A cache-genetic-based modular fuzzy neural network for robot path planning

2002 ◽  
Author(s):  
Kun Hsiang Wu ◽  
Chin Hsing Chen ◽  
Jiann Der Lee
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Fuzzy Neural Network ◽  
Robot Path Planning ◽  
Fuzzy Neural ◽  
Robot Path

An Adaptive Path Planning Based on Improved Fuzzy Neural Network for Multi-Robot Systems

Fuzzy Systems ◽  
2017 ◽  
pp. 1396-1424
Author(s):  
Zhiguo Shi ◽  
Huan Zhang ◽  
Jingyun Zhou ◽  
Junming Wei
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Fuzzy Neural Network ◽  
Robot Path Planning ◽  
A Algorithm ◽  
Effective Performance ◽  
Robot Systems ◽  
Fuzzy Neural ◽  
Adaptive Control Strategy ◽  
Robot Path

The fuzzy neural network (FNN) is the combination of fuzzy theory with neural network, which has advantages of validity and adaptability in robot path planning. However, the path planning based on the FNN is not optimal because of the limitations of the subjective experience and motion mutation and the dead-zone. In this paper, FNN is improved by using A* graph search algorithm to guarantee an optimal path, providing the rationality and the feasibility, in which the grid map is divided into two stages, including the A* algorithm in the first stage and FNN in the second stage. In addition, a neural network based on adaptive control strategy is introduced to compensate the sensor failure and ensures the stability, which is caused by the loss of data and information uncertainty. The simulation results show that the approach is with effective performance in the robot path planning.

Optimal Robot Path Planning with Cellular Neural Network

2013 ◽  
pp. 19-38
Author(s):  
Yongmin Zhong ◽  
Bijan Shirinzadeh ◽  
Xiaobu Yuan
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
State Space ◽  
Real Time ◽  
Cellular Neural Network ◽  
Neural Dynamics ◽  
Robot Path Planning ◽  
Local Connectivity ◽  
Target Activity ◽  
Robot Path

This paper presents a new methodology based on neural dynamics for optimal robot path planning by drawing an analogy between cellular neural network (CNN) and path planning of mobile robots. The target activity is treated as an energy source injected into the neural system and is propagated through the local connectivity of cells in the state space by neural dynamics. By formulating the local connectivity of cells as the local interaction of harmonic functions, an improved CNN model is established to propagate the target activity within the state space in the manner of physical heat conduction, which guarantees that the target and obstacles remain at the peak and the bottom of the activity landscape of the neural network. The proposed methodology cannot only generate real-time, smooth, optimal, and collision-free paths without any prior knowledge of the dynamic environment, but it can also easily respond to the real-time changes in dynamic environments. Further, the proposed methodology is parameter-independent and has an appropriate physical meaning.

Optimal Robot Path Planning With Cellular Neural Network

2019 ◽  
pp. 491-511
Author(s):  
Yongmin Zhong ◽  
Bijan Shirinzadeh ◽  
Xiaobu Yuan
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
State Space ◽  
Real Time ◽  
Cellular Neural Network ◽  
Neural Dynamics ◽  
Robot Path Planning ◽  
Local Connectivity ◽  
Target Activity ◽  
Robot Path

This paper presents a new methodology based on neural dynamics for optimal robot path planning by drawing an analogy between cellular neural network (CNN) and path planning of mobile robots. The target activity is treated as an energy source injected into the neural system and is propagated through the local connectivity of cells in the state space by neural dynamics. By formulating the local connectivity of cells as the local interaction of harmonic functions, an improved CNN model is established to propagate the target activity within the state space in the manner of physical heat conduction, which guarantees that the target and obstacles remain at the peak and the bottom of the activity landscape of the neural network. The proposed methodology cannot only generate real-time, smooth, optimal, and collision-free paths without any prior knowledge of the dynamic environment, but it can also easily respond to the real-time changes in dynamic environments. Further, the proposed methodology is parameter-independent and has an appropriate physical meaning.

Sign in / Sign up

Export Citation Format

Share Document