Embodied, On-line, On-board Evolution for Autonomous Robotics
Embodied, On-line, On-board Evolution for Autonomous Robotics
复制标题
自主机器人的实体化、在线、机载进化
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Nicolas Bredèche
中科院分区：
文献类型：
--
作者：
A. Eiben;E. Haasdijk;Nicolas Bredèche
人工进化在多个机器人项目中发挥着重要作用。最常见的是，进化算法 (EA) 用作启发式优化器来解决某些工程问题，例如 EA 用于寻找良好的机器人控制器。在这些应用程序中，人类设计者/实验者编排和管理整个演化问题解决过程，并将最终结果（即 EA 演化出的（接近）最优解决方案）合并到系统中作为部署的一部分。在系统运行期间，EA 不再发挥任何作用。换句话说，进化的使用仅限于部署前阶段。另一种更具挑战性的进化应用类型是，它在运行期间（而不是之前）充当适应背后的引擎，而无需人工干预。在本节中，我们将详细阐述此类应用程序的可能进化方法，将它们放置在通用特征图上，并通过实验测试其中一些设置以评估其可行性。
Artificial evolution plays an important role in several robotics projects. Most commonly, an evolutionary algorithm (EA) is used as a heuristic optimiser to solve some engineering problem, for instance an EA is used to find good robot controller. In these applications the human designers/experimenters orchestrate and manage the whole evolutionary problem solving process and incorporate the end result –that is, the (near-)optimal solution evolved by the EA– into the system as part of the deployment. During the operational period of the system the EA does not play any further role. In other words, the use of evolution is restricted to the pre-deployment stage. Another, more challenging type of application of evolution is where it serves as the engine behind adaptation during (rather than before) the operational period, without human intervention. In this section we elaborate on possible evolutionary approaches to this kind of applications, position these on a general feature map and test some of these set-ups experimentally to assess their feasibility.