Deep Reinforcement Learning for UAV Intelligent Mission Planning

Yue, Longfei; Yang, Rennong; Zhang, Ying; Yu, Lixin; Wang, Zhuangzhuang

doi:10.1155/2022/3551508

Cited by 10 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML algorithms are used in increment Path efficiency for multi objectives. Sequential decisionmaking problem-solving based on intelligent mission planning methods [37] can be used in the Suppression of Enemy Air Defense (SEAD). The experiments study DRL based on a PPO algorithm that considers the basis of DRL to gain high performance and robustness.…”

Section: ) Machine Learning Approaches In Uavmentioning

confidence: 99%

Routing Approaches used for Electrical Vehicles Navigation: A Survey

Hejres,

Mahjoub,

Hewahi

2024

IJCDS

View full text Add to dashboard Cite

The growing demand for Electric Vehicles (EVs) depends on the high integration of this technology in many areas. Therefore, an important area of research raises interest in finding the optimal path-planning solution for electric vehicles. This paper discusses several reviews and analyzes some of the constraints of the techniques used to improve these systems. The paper discusses common models used in Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGV). This paper investigates the planning approaches that lead to finding the optimal route for the tour from the source to the destination. The review outlines the different models and systems of Unmanned Ariel Vehicles (UAV) and Unmanned Ground Vehicles (UGV). This paper can be considered as comprehensive survey research for EV routing techniques to assist researchers choose the appropriate approach for developing a system based on optimization techniques, machine learning, or Hybrid Approaches (HAs) techniques. Optimization techniques are mostly used to find the optimal path and achieve multi-objective goals. Some findings were approved as the best models inspired by natural biological as genetic algorithms, Particle Swarm Optimization, and Ant Colony Optimization. In addition to machine learning techniques as Reinforcement Learning. The hybrid approach techniques that combine optimization and machine learning techniques can increase robustness in solving routing problems.

show abstract

Section: ) Machine Learning Approaches In Uavmentioning

confidence: 99%

Routing Approaches used for Electrical Vehicles Navigation: A Survey

Hejres,

Mahjoub,

Hewahi

2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…In the tracking of the vehicle, it is necessary to determine each frame of the vehicle motion, establish a Kalman filter to predict the vehicle position, and let the state vector of the vehicle be s k = ½s k y k ŝk ŷk T . The first two components are the vector values of the vehicle on the x-axis and y-axis, and the last two components are the speed of the vehicle on the x-axis and y-axis [27].…”

Section: Combination Of Mean-shift and Kalman Filteringmentioning

confidence: 99%

Moving Target Detection Technology Based on UAV Vision

Cheng¹,

Qin²,

Chen³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The detection of moving objects by machine vision is a hot research direction in recent years. It is widely used in military, medical, transportation, and agriculture. With the rapid development of UAV technology, as well as the high mobility of UAVs and the wide range of high-altitude vision, the target detection technology based on UAV vision is applied to traffic management such as vehicle tracking and detection of vehicle violations. The moving target detection technology in this study is based on the YOLOv3 algorithm. It implements moving vehicle tracking by means of Mean-Shift and Kalman filtering. In this paper, the Gaussian background difference technology is used to analyze the illegal behavior of the vehicle, and the color feature extraction technology is used to identify and locate the license plate, and the information of the illegal vehicle is entered into the database. The experiment compares the moving target detection of UAV vision and the traditional target detection in four aspects: recognition accuracy, recognition speed, manual time, and divergent results. The results show that the average accuracy rates of UAV vision-based moving target detection and traditional pattern recognition are 98.4% and 87.8%, respectively. The recognition speeds are 24.9 (vehicles/sec) and 10.6 (vehicles/sec), respectively. However, the artificial time and divergence results of moving target detection based on UAV vision are only 1/3 of the traditional mode. The moving target detection based on UAV vision has a better moving target detection ability.

show abstract

“…The simulation sets the mission planning scenario in a square area with size 100 km × 100 km. The jammer and reconnaissance UAVs took off from coordinates (20,20) and (23,23), respectively. The two UAVs passed through three radar detection areas to reach the target protected by ground-to-missile, which is deployed in (80,80) and performed the reconnaissance task when the relative distance to the target is less than 20 km.…”

Section: Experiments Establishmentmentioning

confidence: 99%

“…When considering the suppression of enemy air defense mission planning, Ref. [23] established a general intelligent planning architecture based on the proximal policy optimization (PPO) algorithm, but it was not considered a dynamic situation; the experiments only involved direct strikes without situation changes during flight. Unfortunately, the UAV mission planning designed in these studies has weakened the obstacles and purpose requirements in the navigation mission planning, so there is no guarantee of the generalizability of the DRL agent or the robustness of navigation control, especially for target reconnaissance and jamming.…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning for Intelligent Dual-UAV Reconnaissance Mission Planning

et al. 2022

Self Cite

View full text Add to dashboard Cite

The reconnaissance of high-value targets is prerequisite for effective operations. The recent appreciation of deep reinforcement learning (DRL) arises from its success in navigation problems, but due to the competitiveness and complexity of the military field, the applications of DRL in the military field are still unsatisfactory. In this paper, an end-to-end DRL-based intelligent reconnaissance mission planning is proposed for dual unmanned aerial vehicle (dual UAV) cooperative reconnaissance missions under high-threat and dense situations. Comprehensive consideration is given to specific mission properties and parameter requirements through the whole modelling. Firstly, the reconnaissance mission is described as a Markov decision process (MDP), and the mission planning model based on DRL is established. Secondly, the environment and UAV motion parameters are standardized to input the neural network, aiming to deduce the difficulty of algorithm convergence. According to the concrete requirements of non-reconnaissance by radars, dual-UAV cooperation and wandering reconnaissance in the mission, four reward functions with weights are designed to enhance agent understanding to the mission. To avoid sparse reward, the clip function is used to control the reward value range. Finally, considering the continuous action space of reconnaissance mission planning, the widely applicable proximal policy optimization (PPO) algorithm is used in this paper. The simulation is carried out by combining offline training and online planning. By changing the location and number of ground detection areas, from 1 to 4, the model with PPO can maintain 20% of reconnaissance proportion and a 90% mission complete rate and help the reconnaissance UAV to complete efficient path planning. It can adapt to unknown continuous high-dimensional environmental changes, is generalizable, and reflects strong intelligent planning performance.

show abstract

Deep Reinforcement Learning for UAV Intelligent Mission Planning

Cited by 10 publications

References 17 publications

Routing Approaches used for Electrical Vehicles Navigation: A Survey

Routing Approaches used for Electrical Vehicles Navigation: A Survey

Moving Target Detection Technology Based on UAV Vision

Deep Reinforcement Learning for Intelligent Dual-UAV Reconnaissance Mission Planning

Contact Info

Product

Resources

About