A novel path planning approach based on AppART and particle swarm optimization

Authors:
Jian Tang;Jihong Zhu;Zengqi Sun
Affiliations:
State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China;State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China;State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part III
Year:
2005

Citing 2
Cited 3

Gross motion planning—a survey

ACM Computing Surveys (CSUR)
Robot Motion Planning

Robot Motion Planning

Modeling and control of biologically inspired flying robots

Robotica
An efficient method for segmentation of images based on fractional calculus and natural selection

Expert Systems with Applications: An International Journal
Robot path planning in uncertain environment using multi-objective particle swarm optimization

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Due to the NP-hard complexity, the path planning problem may perhaps best be resolved by stochastically searching for an acceptable solution rather than using a complete search to find the guaranteed best solution. Most other evolutionary path planners tend to produce jagged paths consisting of a set of nodes connected by line segments. This paper presents a novel path planning approach based on AppART and Particle Swarm Optimization (PSO). AppART is a neural model multidimensional function approximator, while PSO is a promising evolutionary algorithm. This path planning approach combines neural and evolutionary computing in order to evolve smooth motion paths quickly. In our simulation experiments, some complicated path-planning environments were tested, the result show that the hybrid approach is an effective path planner which outperforms many existing methods.