在NEAT中使用门控递归单元的演进室内导航策略
Evolving Indoor Navigational Strategies Using Gated Recurrent Units In NEAT
摘要:
同步定位和映射(SLAM)算法在小型机器人平台(如微型飞行器)上运行成本很高。Bug算法是一种使用相对较少的处理能力的替代方案,并且通过不构建环境的显式映射来避免高内存消耗。Bug算法在模拟迷宫和机器人迷宫求解领域取得了较好的性能。然而,因为它们是手工设计的,一个自然的问题是它们是否是全局最优控制策略。在这项工作中,我们探讨了性能的神经进化-特别是NEAT -在不断发展的控制策略,模拟差分驱动机器人进行广义迷宫导航。我们扩展了NEAT以包括门控循环单元(GRU),以帮助处理长期依赖关系。我们表明,NEAT和我们的NEAT-GRU可以重复生成控制器,优于I-Bug(一种特别适合用于真实机器人的算法)的测试集209室内迷宫一样的环境。我们表明,NEAT-GRU是优于NEAT在这项任务中,但也出了2个系统,只有NEAT-GRU可以不断发展成功的控制器更难的任务,其中没有轴承的目标信息提供给代理。
英文摘要:
Simultaneous Localisation and Mapping (SLAM) algorithms are expensive to run on smaller robotic platforms such as Micro-Aerial Vehicles. Bug algorithms are an alternative that use relatively little processing power, and avoid high memory consumption by not building an explicit map of the environment. Bug Algorithms achieve relatively good performance in simulated and robotic maze solving domains. However, because they are hand-designed, a natural question is whether they are globally optimal control policies. In this work we explore the performance of Neuroevolution - specifically NEAT - at evolving control policies for simulated differential drive robots carrying out generalised maze navigation. We extend NEAT to include Gated Recurrent Units (GRUs) to help deal with long term dependencies. We show that both NEAT and our NEAT-GRU can repeatably generate controllers that outperform I-Bug (an algorithm particularly well-suited for use in real robots) on a test set of 209 indoor maze like environments. We show that NEAT-GRU is superior to NEAT in this task but also that out of the 2 systems, only NEAT-GRU can continuously evolve successful controllers for a much harder task in which no bearing information about the target is provided to the agent.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。