当前位置: X-MOL 学术Nat. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Disentangling automatic and semi-automatic approaches to the optimization-based design of control software for robot swarms
Nature Machine Intelligence ( IF 18.8 ) Pub Date : 2020-08-10 , DOI: 10.1038/s42256-020-0215-0
Mauro Birattari , Antoine Ligot , Ken Hasselmann

Optimization-based design is an effective and promising approach to realizing collective behaviours for robot swarms. Unfortunately, the domain literature often remains vague about the exact role played by the human designer, if any. It is our contention that two cases should be disentangled: semi-automatic design, in which a human designer operates and steers an optimization process (for example, by fine-tuning the parameters of the optimization algorithm); and (fully) automatic design, in which the optimization process does not involve, need or allow any human intervention. In this Perspective, we briefly review the relevant literature; illustrate the hypotheses, characteristics and core challenges of semi-automatic and automatic design; and sketch out the context in which they could be ideally applied.



中文翻译:

分解自动和半自动方法,以优化为基础的机器人群体控制软件设计

基于优化的设计是一种有效且有前途的方法,可以实现机器人群体的集体行为。不幸的是,领域文献通常对于人类设计师(如果有的话)所扮演的确切角色仍然模糊不清。我们的争论是,两种情况应该分开处理:半自动设计,即由人工设计人员操作和指导优化过程(例如,通过微调优化算法的参数);(完全)自动设计,其中不涉及优化过程,不需要或允许任何人工干预。在此观点中,我们简要回顾了相关文献;说明半自动和自动设计的假设,特征和核心挑战;并勾勒出理想的应用环境。

更新日期:2020-08-10
down
wechat
bug