Abstract
With the continuous development of UAV technology, UAV has been widely used in various industries. In the flight process of UAV, UAV often changes the given path because of obstacles (including static nonliving body and moving living body). According to the properties of obstacles and the characteristics of UAV, standard Kalman filter is used for nonmaneuvering targets, and sigma point Kalman filter is used for maneuvering targets. In the aspect of obstacle avoidance, the minimum search method is used to get the initial population of local programming. Then, the improved genetic algorithm is run. Combined with the predicted obstacle features, the local planning path can be obtained. Finally, the local planning path and global planning path are combined to generate the planning path with new obstacles. At the end of the paper, the obstacle avoidance strategies of static and moving obstacles are simulated. The simulation results show that this method has fast convergence speed and good feasibility and can flexibly deal with the obstacle avoidance and local path planning of various new obstacles.
Highlights
In recent years, with the continuous development of UAV and computer technology, UAV technology is widely used in power, agriculture, film, and other industries
The planning path with new obstacles is generated by combining the local planning path and the global planning path. e simulation results show that this method has fast convergence speed and good feasibility and can flexibly deal with obstacle avoidance and local path planning of various new obstacles
When UAV flies on the planned path, new obstacles appear on the planned path
Summary
With the continuous development of UAV and computer technology, UAV technology is widely used in power, agriculture, film, and other industries. Many research studies on UAV obstacle avoidance are to obtain the two-dimensional position information of UAV height through UAV airborne radar and construct an artificial potential field model to guide UAV to quickly track targets and avoid air obstacles. Similar to this obstacle avoidance method, it is more suitable for obstacle avoidance of stationary objects and does not predict dynamic objects [1, 2]. The main starting point of these research results is to avoid obstacles, which is not fully based on the attributes of obstacles and the characteristics of UAV, so as to organically combine safety obstacle avoidance and path planning. Obstacle avoidance is based on the results of target recognition
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
