Autonomous obstacle avoidance of UAV based on deep reinforcement learning1

2021 ◽  
pp. 1-13
Author(s):  
Songyue Yang ◽  
Guizhen Yu ◽  
Zhijun Meng ◽  
Zhangyu Wang ◽  
Han Li
Keyword(s):  
Obstacle Avoidance ◽  
Physical Simulation ◽  
Early Stage ◽  
Avoidance Performance ◽  
Optimal Decision ◽  
Simulation Environment ◽  
Average Return ◽  
Aerial Vehicle ◽  
Optimal Decision Making ◽  
3D Physical Simulation

In the intelligent unmanned systems, unmanned aerial vehicle (UAV) obstacle avoidance technology is the core and primary condition. Traditional algorithms are not suitable for obstacle avoidance in complex and changeable environments based on the limited sensors on UAVs. In this article, we use an end-to-end deep reinforcement learning (DRL) algorithm to achieve the UAV autonomously avoid obstacles. For the problem of slow convergence in DRL, a Multi-Branch (MB) network structure is proposed to ensure that the algorithm can get good performance in the early stage; for non-optimal decision-making problems caused by overestimation, the Revise Q-value (RQ) algorithm is proposed to ensure that the agent can choose the optimal strategy for obstacle avoidance. According to the flying characteristics of the rotor UAV, we build a V-Rep 3D physical simulation environment to test the obstacle avoidance performance. And experiments show that the improved algorithm can accelerate the convergence speed of agent and the average return of the round is increased by 25%.

scholarly journals Semi-Automatic Method for Early Detection of Xylella fastidiosa in Olive Trees Using UAV Multispectral Imagery and Geostatistical-Discriminant Analysis

2020 ◽  
Vol 13 (1) ◽  
pp. 14
Author(s):  
Annamaria Castrignanò ◽  
Antonella Belmonte ◽  
Ilaria Antelmi ◽  
Ruggiero Quarto ◽  
Francesco Quarto ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Early Detection ◽  
Plant Pathogens ◽  
Early Stage ◽  
Xylella Fastidiosa ◽  
Mediterranean Countries ◽  
Parametric Classification ◽  
Aerial Vehicle ◽  
Olive Groves ◽  
Olive Trees

Xylella fastidiosa subsp. pauca (Xfp) is one of the most dangerous plant pathogens in the world. Identified in 2013 in olive trees in south–eastern Italy, it is spreading to the Mediterranean countries. The bacterium is transmitted by insects that feed on sap, and causes rapid wilting in olive trees. The paper explores the use of Unmanned Aerial Vehicle (UAV) in combination with a multispectral radiometer for early detection of infection. The study was carried out in three olive groves in the Apulia region (Italy) and involved four drone flights from 2017 to 2019. To classify Xfp severity level in olive trees at an early stage, a combined method of geostatistics and discriminant analysis was implemented. The results of cross-validation for the non-parametric classification method were of overall accuracy = 0.69, mean error rate = 0.31, and for the early detection class of accuracy 0.77 and misclassification probability 0.23. The results are promising and encourage the application of UAV technology for the early detection of Xfp infection.

scholarly journals GEAR: On Optimal Decision Making with Auxiliary Data

Stat ◽  
2021 ◽  
Author(s):  
Hengrui Cai ◽  
Rui Song ◽  
Wenbin Lu
Keyword(s):  
Decision Making ◽  
Optimal Decision ◽  
Auxiliary Data ◽  
Optimal Decision Making

Operation decision of logistics service supply chain: considering interruption probability in emergencies

Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Guangsheng Zhang ◽  
Xiao Wang ◽  
Zhiqing Meng ◽  
Qirui Zhang ◽  
Kexin Wu
Keyword(s):  
Decision Making ◽  
Supply Chain ◽  
Evolutionary Game ◽  
Optimal Strategies ◽  
Optimal Decision ◽  
Content Type ◽  
Logistics Service ◽  
Social Reputation ◽  
Punishment Intensity ◽  
Optimal Decision Making

PurposeTo remedy the inherent defect in current research that focuses only on a single type of participants, this paper endeavors to look into the situation as an evolutionary game between a representative Logistics Service Integrator (LSI) and a representative Functional Logistics Service Provider (FLSP) in an environment with sudden crisis and tries to analyze how LSI supervises FLSP's operations and how FLSP responds in a recurrent pattern with different interruption probabilities.Design/methodology/approachRegarding the risks of supply chain interruption in emergencies, this paper develops a two-level model of single LSI and single FLSP, using Evolutionary Game theory to analyze their optimal decision-making, as well as their strategic behaviors on different risk levels regarding the interruption probability to achieve the optimal return with bounded rationality.FindingsThe results show that on a low-risk level, if LSI increases the degree of punishment, it will fail to enhance FLSP's operational activeness in the long term; when the risk rises to an intermediate level, a circular game occurs between LSI and FLSP; and on a high level of risk, FLSP will actively take actions, and its functional probability further impacts LSI's strategic choices. Finally, this paper analyzes the moderating impact of punishment intensity and social reputation loss on the evolutionary model in emergencies and provides relevant managerial implications.Originality/valueFirst, by taking both interruption probability and emergencies into consideration, this paper explores the interactions among the factors relevant to LSI's and FLSP's optimal decision-making. Second, this paper analyzes the optimal evolutionary game strategies of LSI and FLSP with different interruption probability and the range of their optimal strategies. Third, the findings of this paper provide valuable implications for relevant practices, such that the punishment intensity and social reputation loss determine the optimal strategies of LSI and FLSP, and thus it is an effective vehicle for LSSC system administrator to achieve the maximum efficiency of the system.

Sign in / Sign up

Export Citation Format

Share Document