Abstract
In recent years, artificial intelligence has played an increasingly important role in the field of automated control of drones. After AlphaGo used Intensive Learning to defeat the World Go Championship, intensive learning gained widespread attention. However, most of the existing reinforcement learning is applied in games with only two or three moving directions. This paper proves that deep reinforcement learning can be successfully applied to an ancient puzzle game Nokia Snake after further processing. A game with four directions of movement. Through deep intensive learning and training, the Snake (or self-learning Snake) learns to find the target path autonomously, and the average score on the Snake Game exceeds the average score on human level. This kind of Snake algorithm that can find the target path autonomously has broad prospects in the industrial field, such as: UAV oil and gas field inspection, Use drones to search for and rescue injured people after a complex disaster. As we all know, post-disaster relief requires careful staffing and material dispatch. There are many factors that need to be considered in the artificial planning of disaster relief. Therefore, we want to design a drone that can search and rescue personnel and dispatch materials. Current drones are quite mature in terms of automation control, but current drones require manual control. Therefore, the Snake algorithm proposed here to be able to find the target path autonomously is an attempt and key technology in the design of autonomous search and rescue personnel and material dispatching drones.
Highlights
Drones have low levels of autonomy, and they don’t have the autonomy to complete route self-planning, decision making, coordination, and mutual cooperation
As advanced autonomous unmanned systems, the UAV is destined to develop in the direction of high autonomy, low manual intervention, and high intelligence
The intelligence of search and rescue drones is mainly reflected in the path planning ability of autonomous flight and the ability to perform self-determination of tasks
Summary
Drones have low levels of autonomy, and they don’t have the autonomy to complete route self-planning, decision making, coordination, and mutual cooperation. The delay between the action and the resulting reward (which may be thousands of steps) seems daunting compared to the direct correlation between the input and the goal in supervised learning Another problem is that most deep learning algorithms assume that data samples are independent, while in reinforcement learning, sequences of highly correlated states are often encountered. This paper demonstrates that convolutional neural networks can overcome these challenges and learn successful control strategies from raw video data in complex reinforcement learning environments [8], [9]. The major contributions of this paper are summarized as follows: We apply the method of reinforcement learning to the process of simulating the autonomous exploration of the target by the drone in the game environment of the Snake Game.
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.
