Online Evolution of Adaptive Robot Behaviour
Online Evolution of Adaptive Robot Behaviour
复制标题
自适应机器人行为的在线进化
DOI：
10.4018/ijncr.2014040104
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
A. Christensen
中科院分区：
文献类型：
--
作者：
Fernando Silva;P. Urbano;A. Christensen
作者提出并评估了一种在线合成自主机器人神经控制器的新方法。作者将权重和网络拓扑的在线进化与神经调节学习结合起来。作者通过一系列基于模拟的实验展示了我们的方法，其中类似电子冰球的机器人必须执行动态并发觅食任务。在此任务中，分散的食物会定期改变其营养价值或变得有毒。作者证明，无论有没有神经调节，在线进化过程都能够生成很好地适应周期性任务变化的控制器。作者表明，当神经调节学习与进化相结合时，神经控制器的合成速度比单独进化更快。对进化解决方案的分析表明，由于内部动力学的主动修改，神经调节可以更有效地表达给定拓扑的潜力。神经调制网络学习任务的抽象以及由外部刺激触发的不同操作模式。
The authors propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. The authors combine online evolution of weights and network topology with neuromodulated learning. The authors demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic concurrent foraging task. In this task, scattered food items periodically change their nutritive value or become poisonous. The authors demonstrate that the online evolutionary process, both with and without neuromodulation, is capable of generating controllers well adapted to the periodic task changes. The authors show that when neuromodulated learning is combined with evolution, neural controllers are synthesised faster than by evolution alone. An analysis of the evolved solutions reveals that neuromodulation allows for a more effective expression of a given topology's potential due to the active modification of internal dynamics. Neuromodulated networks learn abstractions of the task and different modes of operation that are triggered by external stimulus.