Combining environment-driven adaptation and task-driven optimisation in evolutionary robotics.
Combining environment-driven adaptation and task-driven optimisation in evolutionary robotics.
复制标题
DOI：
10.1371/journal.pone.0098466
复制
发表时间：
2014
期刊：
影响因子：
3.7
通讯作者：
Eiben AE
中科院分区：
文献类型：
--
作者：
Haasdijk E;Bredeche N;Eiben AE
具身进化机器人技术是进化机器人技术的一个子领域，它在运行期间（即以在线方式）在机器人硬件本身上采用进化算法。这使得机器人系统能够不断适应，因此能够自主（重新）调整自己以适应以前未知或动态变化的条件，而无需人工监督。本文解决了此类系统面临的主要挑战之一，即。机器人必须满足两组要求。首先，它们必须在其环境中继续可靠地运行（生存能力），其次，它们必须能够胜任用户指定的任务（有用性）。我们提出的解决方案利用了这样一个事实：进化方法有两种基本的选择机制——幸存者选择和父代选择。这使得进化能够分别解决两组要求：幸存者选择由环境驱动，父代选择基于任务表现。这个想法在多目标和开放式进化（monee）框架中得到了详细阐述，我们通过实验验证了该框架。对由 100 个模拟电子冰球组成的机器人群进行的实验表明，monee 确实可以在不影响环境适应的情况下促进任务驱动的行为。我们还研究了通过“市场机制”扩展父母选择过程，以确保在多项任务上公平分配精力，如果环境促进单一任务的专业化，这是一个特别紧迫的问题。
Embodied evolutionary robotics is a sub-field of evolutionary robotics that employs evolutionary algorithms on the robotic hardware itself, during the operational period, i.e., in an on-line fashion. This enables robotic systems that continuously adapt, and are therefore capable of (re-)adjusting themselves to previously unknown or dynamically changing conditions autonomously, without human oversight. This paper addresses one of the major challenges that such systems face, viz. that the robots must satisfy two sets of requirements. Firstly, they must continue to operate reliably in their environment (viability), and secondly they must competently perform user-specified tasks (usefulness). The solution we propose exploits the fact that evolutionary methods have two basic selection mechanisms–survivor selection and parent selection. This allows evolution to tackle the two sets of requirements separately: survivor selection is driven by the environment and parent selection is based on task-performance. This idea is elaborated in the Multi-Objective aNd open-Ended Evolution (monee) framework, which we experimentally validate. Experiments with robotic swarms of 100 simulated e-pucks show that monee does indeed promote task-driven behaviour without compromising environmental adaptation. We also investigate an extension of the parent selection process with a ‘market mechanism’ that can ensure equitable distribution of effort over multiple tasks, a particularly pressing issue if the environment promotes specialisation in single tasks.
登录
查看更多内容
影响因子：
5.3
作者：
Bianco, R;Nolfi, S
通讯作者：
Nolfi, S
影响因子：
14.3
作者：
Arnold, DV;Beyer, HG
通讯作者：
Beyer, HG
DOI：
10.1017/s0305004100009580
发表时间：
1925-01-01
影响因子：
--
作者：
Fisher, RA
通讯作者：
Fisher, RA
影响因子：
2.6
作者：
Bedau, MA;McCaskill, JS;Ray, TS
通讯作者：
Ray, TS
DOI：
10.1080/13873954.2011.601425
发表时间：
2012-01-01
影响因子：
1.9
作者：
Bredeche, Nicolas;Montanier, Jean-Marc;Winfield, Alan F. T.
通讯作者：
Winfield, Alan F. T.