Li, Shaobao; Yang, Zhenyu

doi:10.1016/j.ifacol.2019.08.049

Cited by 16 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is a continuation of our previous work in [23], where we used image segmentation for visual servoing. In this work, we avoid segmentation of the video signal and instead use YOLO9000 or Yolov2 as an augmented sensor for localization of objects in the environment.…”

Section: Current Workmentioning

confidence: 95%

“…This system is called end-to-end because instead of using lane detection, path planning and control algorithms separately, it optimizes all this processing simultaneously using the representation model learned by CNN. Refs [13,15,16,[18][19][20][21][22][23] could be classified as end-to-end methods.…”

Section: State Of the Art In Visual Servoingmentioning

confidence: 99%

“…Our previous works on visual servoing for drones also used Alexnet. For instance, in [23], we used transfer learning changing the last layers of Alexnet to create a network capable of recognizing wind turbines. The DNN was called WindMillNet and its output was the probability that an image from the camera contained a wind turbine.…”

Section: State Of the Art In Visual Servoingmentioning

confidence: 99%

See 2 more Smart Citations

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

Durdevic

Ortiz-Arroyo

2020

Sensors

Self Cite

View full text Add to dashboard Cite

This paper describes a novel stereo vision sensor based on deep neural networks, that can be used to produce a feedback signal for visual servoing in unmanned aerial vehicles such as drones. Two deep convolutional neural networks attached to the stereo camera in the drone are trained to detect wind turbines in images and stereo triangulation is used to calculate the distance from a wind turbine to the drone. Our experimental results show that the sensor produces data accurate enough to be used for servoing, even in the presence of noise generated when the drone is not being completely stable. Our results also show that appropriate filtering of the signals is needed and that to produce correct results, it is very important to keep the wind turbine within the field of vision of both cameras, so that both deep neural networks could detect it.

show abstract

Section: Current Workmentioning

confidence: 95%

Section: State Of the Art In Visual Servoingmentioning

confidence: 99%

Section: State Of the Art In Visual Servoingmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

Durdevic

Ortiz-Arroyo

2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, a straightforward strategy consists of using only the increments of the odometry in the filter. An example of the application of this strategy is the Robot Operating System (ROS) package robot_pose_ekf 9 . In this work, we used a different approach, which considers some extra states representing the accumulated error of the visual odometry.…”

Section: State Estimationmentioning

confidence: 99%

“…Drones receive special attention due to their capabilities to execute different tasks 1 Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais (UFMG), Belo Horizonte, MG, Brazil with better precision and lower cost than other traditional aerial vehicles. Several researches address the use of these flying robots for mapping [21], surveillance [31,57], inspections [2,9], package delivery [44,58], among other tasks.…”

Section: Introductionmentioning

confidence: 99%

An integrated solution for an autonomous drone racing in indoor environments

Rezende

Miranda

Rezeck

et al. 2021

Intel Serv Robotics

View full text Add to dashboard Cite

The use of drones is becoming more present in modern daily life. One of the most challenging tasks associated with these vehicles is the development of perception and autonomous navigation systems. Competitions such as Artificial Intelligence Robotic Racing (AIRR) and Autonomous Drone Racing were launched to drive the advances in such strategies, requiring the development of integrated systems for autonomous navigation in a racing environment. In this context, this paper presents an improved integrated solution for autonomous drone racing, which focuses on simple, robust, and computationally efficient techniques to enable the application in embedded hardware. The strategy is divided into four modules: (i) A trajectory planner computes a path that passes through the sequence of desired gates; (ii) a perception system that obtains the global pose of the vehicle by using an onboard camera; (iii) a localization system which merges several sensed information to estimate the drone's states; and, (iv) an artificial vector field-based controller in charge of following the plan by using the estimated states. To evaluate the performance of the entire integrated system, we extended the FlightGoggles simulator to use gates similar to those used in the AIRR competition. A computational cost analysis demonstrates the high performance of the proposed perception method running on limited hardware commonly embedded in aerial robots. In addition, we evaluate the localization system by comparing it with ground truth and when there is a disturbance in the location of the gates. Results in a representative race circuit based on the AIRR competition showed the proposed strategy's competing performance, presenting itself as a feasible solution for drone racing systems.

show abstract

15th European Workshop on Advanced Control and Diagnosis (ACD 2019)

2022

Lecture Notes in Control and Information Sciences - Proceedings

View full text Add to dashboard Cite

This paper presents a novel approach based on deep neural networks for autonomous navigation of a quad-copter UAV in a sparsely populated environment. Images from the video camera mounted on the UAV are split, emulating a compounded eye, and processed by deep neural networks that calculate the probability that each image contains a wind turbine object. Then, these probabilities are used as inputs to a vision servoing system that controls the drone's navigation movements. Our experiments show that our approach produces relatively stable movements in the UAV, allowing it to find and navigate autonomously towards a wind turbine.

show abstract

Vision Aided Navigation of a Quad-Rotor for Autonomous Wind-Farm Inspection

Cited by 16 publications

References 9 publications

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

An integrated solution for an autonomous drone racing in indoor environments

15th European Workshop on Advanced Control and Diagnosis (ACD 2019)

Contact Info

Product

Resources

About