Motion Planning of a Spherical Robot Using eXtended Classifier Systems
محل انتشار: بیست و یکمین کنفرانس مهندسی برق ایران
سال انتشار: 1392
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 961
فایل این مقاله در 6 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEE21_322
تاریخ نمایه سازی: 27 مرداد 1392
چکیده مقاله:
In comparison to wheeled robots, spherical mobile robots offer greater mobility, stability, and cope for operation in hazardous environments. In this paper, we propose a direct approach to motion planning based on the notion of Learning Agents” wherein the motions of the robot at consecutive time-steps are determined by a set of condition-action rules that embody the agent. While traditional motion planning schemes rely on pre-planned optimal trajectories and/or feedback control techniques, the learning agent approach enjoys a model-free methodology that enables the robot to function in semi- or even non-observable environments. The approach presented in this paper employs the eXtended Classifier System (XCS) as its learning agent. Results from numerous simulated experiments show that the proposed approach is capable of adopting a near-optimal path towards a predefined goal point from any given position/orientation.
کلیدواژه ها:
نویسندگان
M. J. Esfandyari
School of Mechanical Engineering, University of Tehran, Tehran, Iran
M Roozegar
Center for Mechatronics and Automation, School of Mechanical Engineering, University of Tehran
M Shariat Panahi
School of Mechanical Engineering, University of Tehran, Tehran, Iran
M. Mahjoob
Center for Mechatronics and Automation, School of Mechanical Engineering, University of Tehran