DEVELOPMENT MOBILE ROBOT CONTROL ARCHITECTURE WITH INTEGRATED PLANNING AND CONTROL ON LOW COST MICROCONTROLLER
| Main Author: | Nurmaini, Siti |
|---|---|
| Format: | Article NonPeerReviewed application/pdf |
| Terbitan: |
Little Lion Scientific
, 2012
|
| Subjects: | |
| Online Access: |
http://eprints.unsri.ac.id/425/1/12Vol35No1.pdf http://www.jatit.org http://eprints.unsri.ac.id/425/ |
Daftar Isi:
- This paper presents new hybrid control architecture-based interval type-2 nuro-fuzzy (IT2NF) forembedded mobile robot navigation where event-driven control is used to handle the dynamically changing of the environment. The proposed hybrid control architecture combining behavior-based reactive navigation and model-based environmental classification has been developed. Weightless neural network (WNNs) in charge of environmental classification, this strategy does not only enable the mobile robot to avoid local minimum points but also eliminates the requirement for prior detailed modeling of the environment. Then, IT2FLC based reactive behavior is utilized to perform mobile robot navigation task use environmental pattern classification. The previous study show that embedded controller on low cost microcontroller is difficult to design due to hardware and software constraints. In this paper, the hybrid control architecture uses hierarchical structure of IT2 fuzzy sets (IT2FS) to avoid the huge rule base due to the embedded platform and modular structure of WNNs to reduce the computational cost and increases processing speed of the controller. Technologies to address these limitations are integrated into hybrid controller architecture to be carried out, thus the autonomous mobile robot navigation system can be executed successfully. Flexibility and performance of the proposed control architecture is validated through experiments on the real embedded mobile robot in a variety of environmental condition. The experimental results show that, the proposed architecture-based IT2NF has dealt in real environment with uncertainties present in the changing and unstructured environments can avoid obstacles at the desired safe distance, follow the desired trajectory in smooth movement and produces minimal computational resources.