• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Tools with Artificial Intelligence >New Bio-Inspired Coordination Strategies for Multi-Agent Systems Applied to Foraging Tasks
【24h】

New Bio-Inspired Coordination Strategies for Multi-Agent Systems Applied to Foraging Tasks

机译：适用于觅食任务的多智能体系统的新生物启发式协调策略

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Multiple agent systems can be applied to foraging tasks, thus solving this problem in a cooperative approach. The major processes performed by a forager agent are searching and homing. A new coordination searching strategy inspired on Tabu Search is reported here by modifying a previous probabilistic cellular automata ant memory model. Moreover, new homing strategies based on ants behavior and cellular automata are investigated. Combining bio-inspired searching and homing strategies, we propose a new coordination model for foraging in robotics called Hybrid Cellular Automata Ant Queue model, or HCAAQ for short. The model is able to adapt the current system dynamics if either the number of robots or the environment structure change. Experimental simulations were conducted to evaluate different versions of memory policies, resulting in a new homing strategy based on ants communication by inverted pheromone. Besides, simulations confirm that the new homing strategy proposed herein distributes agents equitably between the nests, accelerating the task performance. As a result, using the new team coordination it is possible to avoid lines forming near the nests, specially when the robot number has increased, thus outperforming previous models. The proposed method was implemented in a robotics simulation environment called Webots to better investigate the application of the multi-agent system. Simulation results indicate that the HCAAQ proposed herein could be implemented in multi-robot systems.
机译：可以将多个代理系统应用于搜寻任务，从而以协作方式解决此问题。觅食者代理执行的主要过程是搜索和归巢。通过修改以前的概率细胞自动机记忆模型，在此报告了一种在禁忌搜索中得到启发的新的协调搜索策略。此外，研究了基于蚂蚁行为和细胞自动机的新归巢策略。结合生物启发的搜索和归位策略，我们提出了一种用于机器人技术中觅食的新协调模型，称为混合细胞自动机蚂蚁队列模型，简称HCAAQ。如果机器人的数量或环境结构发生变化，则该模型能够适应当前的系统动态。进行了实验仿真以评估不同版本的内存策略，从而产生了一种新的基于反向信息素与蚂蚁通信的归巢策略。此外，模拟证实了本文提出的新的归巢策略可以在巢之间平均分配代理，从而加快了任务执行速度。结果，使用新的团队协作，可以避免在巢附近形成线条，特别是在机器人数量增加时，因此表现优于以前的模型。所提出的方法在名为Webots的机器人仿真环境中实现，以更好地研究多智能体系统的应用。仿真结果表明，本文提出的HCAAQ可以在多机器人系统中实现。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号