Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground

Wang, Peng; Li, Xiaoqiang; Song, Chunxiao; Zhai, Shipeng

doi:10.1155/2020/7167243

Cited by 9 publications

(8 citation statements)

References 13 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each attribute of employment data is generalized, and the original data set of college students' employment is divided into a conditional attribute set and a target attribute set. e goal of generalization is to divide the interval of continuous employment attributes in the original data set of college students' employment into many cells, each with a discrete symbol [25]. In order to create a decision-making system, match the nodes in the hierarchical classification model with the conditional attributes of the employment data set to be classified.…”

Section: Construction Of Predictive Factor Model Of Subjectivementioning

confidence: 99%

Subjective Employment Obstacle of College Students and Its Predictor Model Based on Deep Learning

Wang¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the development of higher education in full swing, the number of college students in China is increasing, the employment pressure of college students is increasing, and the employment situation in universities is not optimistic. Subjective career obstacles are obstacles that individuals may encounter when they perceive themselves according to their own conditions and surrounding environmental factors based on their future career pursuit and goals. In this paper, it is of practical significance to use the employment confidence index of college students to analyze and predict their employment confidence. Based on DL (deep learning), a model GM-BPNN (Gray model-BP neural network) of subjective employment obstacles of college students and its predictive factors is proposed. Initially, the employment data of a university are collected and normalized. Then, GM and BPNN are used to model and predict the number of college students’ employment from different angles. Finally, the weights of the prediction results of GM and BPNN are determined, and the final prediction results of the number of college students’ employment are obtained by weighting. The results show that the relative error of the combined model is smaller and the accuracy is higher.

show abstract

Section: Construction Of Predictive Factor Model Of Subjectivementioning

confidence: 99%

Subjective Employment Obstacle of College Students and Its Predictor Model Based on Deep Learning

Wang¹

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…A sale price near to one indicates that long-term incentives are weighted similarly to short-term rewards, but a reduced interest factor indicates that the individual is myopic and only cares about prizes that are due this month in Eq. (2).…”

Section: Dqn Algorithmmentioning

confidence: 99%

“…The autonomous robots use a tool path to choose the best path from point A to point B without colliding with any barriers [1]. The proposed approach for mobile robots is in the face of increasing scientific and technological breakthroughs is currently confronted with a complicated and dynamic world [2]. The traditional path planning algorithms lack certain salient merits such as least working cost and minimal processing time.…”

Section: Introductionmentioning

confidence: 99%

“…But emphasizes theoretical accuracy with the conducted research [11]. Wang et al (2020) had described that the dynamic path planning algorithm is incapable of solving problems related to wheeled mobile robots with scenarios including slopes and dynamic obstacles constantly moving at their rate. The Tree-Double Deep Q Network technique for variable trajectory tracking in robotic systems is suggested in this research.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Potential Field Incorporated Deep-Q-Network Algorithm for Mobile Robot Path Prediction

Sivaranjani¹,

Vinod²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Autonomous navigation of mobile robots is a challenging task that requires them to travel from their initial position to their destination without collision in an environment. Reinforcement Learning methods enable a state action function in mobile robots suited to their environment. During trial-and-error interaction with its surroundings, it helps a robot to find an ideal behavior on its own. The Deep Q Network (DQN) algorithm is used in TurtleBot 3 (TB3) to achieve the goal by successfully avoiding the obstacles. But it requires a large number of training iterations. This research mainly focuses on a mobility robot's best path prediction utilizing DQN and the Artificial Potential Field (APF) algorithms. First, a TB3 Waffle Pi DQN is built and trained to reach the goal. Then the APF shortest path algorithm is incorporated into the DQN algorithm. The proposed planning approach is compared with the standard DQN method in a virtual environment based on the Robot Operation System (ROS). The results from the simulation show that the combination is effective for DQN and APF gives a better optimal path and takes less time when compared to the conventional DQN algorithm. The performance improvement rate of the proposed DQN + APF in comparison with DQN in terms of the number of successful targets is attained by 88%. The performance of the proposed DQN + APF in comparison with DQN in terms of average time is achieved by 0.331 s. The performance of the proposed DQN + APF in comparison with DQN average rewards in which the positive goal is attained by 85% and the negative goal is attained by −90%.

show abstract

“…Lei et al found that adding the Q-Learning algorithm to the reinforcement learning path enhances the ability of robots to dynamically avoid obstacles and local planning in the environment (Lei et al, 2018 ; Liu et al, 2019 ). Wang et al found that compared with Distributed DQN (DDQN) algorithm, the Tree Double Deep Network (TDDQN) has the advantages of fast convergence speed and low loss (Wang P. et al, 2020 ). By using a neural network to strengthen the learning path planning system, Wen et al suggested that the mobile robot can be navigated to a target position without colliding with any obstacles and other mobile robots, and this method was successfully applied to the physical robot platform (Wen et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

The Path Planning of Mobile Robot by Neural Networks and Hierarchical Reinforcement Learning

Liao

2020

Front. Neurorobot.

View full text Add to dashboard Cite

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.

show abstract

Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground

Cited by 9 publications

References 13 publications

Subjective Employment Obstacle of College Students and Its Predictor Model Based on Deep Learning

Subjective Employment Obstacle of College Students and Its Predictor Model Based on Deep Learning

Artificial Potential Field Incorporated Deep-Q-Network Algorithm for Mobile Robot Path Prediction

The Path Planning of Mobile Robot by Neural Networks and Hierarchical Reinforcement Learning

Contact Info

Product

Resources

About