The Effects of Rewards on Autonomous Unmanned Aerial Vehicle (UAV) Operations Using Reinforcement Learning

2021 ◽  
pp. 1-12
Author(s):  
Hemali Virani ◽  
Dahai Liu ◽  
Dennis Vincenzi
Keyword(s):  
Reinforcement Learning ◽  
Steady State ◽  
Unmanned Aerial Vehicle ◽  
Target Localization ◽  
Correct Detection ◽  
Localization Task ◽  
Detection Systems ◽  
Learning Agent ◽  
Aerial Vehicle ◽  
Steady State Performance

The effects of rewards on the ability of an autonomous UAV controlled by a Reinforcement Learning agent to accomplish a target localization task were investigated. It was shown that with an increase in the reward obtained by a learning agent upon correct detection, systems would become more risk-tolerant, efficient and have a tendency to locate targets faster with an increase in the sensor sensitivity after systems achieve steady-state performance.

scholarly journals 3D target localization based on multi–unmanned aerial vehicle cooperation

2020 ◽  
pp. 002029402092226
Author(s):  
Cheng Xu ◽  
Chanjuan Yin ◽  
Daqing Huang ◽  
Wei Han ◽  
Dongzhen Wang
Keyword(s):  
Remote Sensing ◽  
Unmanned Aerial Vehicle ◽  
Target Localization ◽  
Weight Matrix ◽  
Target Point ◽  
Observation Data ◽  
Remote Sensing Images ◽  
Localization Method ◽  
Ground Target ◽  
Aerial Vehicle

Ground target three-dimensional positions measured from optical remote-sensing images taken by an unmanned aerial vehicle play an important role in related military and civil applications. The weakness of this system lies in its localization accuracy being unstable and its efficiency being low when using a single unmanned aerial vehicle. In this paper, a novel multi–unmanned aerial vehicle cooperative target localization measurement method is proposed to overcome these issues. In the target localization measurement stage, three or more unmanned aerial vehicles simultaneously observe the same ground target and acquire multiple remote-sensing images. According to the principle of perspective projection, the target point, its image point, and the camera’s optic center are collinear, and nonlinear observation equations are established. These equations are then converted to linear equations using a Taylor expansion. Robust weighted least-squares estimation is used to solve the equations with the objective function of minimizing the weighted square sum of re-projection errors from target points to multiple pairs of images, which can make the best use of the effective information and avoid interference from the observation data. An automatic calculation strategy using a weight matrix is designed, and the weight matrix and target-position coordinate value are updated in each iteration until the iteration stopping condition is satisfied. Compared with the stereo-image-pair cross-target localization method, the multi–unmanned aerial vehicle cooperative target localization method can use more observation information, which results in higher rendezvous accuracy and improved performance. Finally, the effectiveness and robustness of this method is verified by numerical simulation and flight testing. The results show that the proposed method can effectively improve the precision of the target’s localization and demonstrates great potential for providing more accurate target localization in engineering applications.

Reinforcement Learning-Based Optimal Flat Spin Recovery for Unmanned Aerial Vehicle

2017 ◽  
Vol 40 (4) ◽  
pp. 1076-1084 ◽  
Author(s):  
Donghae Kim ◽  
Gyeongtaek Oh ◽  
Yongjun Seo ◽  
Youdan Kim
Keyword(s):  
Reinforcement Learning ◽  
Unmanned Aerial Vehicle ◽  
Aerial Vehicle

scholarly journals Synthesis of algorithm of unmanned aerial vehicle detection by acoustic noise

Doklady BGUIR ◽  
2021 ◽  
Vol 19 (2) ◽  
pp. 65-73
Author(s):  
A. D. Puzanau ◽  
D. S. Nefedov
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Acoustic Noise ◽  
Signal To Noise Ratio ◽  
Weather Conditions ◽  
Wind Noise ◽  
Detection Range ◽  
Detection Systems ◽  
A Value ◽  
Coherent Accumulation ◽  
Aerial Vehicle

 The algorithm of detection of acoustic noise provided by an unmanned aerial vehicle (UAV) in the noise background due to wind is synthesized in the article. Creation of the algorithm has been carried out using the Neyman – Pearson lemma. The algorithm assumes a combination of the stages of wind noise coherent compensation and coherent accumulation of UAV’s acoustic noise sound pressure impulses. The coherent accumulation time matches doubled time of fluctuation correlation resulted by experimental research of acoustic noise of different types of  UAVs. Efficiency of the developed algorithm of UAV detection depends on flight velocity, foreshortening, amount of blades and rotor turnovers of UAV as well as weather conditions. For the probability of a false alarm value of 10–4, the probability of correct UAV detection value of 0.9 is provided wherein signal-to-noise ratio has a value of 8 dB. These indicators correspond the detection range of 200 to 300 meters. The obtained results allow discussions about perspective of acoustic UAVs detection systems adaptation. 

scholarly journals Model Penahan Ketinggian Quadrotor Berbasis PID dengan Jaringan Syaraf Tiruan Propagasi Mundur

2021 ◽  
Vol 10 (2) ◽  
pp. 156-162
Author(s):  
Faisal Fajri Rahani ◽  
Dinan Yulianto
Keyword(s):  
Steady State ◽  
Real Time ◽  
Unmanned Aerial Vehicle ◽  
Rise Time ◽  
Settling Time ◽  
Aerial Vehicle ◽  
State Error

Quadrotor adalah salah satu jenis Unmanned Aerial Vehicle (UAV) atau wahana terbang tanpa awak yang dapat terbang dengan kendali jarak jauh maupun menggunakan kendali otomatis. Dalam melakukan misinya, quadrotor memerlukan sistem kendali yang baik. Salah satu sistem kendali dalam sistem quadrotor adalah sistem kendali ketinggian. Kendali ketinggian akan mengendalikan quadrotor seusai ketinggian yang diinginkan walaupun terdapat gangguan dan beban quadrotor itu sendiri. Metode kendali yang banyak digunakan adalah kendali PID. Kendali PID menghasilkan respons yang kurang baik karena konstanta PID yang bersifat tetap, sedangkan gangguan saat quadrotor terbang akan berubah-ubah. Oleh karena itu, makalah ini menawarkan kendali yang dapat menyesuaikan diri saat terkena gangguan tertentu. Metode yang ditawarkan adalah kendali PID dengan Jaringan Saraf Tiruan (JST). Sistem JST akan menala komponen PID secara real-time sesuai gangguan yang terjadi. Penggunaan PID dengan JST menghasilkan respons rise time lebih cepat 0,0594 detik, overshoot turun 7,58%, steady state error turun ±0,0672, dan settling time turun 1,031 detik dibandingkan dengan PID konvensional. Hal ini menunjukkan bahwa PID dengan JST menghasilkan respons kendali yang lebih baik dibandingkan dengan PID saja.

Sign in / Sign up

Export Citation Format

Share Document