Abstract
Existing mobile robots cannot complete some functions. To solve these problems, which include autonomous learning in path planning, the slow convergence of path planning, and planned paths that are not smooth, it is possible to utilize neural networks to enable to the robot to perceive the environment and perform feature extraction, which enables them to have a fitness of environment to state action function. By mapping the current state of these actions through Hierarchical Reinforcement Learning (HRL), the needs of mobile robots are met. It is possible to construct a path planning model for mobile robots based on neural networks and HRL. In this article, the proposed algorithm is compared with different algorithms in path planning. It underwent a performance evaluation to obtain an optimal learning algorithm system. The optimal algorithm system was tested in different environments and scenarios to obtain optimal learning conditions, thereby verifying the effectiveness of the proposed algorithm. Deep Deterministic Policy Gradient (DDPG), a path planning algorithm for mobile robots based on neural networks and hierarchical reinforcement learning, performed better in all aspects than other algorithms. Specifically, when compared with Double Deep Q-Learning (DDQN), DDPG has a shorter path planning time and a reduced number of path steps. When introducing an influence value, this algorithm shortens the convergence time by 91% compared with the Q-learning algorithm and improves the smoothness of the planned path by 79%. The algorithm has a good generalization effect in different scenarios. These results have significance for research on guiding, the precise positioning, and path planning of mobile robots.
Highlights
Mobile robot autonomous navigation can be divided into three subsystems: information perception, behavior decision-making, and manipulation control
It was found that compared to the Double Deep Q-Learning (DDQN) algorithm, it runs faster and has an optimal path
Compared to the Q-Learning and A3C algorithms, after adding reinforcement learning, the convergence time of robot path planning is increased by 13.54%; compared to the Q-Learning and Deep Q-Learning Network (DQN) algorithms, after adding the neural network algorithm, the convergence time of robot path planning is increased by 33.85%, FIGURE 7 | Experimental results of different path planning algorithms of mobile robot
Summary
Mobile robot autonomous navigation can be divided into three subsystems: information perception, behavior decision-making, and manipulation control. Path planning is the basis of mobile robot navigation and control (Ghosh et al, 2017; Orozco-Rosas et al, 2019). There are many methods of path planning. According to specific algorithms and strategies, path planning algorithms can be roughly divided into four types: template matching, artificial potential field, map construction, and artificial intelligence (Zhao et al, 2018). The current path planning of mobile robots relies heavily on the surrounding environment. In addition to the limitations of traditional path planning, robots cannot complete their learning and judgment in complex environments, a bottleneck in the development of research in this field (Bakdi et al, 2017). It is important to develop a path planning method with low reliance on the environment, which can quickly adapt to the surrounding environment
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 call
