Abstract
A fuzzy configuration space description method that provides the path planning solution for autonomous mobile robots in dynamically changing environment is proposed based on a hybrid planning algorithm that combines total solutions and reactive control through fuzzy proximity measures. The system (made with C++) that monitors and controls mobile robots remotely is created using a multithreaded model while taking advantage of high performance OpenGL routines to counter the increase in computational cost generated by this approach. Experiments on a real Lego robot are performed using a personal computer with a 1.5GHz Pentium4 CPU and a CCD camera. The efficiency of the hybrid algorithm and the potential of this approach, as a distributed system, in greatly changing dynamic environments are shown. The system provides a starting point for further development of distributed robotic systems, for application in human support tasks where interaction with nonprecise human behaviors are better mentioned with fuzzy parameters.
| Original language | English |
|---|---|
| Pages (from-to) | 26-34 |
| Number of pages | 9 |
| Journal | Journal of Advanced Computational Intelligence and Intelligent Informatics |
| Volume | 10 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - Jan 2006 |
| Externally published | Yes |
Keywords
- Mobile robot
- fuzzy configuration space
- fuzzy proximity measure
- multithreaded models
- path planning