Monocular visual mapping for obstacle avoidance on UAVs

Magree, Daniel; Mooney, John G.; Johnson, Eric N.

doi:10.1109/icuas.2013.6564722

Cited by 16 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [94] a monocular based feature estimation algorithm for terrain mapping was presented, which performed obstacle avoidance for UAVs. The proposed method utilized an EKF to estimate the location of image features in the environment, with the major advantage to be the fast depth convergence of estimated feature points, which was succeeded by the utilization of inverse depth parameterization.…”

Section: Obstacle Detectionmentioning

confidence: 99%

Survey on Computer Vision for UAVs: Current Developments and Trends

Kanellakis

Nikolakopoulos

2017

J Intell Robot Syst

295

120

View full text Add to dashboard Cite

During last decade the scientific research on Unmanned Aerial Vehicless (UAVs) increased spectacularly and led to the design of multiple types of aerial platforms. The major challenge today is the development of autonomously operating aerial agents capable of completing missions independently of human interaction. To this extent, visual sensing techniques have been integrated in the control pipeline of the UAVs in order to enhance their navigation and guidance skills. The aim of this article is to present a comprehensive literature review on vision based applications for UAVs focusing mainly on current developments and trends. These applications are sorted in different categories according to the research topics among various research groups. More specifically vision based position-attitude control, pose estimation and mapping, obstacle detection as well as target tracking are the identified components towards autonomous agents. Aerial platforms could reach greater level of autonomy by integrating all these technologies onboard. Additionally, throughout this article the concept of fusion multiple sensors is highlighted, while an overview on the challenges C. Kanellakis ( ) · G. Nikolakopoulos Luleå University of Technology, Luleå, Sweden e-mail: christoforos.kanellakis@ltu.se G. Nikolakopoulos e-mail: geonik@ltu.se addressed and future trends in autonomous agent development will be also provided.

show abstract

Section: Obstacle Detectionmentioning

confidence: 99%

Survey on Computer Vision for UAVs: Current Developments and Trends

Kanellakis

Nikolakopoulos

2017

J Intell Robot Syst

295

120

View full text Add to dashboard Cite

show abstract

“…It is especially important in the scenarios where the GPS information is partially not available or not precise enough to process it. Sensors like RGB-D cameras [15], Laser [18], monocular camera [21], and stereo cameras [3] are used mobile robotics applications. The selection of the appropriate sensors suit depends on many factors, such as the robot's payload capability, computational power, light variations, size of the environment, color intensities, or the textures richness of the outdoor scenario.…”

Section: Related Workmentioning

confidence: 99%

Real-time graph-based SLAM in unknown environments using a small UAV

Annaiyan

Olivares-Méndez

Voos

2017

2017 International Conference on Unmanned Aircraft Systems (ICUAS)

View full text Add to dashboard Cite

Abstract-Autonomous navigation of small Unmanned Aerial Vehicles (UAVs) in cluttered environments is still a challenging problem. In this work, we present an approach based on graph slam and loop closure detection for online mapping of unknown outdoor environments using a small UAV. Here, we used an onboard front facing stereo camera as the primary sensor. The data extracted by the cameras are used by the graph-based slam algorithm to estimate the position and create the graph-nodes and construct the map. To avoid multiple detections of one object as different objects and to identify re-visited locations, a loop closure detection is applied with optimization algorithm using the g2o toolbox to minimize the error. Furthermore, 3D occupancy map is used to represent the environment. This technique is used to save memory and computational time for the online processing. Real experiments are conducted in outdoor cluttered and open field environments.The experiment results show that our presented approach works under real time constraints, with an average time to process the nodes of the 3D map is 17.79ms

show abstract

“…There are various researches for navigating and avoiding obstacles for a moving robot [22,23] or other vehicles [4,[24][25][26][27][28]. In the all these works, the moving obstacle avoidance problem was tackled as a path planning problem.…”

Section: Introductionmentioning

confidence: 99%

State Dependent Riccati Equation (SDRE) controller design for moving obstacle avoidance in mobile robot

Asgari

Foghahayee

2020

SN Appl. Sci.

View full text Add to dashboard Cite

In this paper, a new navigating method for a non-holonomic wheeled moving robot in a dynamic environment with the moving obstacles is proposed. This method is indeed the combination of the nonlinear optimal controller based on State-Dependent Riccati Equation (SDRE) and an obstacle avoidance algorithm named artificial potential field (APF). The corresponding cost function of the SDRE is obtained of APF algorithm. APF algorithm forces the robot to approach the target as an attracting (low-potential) point and to get away from the obstacle as a repulsing (high-potential) point. This method calculates the best path from origin to destination which also implicitly guaranties the stability. The obtained path is the best according to the both amount of traveled distance and input energy. Moreover, this approach not only avoid both fixed and moving obstacle, but also create a smooth path in presence of them. Keeping the nonlinear structure of the system instead of eliminating them during the linearization process is the advantage of SDRE method. Here, the robot navigation is done in the presence of the three different movements of obstacle: (1) fixed speed, (2) fixed acceleration and (3) non-uniform circular. The represented simulation results indicate a suitable performance of the proposed algorithm.

show abstract

Monocular visual mapping for obstacle avoidance on UAVs

Cited by 16 publications

References 13 publications

Survey on Computer Vision for UAVs: Current Developments and Trends

Survey on Computer Vision for UAVs: Current Developments and Trends

Real-time graph-based SLAM in unknown environments using a small UAV

State Dependent Riccati Equation (SDRE) controller design for moving obstacle avoidance in mobile robot

Contact Info

Product

Resources

About