Artificial life [Artif Life] 2017 Winter; Vol. 23 (1), pp. 80-104. Date of Electronic Publication: 2017 Jan 31.
Algorithms, Body Size, Reinforcement, Psychology, Gait, Learning, and Robotics methods
Evolutionary robotics using real hardware is currently restricted to evolving robot controllers, but the technology for evolvable morphologies is advancing quickly. Rapid prototyping (3D printing) and automated assembly are the main enablers of robotic systems where robot offspring can be produced based on a blueprint that specifies the morphologies and the controllers of the parents. This article addresses the problem of gait learning in newborn robots whose morphology is unknown in advance. We investigate a reinforcement learning method and conduct simulation experiments using robot morphologies with different size and complexity. We establish that reinforcement learning does the job well and that it outperforms two alternative algorithms. The experiments also give insights into the online dynamics of gait learning and into the influence of the size, shape, and morphological complexity of the modular robots. These insights can potentially be used to predict the viability of modular robotic organisms before they are constructed.
Artificial life [Artif Life] 2017 Spring; Vol. 23 (2), pp. 186-205. Date of Electronic Publication: 2017 May 17.
Artificial Intelligence, Computer-Aided Design instrumentation, Energy-Generating Resources, and Power Plants
Design mining is the use of computational intelligence techniques to iteratively search and model the attribute space of physical objects evaluated directly through rapid prototyping to meet given objectives. It enables the exploitation of novel materials and processes without formal models or complex simulation. In this article, we focus upon the coevolutionary nature of the design process when it is decomposed into concurrent sub-design-threads due to the overall complexity of the task. Using an abstract, tunable model of coevolution, we consider strategies to sample subthread designs for whole-system testing and how best to construct and use surrogate models within the coevolutionary scenario. Drawing on our findings, we then describe the effective design of an array of six heterogeneous vertical-axis wind turbines.
Weiss, Charles., Bonvillian, William., and Weiss, Charles.
Renewable energy sources -- Research -- Government policy -- United States., Energy policy -- United States., and Federal aid to research -- United States.
From the Publisher: America is addicted to fossil fuels, and the environmental and geopolitical costs are mounting. A federal program-on the scale of the Manhattan Project or the Apollo Program-to stimulate innovation in energy policy seems essential. In Structuring an Energy Technology Revolution, Charles Weiss and William Bonvillian make the case for just such a program. Their proposal backs measures to stimulate private investment in new technology, including a cap-and-trade system or carbon tax, but augments these with a revamped energy innovation system. It would encourage a broad range of innovations that would give policymakers a variety of technological options over the long implementation period and at the huge scale required. Using new organizational features, the program would go beyond traditional research and development efforts to promote prototyping, demonstration, and deployment of technological innovations faster than could be accomplished by market forces alone. Weiss and Bonvillian propose a new integrated policy framework for advancing energy technology and outline a four-step approach for encouraging energy innovations: assessment of how new technology will be launched, focusing on obstacles that may be encountered in the marketplace; development of technology-neutral policies and incentives, putting new technology pathways into practice to bridge the traditional "valley of death" between research and late-stage development; identification of gaps in the existing system of institutional support for energy innovation; and the establishment of private and public interventions to fill these gaps. This approach aims for a level playing field so that technologies can compete with one another on their merits. Strong leadership and public support will be needed to resist the pressure of entrenched interests against putting new technology pathways into practice. This book will help start the process.