Deep Reinforcement Learning based Aggressive Collision Avoidance with Limited FOV for Unmanned Aerial Vehicles

2022 ◽  
Author(s):  
Mehmet Hasanzade ◽  
Omar Shadeed ◽  
Emre Koyuncu
Robotica ◽  
2021 ◽  
pp. 1-20
Author(s):  
Daegyun Choi ◽  
Anirudh Chhabra ◽  
Donghoon Kim

Summary This paper proposes an intelligent cooperative collision avoidance approach combining the enhanced potential field (EPF) with a fuzzy inference system (FIS) to resolve local minima and goal non-reachable with obstacles nearby issues and provide a near-optimal collision-free trajectory. A genetic algorithm is utilized to optimize parameters of membership function and rule base of the FISs. This work uses a single scenario containing all issues and interactions among unmanned aerial vehicles (UAVs) for training. For validating the performance, two scenarios containing obstacles with different shapes and several UAVs in small airspace are considered. Multiple simulation results show that the proposed approach outperforms the conventional EPF approach statistically.


Actuators ◽  
2018 ◽  
Vol 8 (1) ◽  
pp. 1 ◽  
Author(s):  
Sunan Huang ◽  
Rodney Swee Huat Teo ◽  
Wenqi Liu

It is well-known that collision-free control is a crucial issue in the path planning of unmanned aerial vehicles (UAVs). In this paper, we explore the collision avoidance scheme in a multi-UAV system. The research is based on the concept of multi-UAV cooperation combined with information fusion. Utilizing the fused information, the velocity obstacle method is adopted to design a decentralized collision avoidance algorithm. Four case studies are presented for the demonstration of the effectiveness of the proposed method. The first two case studies are to verify if UAVs can avoid a static circular or polygonal shape obstacle. The third case is to verify if a UAV can handle a temporary communication failure. The fourth case is to verify if UAVs can avoid other moving UAVs and static obstacles. Finally, hardware-in-the-loop test is given to further illustrate the effectiveness of the proposed method.


Author(s):  
Jialong Zhang ◽  
Bing Xiao ◽  
Maolong Lv ◽  
Qiang Zhang

This article addresses a flight-stability problem for the multiple unmanned aerial vehicles cooperative formation flight in the process of the closed and high-speed flight. The main objective is to design a cooperative formation controller with known external factors, and this controller can keep the consensus of attitude and position and reduce the communication delay between any two unmanned aerial vehicles and increase unmanned aerial vehicles formation cruise time under the known external factors. Known external factors are taken into consideration, and longitude maneuvers using nonlinear thrust vectors were employed with unsteady aerodynamic models, according to the attitude and position of unmanned aerial vehicles, which were employed as corresponding input signals for studying the dynamic characteristics of unmanned aerial vehicles formation flight. In addition, the relative distance between any two unmanned aerial vehicles was not allowed to exceed their safe distance so that the controller could perform collision avoidance. An analysis of formation flight distance error shows that it converged to a fixed value that well ensured unmanned aerial vehicles formation flight stability. The experimental results show that the controller can improve the speed of a closed formation effectively and maintain the stability of formation flight, which provides a method for closed formation flight controller design and collision avoidance for any two unmanned aerial vehicles. Meanwhile, the effectiveness of proposed controller is fully proved by semi-physical simulation platform.


Author(s):  
Jun Tang ◽  
Jiayi Sun ◽  
Cong Lu ◽  
Songyang Lao

Multi-unmanned aerial vehicle trajectory planning is one of the most complex global optimum problems in multi-unmanned aerial vehicle coordinated control. Results of recent research works on trajectory planning reveal persisting theoretical and practical problems. To mitigate them, this paper proposes a novel optimized artificial potential field algorithm for multi-unmanned aerial vehicle operations in a three-dimensional dynamic space. For all purposes, this study considers the unmanned aerial vehicles and obstacles as spheres and cylinders with negative electricity, respectively, while the targets are considered spheres with positive electricity. However, the conventional artificial potential field algorithm is restricted to a single unmanned aerial vehicle trajectory planning in two-dimensional space and usually fails to ensure collision avoidance. To deal with this challenge, we propose a method with a distance factor and jump strategy to resolve common problems such as unreachable targets and ensure that the unmanned aerial vehicle does not collide into the obstacles. The method takes companion unmanned aerial vehicles as the dynamic obstacles to realize collaborative trajectory planning. Besides, the method solves jitter problems using the dynamic step adjustment method and climb strategy. It is validated in quantitative test simulation models and reasonable results are generated for a three-dimensional simulated urban environment.


Sign in / Sign up

Export Citation Format

Share Document