Sampling-based motion planning algorithms with the aim to improve the preprocessing Speed of the RRT* algorithm
Publish place: The Second International Conference and the Third National Conference on the Application of New Technologies in Engineering Sciences
Publish Year: 1394
نوع سند: مقاله کنفرانسی
زبان: English
View: 450
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ITCC02_233
تاریخ نمایه سازی: 21 شهریور 1395
Abstract:
In this paper, have been proposed an algorithm based on sampling in order to motion planning multi-robot systems with IPSRRT* name that the aim of it is the RRT* algorithm preprocessing accelerating. The used Strategies in the in IPSRRT* algorithm: 1. the forming and development of two independent random trees of two end point and start point. 2. The sampling based success rate of start and end point. 3. the sampling of middle zone of two start and target zone according to success probability predicting in the future steps and weights assigning to environment different areas for increasing and decreasing of randomly point probability of each zone (all environment points with different probability percent have chance to participate in a random sample choice.)Finally, the proposed algorithm tested in Webots simulator and it’s results compared with TGRRT* ،RRT and RRT* algorithms. The tests results showed that proposed algorithm not only increases the preprocessing speed but also provide shorter route than providing other algorithms.
Keywords:
Authors
Raheleh NickAmal
Robotic Dept,Amirkabir University of Technology
Ali Mohades
Computer Science,Amirkabir University of Technology
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :