Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476639Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Mohd Zakree Ahmad Nazri, Dr. | |
| dc.contributor.author | Mohammad Naim Rastgoo (P61035) | |
| dc.date.accessioned | 2023-10-06T09:23:01Z | - |
| dc.date.available | 2023-10-06T09:23:01Z | - |
| dc.date.issued | 2014-03-12 | |
| dc.identifier.other | ukmvital:122305 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476639 | - |
| dc.description | In the last few years, using autonomous robots in dynamic environments, which are populated, by dynamic and static objects have become very popular. Dynamic environment changes continuously and the robot should be able to track its surrounding changing therefor planning and execution of its future motions must be done for a short time. To plan for the robot’s motions with incomplete initial robot’s information about its environment, Real-time search is known as a proper and standard method. In our domain, when the number of depression regions in the dynamic environment increase that is due to the high density of static obstacles, the real-time heuristic search algorithms easily trap into those regions and increase the cost of solutions. The depression regions called bounded areas in the environment that their heuristic values are inaccurate in compare with the actual cost to reach the solution. The best known real-time heuristic search algorithm in dynamic environment is PLRTA*, presented a new mechanism base on the partitioning static and dynamic heuristic costs and learns them separately but the searching strategy of this algorithm are poor in the environment with the increasing number of depression regions. This means, PLRTA* has tendency to search the depression regions and learn more dynamic heuristic costs in those regions rather than to search other regions to learn other effective dynamic heuristic costs. In this paper, we present a new version of PLRTA*that is called DAPLRTA*. This method can avoid the heuristic depression regions that result in decreasing the search time and cost of the solutions. To validate the effectiveness and usefulness of these algorithms, we developed a simulation environment for conducting simulation-based experiments in different scenarios.,Master of Science,Certification of Master's / Doctoral Thesis" is not available" | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Robots -- Motion | |
| dc.subject | Heuristic algorithms | |
| dc.subject | Universiti Kebangsaan Malaysia -- Dissertations | |
| dc.subject | Dissertations, Academic -- Malaysia | |
| dc.title | Robot motion planning using partitioned heuristic depression avoidance technique in dynamic environment | |
| dc.type | theses | |
| dc.format.pages | 91 | |
| dc.identifier.callno | QA76.9.A43R374 2014 3 tesis | |
| dc.identifier.barcode | 005606(2021)(PL2) | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_122305+SOURCE1+SOURCE1.0.PDF Restricted Access | 17.86 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.