NUST Institutional Repository
Trajectory Optimization and Obstacle Avoidance of Autonomous Vehicles Using Robust and Efficient Rapidly Exploring Random Tree (RE-RRT*)
- DSpace Home
- →
- E-Theses
- →
- CEME
- →
- Computer Software Engineering
- →
- MS
- →
- View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Gul, Kaynat | |
| dc.date.accessioned | 2023-07-11T08:55:26Z | |
| dc.date.available | 2023-07-11T08:55:26Z | |
| dc.date.issued | 2023 | |
| dc.identifier.other | 00000330764 | |
| dc.identifier.uri | http://10.250.8.41:8080/xmlui/handle/123456789/34555 | |
| dc.description | Supervisor: Dr Naeem Ul Islam | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | College of Electrical & Mechanical Engineering (CEME), NUST | en_US |
| dc.title | Trajectory Optimization and Obstacle Avoidance of Autonomous Vehicles Using Robust and Efficient Rapidly Exploring Random Tree (RE-RRT*) | en_US |
| dc.type | Thesis | en_US |
| dcterms.abstract | One of the key issues in robotics is the motion planning problem. This study provides a local trajectory planning and obstacle avoidance strategy based on the Rapidly exploring Random Tree algorithm for autonomous vehicles to handle the issue of travelling in complicated surroundings. Rapidly Exploring Random Trees (RRT), a sampling-based pathfinding algorithm, has been extensively employed in motion planning issues. The RRT algorithm still has several limitations, including a sluggish convergence rate, significant search time volatility, a vast dense sample space, and unsmooth search routes. In this study, we suggest RE-RRT*(Robust and Efficient RRT*), a new RRT-based pathfinding algorithm. which extends Rapidly exploring Random Tree (RRT*), to identify a speedy path that is close to optimal. The Choose Parent and Rewire processes are used by RE-RRT* to continuously improve the path in succeeding cycles. The sample space is constrained during each stage of the random tree's growth., so reducing the number of pointless searches. The RE-RRT* algorithm can converge to a shorter path with a smaller number of iterations and be smoother, according to simulation and experimental results under diverse obstacle settings. The suggested method can increase search effectiveness, speed up convergence, and decrease processing time. Due to these advantages, our suggested RE-RRT* beats RRT* in experiments in terms of computational time, sampling space, speed, and stability |
Files in this item
This item appears in the following Collection(s)
-
MS [441]