Abstract
Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The feature representation of the depth image was extracted through a pre-trained convolutional-neural-networks model. Based on the recent success of deep Q-network on artificial intelligence, the robot controller achieved the exploration and obstacle avoidance abilities in several different simulated environments. It is the first time that the reinforcement learning is used to build an exploration strategy for mobile robots through raw sensor information.
Highlights
For mobile robots, exploration in an unknown environment is always a fundamental problem in various areas, such as rescue and mining
Regarding the requirements mentioned above, deep reinforcement learning (DRL), merging reinforcement learning and deep learning, is a proper method to apply in this scenario
We developed a Convolutional neural network (CNN)-based reinforcement learning method for mobile robots to explore an unknown environment based on raw sensor information
Summary
Exploration in an unknown environment is always a fundamental problem in various areas, such as rescue and mining. Robot requires complicated logic about the obstacles and the topological mapping of environments [1, 2] designed by human beings based on the information provided from vision or depth sensors. Convolutional neural networks [3], called deep learning, have attracted more and more attentions in artificial intelligence. This hierarchical model shows great potential in feature representations. Google DeepMind implemented a deep Q-network (DQN) [4] on 49 Atari-2600 games. This method outperformed almost all of other state-of-the-art
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.
