Affiliation:
1. Department of Computer Science and Engineering Auburn University, Alabama
2. NASA Center for Autonomous Control Engineering North Carolina A&T State University Greensboro, North Carolina
Abstract
In this paper we show a relationship between artificial potential field (APF) based motion planning/navigation, and constrained optimi zation. We then present a simple genetic hill climbing algorithm (SGHC), which is used to navigate a point robot through an environ ment using the APF approach. We compare SGHC with steepest descent hill climbing (SDHC). In SDHC, candidate moves are evaluated within a 360-degree radius and the best candidate is selected by the robot. One would think that SGHC would be at a disad vantage ; however, the performance of SGHC is comparable with SDHC. SGHC has an advantage in that it is capable of evolving (learning) the appropriate step size as well as the appropriate angle of movement.
Subject
Computer Graphics and Computer-Aided Design,Modeling and Simulation,Software
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Using haptic feedbacks for obstacle avoidance in helicopter flight;Progress in Flight Dynamics, Guidance, Navigation, and Control – Volume 10;2018
2. Automatic Parameter Identification for Mechatronic Systems;Multibody System Dynamics, Robotics and Control;2012-11-06
3. Exponential navigation functions with a learning algorithm;2008 American Control Conference;2008-06