scholarly journals Bootstrapping Artificial Evolution to Design Robots for Autonomous Fabrication

Robotics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 106
Author(s):  
Edgar Buchanan ◽  
Léni K. Le Goff ◽  
Wei Li ◽  
Emma Hart ◽  
Agoston E. Eiben ◽  
...  

A long-term vision of evolutionary robotics is a technology enabling the evolution of entire autonomous robotic ecosystems that live and work for long periods in challenging and dynamic environments without the need for direct human oversight. Evolutionary robotics has been widely used due to its capability of creating unique robot designs in simulation. Recent work has shown that it is possible to autonomously construct evolved designs in the physical domain; however, this brings new challenges: the autonomous manufacture and assembly process introduces new constraints that are not apparent in simulation. To tackle this, we introduce a new method for producing a repertoire of diverse but manufacturable robots. This repertoire is used to seed an evolutionary loop that subsequently evolves robot designs and controllers capable of solving a maze-navigation task. We show that compared to random initialisation, seeding with a diverse and manufacturable population speeds up convergence and on some tasks, increases performance, while maintaining manufacturability.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hiroshi Okamura ◽  
Yutaka Osada ◽  
Shota Nishijima ◽  
Shinto Eguchi

AbstractNonlinear phenomena are universal in ecology. However, their inference and prediction are generally difficult because of autocorrelation and outliers. A traditional least squares method for parameter estimation is capable of improving short-term prediction by estimating autocorrelation, whereas it has weakness to outliers and consequently worse long-term prediction. In contrast, a traditional robust regression approach, such as the least absolute deviations method, alleviates the influence of outliers and has potentially better long-term prediction, whereas it makes accurately estimating autocorrelation difficult and possibly leads to worse short-term prediction. We propose a new robust regression approach that estimates autocorrelation accurately and reduces the influence of outliers. We then compare the new method with the conventional least squares and least absolute deviations methods by using simulated data and real ecological data. Simulations and analysis of real data demonstrate that the new method generally has better long-term and short-term prediction ability for nonlinear estimation problems using spawner–recruitment data. The new method provides nearly unbiased autocorrelation even for highly contaminated simulated data with extreme outliers, whereas other methods fail to estimate autocorrelation accurately.


Author(s):  
Marcus Pietsch ◽  
Pierre Tulowitzki ◽  
Colin Cramer

Both organizational and management research suggest that schools and their leaders need to be ambidextrous to secure prosperity and long-term survival in dynamic environments characterized by competition and innovation. In this context, ambidexterity refers to the ability to simultaneously pursue exploitation and exploration and thus to deliver efficiency, control and incremental improvements while embracing flexibility, autonomy and discontinuous innovation. Using a unique, randomized and representative data set of N = 405 principals, we present findings on principals’ exploitation and exploration. The results indicate: (a) that principals engage far more often in exploitative than in explorative activities; (b) that exploitative activities in schools are executed at the expense of explorative activities; and (c) that explorative and ambidextrous activities of principals are positively associated with the (perceived) competition between schools. The study brings a novel perspective to educational research and demonstrates that applying the concept of ambidexterity has the potential to further our understanding of effective educational leadership and management.


Author(s):  
Paul L. Joskow

Abstract Electric power sectors around the world have changed dramatically in the last 25 years as a result of sector liberalization policies. Many electricity sectors are now pursuing deep decarbonization goals which will entail replacing dispatchable fossil generation primarily with intermittent renewable generation (wind and solar) over the next 20–30 years. This transition creates new challenges for both short-term wholesale market design and investment incentives consistent with achieving both decarbonization commitments and security of supply criteria. Thinking broadly about the options for institutional change from a Williamsonian perspective – thinking like Williamson – provides a useful framework for examining institutional adaptation. Hybrid markets that combine ‘competition for the market’ that relies on competitive procurement for long-term purchased power agreements with wind, solar, and storage developers, ideally in a technology neutral fashion, and ‘competition in the market’ that relies on short-term markets designed to produce efficient and reliable operations of intermittent generation and storage, is identified as a promising direction for institutional adaptation. Many auction, contract, and market integration issues remain to be resolved.


Indoor Air ◽  
2021 ◽  
Author(s):  
Shide Salimi ◽  
Esteban Estrella Guillén ◽  
Holly Samuelson

1998 ◽  
Vol 4 (4) ◽  
pp. 311-335 ◽  
Author(s):  
Stefano Nolfi ◽  
Dario Floreano

Coevolution (i.e., the evolution of two or more competing populations with coupled fitness) has several features that may potentially enhance the power of adaptation of artificial evolution. In particular, as discussed by Dawkins and Krebs [3], competing populations may reciprocally drive one another to increasing levels of complexity by producing an evolutionary “arms race.” In this article we will investigate the role of coevolution in the context of evolutionary robotics. In particular, we will try to understand in what conditions coevolution can lead to “arms races.” Moreover, we will show that in some cases artificial coevolution has a higher adaptive power than simple evolution. Finally, by analyzing the dynamics of coevolved populations, we will show that in some circumstances well-adapted individuals would be better advised to adopt simple but easily modifiable strategies suited for the current competitor strategies rather than incorporate complex and general strategies that may be effective against a wide range of opposing counter-strategies.


2019 ◽  
Vol 6 (2) ◽  
pp. 1-12
Author(s):  
Gesoon j.k Al-Abass ◽  
Huda R. ALkifaey

"Internet of things (IoT) domain targets human with smart resolutions through the connection of “M2M” in all over the world, effectively. It was difficult to ignore domain importance field of IoT with the new deployment of applications such as smartphone in recent days. The most important layer in architecture of IoT is network layer, because of various systems (perform of cloud computing, switching, hub, gateway, so on), different technologies of connection (Long-Term Evolution (LTE), WIFI, Bluetooth, etc.) gathered in layer. Network layers should transfer the information from or to various applications/objects, via gateways/interfaces between networks that are heterogeneous, therefore utilizing different connection technologies, protocols. Recent work highlighted IoT technologies state-of-the-art utilized in architectures of IoT, some variations among them in addition to the applications of them in life."


Sign in / Sign up

Export Citation Format

Share Document